# askFinz — Full content index
> Source: https://askfinz.com/llms-full.txt  |  See also: https://askfinz.com/llms.txt

askFinz (also: askfinz, AskFinz, ask finz, finz, finz AI) is an AI platform with 29 purpose-built workspaces sharing one memory layer, one login, and a model router. A subsidiary of PAUL V | Holdings. Currently in private access.

## Platform

askFinz routes every query to the best AI model from 10 cloud providers: OpenAI, Gemini, Mistral, Llama, Qwen, DeepSeek, Moonshot, NVIDIA NIM, Z.ai, Google Cloud. The browser extension adds 380+ models that run on-device with no data leaving the browser.

### Platform capabilities

- **Multi-model, one mind.** Route any question to the right model — automatically. Switch by hand whenever you like.
- **Agents that finish the job.** An agent for research, an agent for code, an agent for the live web. Composable. Persistent. Patient.
- **A workspace per discipline.** Chat, research, code, finance, medicine, learning. Each its own room, all sharing one memory.
- **Cite the source. Always.** Research mode never makes a claim it can't back. Footnotes are first-class.
- **Run a browser, watch it work.** The Navigator drives a real browser and streams it back to you. You stay in the loop.
- **Your data, your perimeter.** Sensitive workspaces have their own database with isolated credentials and encryption.

### Surfaces

**Browser extension** [shipping] — https://askfinz.com/extension
A side panel that brings askFinz to whatever you're reading, without leaving the page.

**Desktop** [shipping] — https://askfinz.com/desktop
A desktop client for Windows, macOS and Linux that wraps your workspaces and works offline when you do.

**askFinz OS** [beta] — https://askfinz.com/os
A purpose-built Linux distro (Ubuntu 24.04 LTS + k3s + KubeVirt) for workstations, servers and IoT devices. Kiosk into the askFinz cloud on top; a managed compute node the cloud schedules workloads onto underneath.

## Workspaces (20 live)

### Chat — https://askfinz.com/apps/chat
Status: shipping  |  Switch between AI minds in a single thread. Bring files, keep history.

### Research — https://askfinz.com/apps/research
Status: shipping  |  Notebooks that read, synthesise and reference. Branch, version, merge — turn a question into a defensible answer.

### Code — https://askfinz.com/apps/code
Status: shipping  |  Projects, deployments, templates, a pair-programmer that reads the room. A home for the work between commits.

### News — https://askfinz.com/apps/news
Status: shipping  |  Many sources, deduplicated and clustered, with a daily audio briefing you can listen to.

### Search — https://askfinz.com/apps/search
Status: shipping  |  askFinz's own search engine. Built so a human, an agent or a model can ask the same question and get back something they can each use.

### Dash — https://askfinz.com/apps/dash
Status: shipping  |  Dash is the internal control panel for askFinz operators and account admins. Account-wide config, billing, model usage, audit trails and observability — not a public product.

### Storage — https://askfinz.com/apps/storage
Status: shipping  |  Drag, drop, share and recover. A recycle bin, link sharing and quick search over your files.

### Train — https://askfinz.com/apps/train
Status: beta  |  Run a fine-tune, watch the progress, ship the result. Roll back when you need to. Adapt a base model on your own data and deploy it next to the catalog.

### Workflow — https://askfinz.com/apps/workflow
Status: beta  |  A visual pipeline builder. Wire askFinz into the way you already work — triggers, steps, AI calls, retries. Pipelines that run while you sleep.

### Mail & Calendar — https://askfinz.com/apps/mail
Status: shipping  |  Email and calendar with an agent on call. Triage, drafts in your voice, and scheduling across calendars.

### Estate — https://askfinz.com/apps/estate
Status: beta  |  Listings with the questions you forgot to ask, answered upfront.

### Travel — https://askfinz.com/apps/travel
Status: beta  |  Flights, hotels, cars and activities — drafted, costed, booked, all inside one workspace. Live carrier inventory, transparent pricing, multi-stage round-trip selection, heatmap seat picker, tight-connection warnings and a discovery map of where you can fly from your home airport this year.

### Stream — https://askfinz.com/apps/stream
Status: beta  |  A creator media platform — upload video and music, go live from OBS, and earn from your audience in credits, with Finz AI assisting hosts and viewers throughout.

### Shop — https://askfinz.com/apps/shop
Status: beta  |  An e-commerce workspace where anyone can spin up a storefront — products, checkout, payments, orders, analytics. The order pipeline is wired to Mail and Workflow from day one, so receipts, shipping events and returns are built-in, not bolted on.

### Map — https://askfinz.com/apps/map
Status: shipping  |  A real-time map service for every workspace and a destination-grade app in its own right. Live ADS-B aircraft, AIS vessels, ~10k satellites tracked client-side, weather, airports, ocean / pollution / events overlays, plus geocoding and tile services every other askFinz workspace reaches into when it needs a pin, a route or a polygon.

### Create — https://askfinz.com/apps/create
Status: beta  |  An AI studio for generating, editing and remixing images and video. A layered editor for non-destructive image work, a timeline editor for video, an asset library shared with Storage, and a cost dial visible at every step.

### Projects — https://askfinz.com/apps/project
Status: shipping  |  Projects, sprints, boards and issues — with dependencies, burndown, automations and cross-project roll-ups.

### Socials — https://askfinz.com/apps/socials
Status: beta  |  Connect every account, schedule across networks, analyse what's landing. One queue for posts, one calendar, one place to see how a thread travelled.

### Feedback — https://askfinz.com/apps/feedback
Status: shipping  |  The public feedback portal for the askFinz platform. Report bugs with severity and reproduction steps, request features with a why and examples, and vote on what the team should build next. Staff triage issues in real time — status changes, comment threads and resolution banners are visible to everyone the moment they happen.

### Access — https://askfinz.com/apps/access
Status: beta  |  Your identity layer for askFinz — single sign-on, sessions, billing, devices, recovery. Built to plug into askFinz OS so a fresh workstation comes online already signed in, with the workspaces, browser and extension already configured.

## AI Agents (51+ across 10 groups)

Full catalogue: https://askfinz.com/agents

### Foundational — Shared across apps
A small set of always-on pieces that route a prompt to the right specialist, plan multi-step work, and check the result before it reaches you.

- **Thinker** [shipping]: Reads the prompt and classifies intent, complexity and entities.
- **Planner** [shipping]: Breaks a task into ordered steps, each tagged with the kind of specialist it needs.
- **Router** [shipping]: Matches every step to the best-fit agent and the right depth of reasoning.
- **Executor** [shipping]: Runs the plan step by step, streaming each event so you can watch the work happen.
- **Reflector** [shipping]: Reviews the finished result against the brief and asks for a retry when quality is short.
- **Ingestor** [shipping]: Pulls relevant memory, prior work and uploaded files into context before the model sees them.
- **A2A Bridge** [beta]: Speaks the open agent-to-agent protocol so external agents can ask askFinz to do real work.

### Research — research.askfinz.ai
A reading room that browses for you, argues with itself, and writes only what it can cite.

- **Deep Researcher** [shipping]: Plans, browses and synthesises a long-form study, streaming every step.
- **Council** [shipping]: Runs the same prompt across several minds in parallel, then a judge merges the strongest drafts.
- **Critic** [shipping]: Generator + reviewer pair — scores a draft against a rubric and sends it back for one revision.
- **Source Matrix** [shipping]: Reads N sources across M questions and fills a comparison grid with a confidence score per cell.
- **Citation Lens** [shipping]: Pulls inbound citations for any source and labels each one as supporting, contradicting or neutral.
- **Reviewer** [shipping]: Lint, gap analysis and rubric scoring on a draft — surfaces uncited claims and missing sections.
- **Library Trainer** [beta]: Licences public-library documents for training, settles royalties and tracks owner credits.
- **Template Extractor** [shipping]: Reads any document and proposes a reusable structure you can apply to the next study.
- **Suggestion Reviewer** [shipping]: Turns tracked-change proposals into accept/reject decisions with an audit trail.

### Code — code.askfinz.ai
A pair-programmer that lives in the editor and a small army of specialists you can call when the work needs more than one head.

- **Code Agent** [shipping]: Pairs in the editor — reads the repo, edits files, runs commands, answers in your terminal.
- **Inline Agent** [shipping]: Highlight a span of code and ask for the rewrite right there; preview the diff before accepting.
- **Swarm** [shipping]: Run several code agents at once on the same prompt or on independent slices of a task.
- **Coordinator** [shipping]: Lets the main agent spawn sub-agents on its own and weave their answers into one reply.
- **Sub-agent Spawner** [shipping]: Drops a focused agent onto a sub-task with its own scratchpad, then hands the result back.
- **Ultraplan** [beta]: Multi-agent planning — parallel planners propose approaches, the best parts get merged.
- **Batch Worker** [shipping]: Runs thousands of prompts through a model in one cheap overnight job and streams results as ready.
- **Skills** [shipping]: Reusable role packs (refactor, test, review, debug, security, optimise) the agent loads on demand.
- **Hooks Runner** [shipping]: Fires shell commands before, during or after a tool call so your project rules stay enforced.
- **Tool Server** [shipping]: Exposes the workspace as a tool registry so other agents — even ones outside askFinz — can call it.
- **Live Collaborator** [beta]: Cursor presence, real-time cursors and shared selections when more than one person is in the file.
- **Bug Hunter** [shipping]: A specialised mode that hardens its prompt for reproducing, isolating and fixing nasty bugs.

### Chat — chat.askfinz.ai
Specialists you can summon by role inside any conversation — and one general-purpose mind that knows when to hand off.

- **Researcher** [shipping]: Reads broadly, cross-references claims, cites sources and structures the answer.
- **Coder** [shipping]: Generates, reviews, debugs and refactors code in any major language.
- **Writer** [shipping]: Drafts, edits and rewrites to a target tone — clean structure, plain language.
- **Analyst** [shipping]: Works with numbers — tables, comparisons, charts and quantitative reasoning.
- **Summariser** [shipping]: Distils long content into the essentials with a structured outline and TL;DR.
- **Advisor** [beta]: Secondary mind running alongside the primary, surfacing alternative suggestions as you go.

### News — news.askfinz.ai
Crawls, deduplicates, listens — turns the firehose into a single briefing and a daily audio version you can play.

- **Crawler** [shipping]: Reaches into hundreds of publishers, extracts full articles and keeps the index fresh.
- **Analyst** [shipping]: Sentiment, bias and category — every story scored so the briefing reads honestly.
- **Briefing Host** [shipping]: Builds the hourly transcript across today's top stories and renders it as audio.
- **Risk Watcher** [beta]: Scans the headline window for sector and ticker risk signals over a rolling fourteen-day view.

### Browser — Cross-app capability
A real browser an agent can drive — for the times the web won't give you an API.

- **Navigator** [shipping]: Drives a real, headed browser to read pages, follow flows and fill forms — with a screencast.
- **Proxy Manager** [shipping]: Rotates clean exit-IPs and degrades gracefully so a brittle site doesn't end the session.

### Search — search.askfinz.ai
askFinz's own search index — keeps every workspace findable for humans, agents and other models.

- **Indexer** [shipping]: Reads every workspace and keeps the askFinz vector index in sync as you work.
- **Index Reviewer** [shipping]: Sweeps the index for stale, broken or low-quality entries and quietly heals them.

### Workflow — workflow.askfinz.ai
Drag-and-drop flows that the platform can execute on a schedule or on demand.

- **Workflow Runner** [shipping]: Executes a custom flow you've designed — connects steps, ships the output, logs the run.

### Memory — Cross-app capability
What every other agent leans on so it doesn't forget you between sessions.

- **Memory Keeper** [shipping]: Saves the facts you ask it to remember and pulls them back into future conversations.
- **Team Memory** [shipping]: Shares a project-scoped memory across collaborators with last-write-wins reconciliation.
- **Dreamer** [beta]: Once a week, distils recent session logs into durable project memory you can review.
- **Memory Searcher** [shipping]: Semantic recall across everything memory has ever held — surfaces the right fact, fast.

### Safety — Cross-app capability
The pieces that say no on your behalf — so a fast agent never becomes a destructive one.

- **Permissions** [shipping]: Per-tool approval rules with wildcard allow/deny so risky actions always pause for you.
- **Diff Reviewer** [shipping]: Queues every file write for inspection before it lands — accept, reject or rewrite the patch.
- **Sandbox** [shipping]: Restricts which files and domains an agent may touch, even when it is told to do more.
- **Verifier** [beta]: Cross-checks an action against your stated intent before money is spent or content is sent.

## Orchestrator

The askFinz Orchestrator coordinates work across agents. It classifies intent, plans steps, routes to specialists, executes in parallel, reviews quality, and integrates memory — all without manual configuration.

- **Intent Classification**: The Thinker agent reads your prompt and classifies intent, complexity, and required capabilities before routing.
- **Multi-Step Planning**: The Planner breaks complex tasks into ordered steps, each tagged with the specialist agent needed.
- **Dynamic Routing**: The Router matches each step to the best-fit agent based on capabilities, current load, and reasoning depth required.
- **Parallel Execution**: Independent steps run in parallel. The Executor coordinates timing and merges results when dependencies resolve.
- **Quality Review**: The Reflector checks finished work against the original brief and requests retries when quality falls short.
- **Memory Integration**: The Ingestor pulls relevant context from prior conversations, uploaded files, and saved work before execution.

## Protocols

Full details: https://askfinz.com/protocols

The askFinz Orchestrator coordinates work across agents using open protocols for agent interoperability. External agents and tools can call askFinz and vice versa.

**A2A (Agent-to-Agent)** [Shipping]
Agents communicate directly with each other to coordinate complex tasks. The askFinz Orchestrator routes work between specialized agents using structured messages.
Use: Internal agent coordination, sub-agent spawning, parallel task execution

**MCP (Model Context Protocol)** [Shipping]
Anthropic's open standard for connecting AI systems to external data sources and tools. askFinz agents can call MCP servers you configure.
Use: External tool integration, custom data sources, third-party services

**ACP (Agent Communication Protocol)** [Shipping]
IBM's open protocol for structured agent communication and interoperability across different AI systems.
Use: Cross-vendor agent communication, enterprise AI interoperability

**A2P (Agent-to-Person)** [Soon]
Agents pause for human input when needed. Permission requests, confirmations, and clarifications flow through this protocol.
Use: Permission requests, CAPTCHA pauses, decision points, review gates

**A2UI (Agent-to-UI)** [Soon]
Agents stream structured updates to the interface. Progress indicators, intermediate results, and tool calls render in real-time.
Use: Live progress streaming, step-by-step visibility, result rendering

## Models

Full details: https://askfinz.com/models

**Cloud routing (10 providers):** OpenAI, Gemini, Mistral, Llama, Qwen, DeepSeek, Moonshot, NVIDIA NIM, Z.ai, Google Cloud.
The router picks the best model per task automatically. Manual override is always available.

**On-device models (browser extension):** 380+ open-weight models via WebLLM/MLC. Runs entirely in the browser — no data leaves the device. Available in Chrome and Edge.

## Pricing

Full pricing: https://askfinz.com/pricing

**Browser Extension & Desktop App** — $8.19/mo (annual: $89.54/yr). No token caps, no usage limits, no restrictions. 380+ AI models. Separate from cloud workspace plans.

Cloud workspace plans:
- Free: $0 — basic access.
- Student: $10/mo — full workspace access at student pricing.
- Starter: $15/mo — full workspace + agents + citations.
- Pro: $49/mo — higher limits, priority routing, advanced agents.
- Business: $149/mo — team features, shared workspace, admin controls.
- Enterprise: custom — dedicated infrastructure, SAML SSO, audit logs, askFinz OS access.

### Pricing FAQ

**Q: Is annual billing cheaper?**
A: Yes — every paid plan is priced lower when you pay yearly instead of twelve monthly payments. You'll see the annual figure on each plan at checkout.

**Q: Are there any egress or download fees?**
A: No. Downloading your files from askFinz is always free — no egress charges, ever. We built on a provider partnership that makes outbound delivery cost us nothing, so we pass that directly to you.

**Q: Can I bring my own keys?**
A: Yes. askFinz routes to every major model out of the box, and you can plug in your own provider API keys whenever you'd rather run on your own account. No lock-in — export your data any time.

**Q: What does Enterprise add?**
A: SAML SSO, audit logs, an isolated data perimeter, dedicated compute, askFinz OS device management and self-host options — shaped to your organisation. It's custom-priced; talk to us.

## Solutions

Full details: https://askfinz.com/solutions

Industry-specific bundles that combine askFinz workspaces around a real workflow.

### Wealth & finance — https://askfinz.com/solutions/wealth
A workshop for analysts, advisors and operators of capital — research notebooks, multi-source news, semantic search and KPI dashboards under one login.
Key workspaces: Research, News, Finance, Data, Chat, Search.

### Healthcare — https://askfinz.com/solutions/healthcare
For medical professionals — literature review, clinical note drafting, drug-interaction lookup and patient-facing content generation.
Key workspaces: Research, Chat, Docs, Knowledge, Search.

### Education — https://askfinz.com/solutions/education
For students and educators — essay assistance, citation management, quiz generation, course content creation and reading comprehension.
Key workspaces: Research, Chat, Docs, Edu, Knowledge, Create.

### Research — https://askfinz.com/solutions/research
For academic and professional researchers — deep literature search, source matrix, citation network analysis and long-form synthesis.
Key workspaces: Research, Chat, Docs, Search, Knowledge.

### Operations — https://askfinz.com/solutions/operations
For business operations teams — workflow automation, data analysis, report generation and cross-tool integration.
Key workspaces: Workflow, Data, Dash, Chat, Search, Knowledge.

## Use cases

### undefined — https://askfinz.com/for/equity-research


- Pull the read together: Open a notebook per name; cite 10-K passages, the recent call and your own prior notes — each claim next to its source.
- Ground it in current news: Sweep deduped, multi-source news clusters on the names you cover so a single story doesn't read four ways.
- Search across everything you've filed: Semantic search over the filings, transcripts and notes you've already collected — find the passage, not just the document.

### undefined — https://askfinz.com/for/due-diligence


- Apply one rubric to every target: Branch the same diligence question set per company so each gets the same depth — no target gets the thin treatment.
- Read the document room: Upload the data-room files and search across them semantically; pull the clause or figure, not the 200-page PDF.
- Check the public record: Sweep deduped news clusters for litigation, leadership churn and the stories that don't make the management deck.

### undefined — https://askfinz.com/for/market-research


- Frame the question as a notebook: Open a notebook per market or segment; branch sub-threads for sizing, players and trends so the structure mirrors the brief.
- Synthesise the reading: Pull the reports and articles into one place and let the workspace draft the synthesis — agreement on top, disagreement surfaced underneath.
- Track the live signal: Deduped, multi-source news clusters keep the brief current between updates instead of going stale the week after you write it.

### undefined — https://askfinz.com/for/competitive-analysis


- A thread per competitor: Branch a notebook thread for each rival so positioning, pricing moves and launches accumulate in one place over time.
- Catch the moves early: Deduped, multi-source news clusters surface a competitor's announcement once — not four near-identical times — the day it lands.
- Synthesise into a battlecard: Let the workspace draft the comparison — where they're ahead, where they're exposed — with each line linked to its source.

### undefined — https://askfinz.com/for/financial-analysts


- Morning briefing: Pull the day's signal across feeds, deduped and clustered by holding or sector — the read, not the noise.
- Citation-backed notes: Draft a note where every number links back to the page it came from, in your house template.
- Ask across models: Switch between AI models in one thread for the question at hand — bring files, keep the history.

### undefined — https://askfinz.com/for/consultants


- Scope the question: Open a notebook per engagement; branch threads for the market, the players and the recommendation so structure mirrors the deck.
- Synthesise the inputs: Pull reports, interviews and articles into one place and draft the synthesis with sources attached.
- Draft across models: Switch AI models mid-thread for framing, rewriting or stress-testing the argument — keep the whole history.

### undefined — https://askfinz.com/for/literature-review


- Organise the corpus: Bring the papers into one notebook; branch threads by question or theme so the structure matches the review.
- Synthesise with citations: Draft a synthesis that puts agreement on top and surfaces where the literature conflicts — each claim linked to its paper.
- Search across the reading: Semantic search over the whole corpus: find the finding, the method or the quote without re-skimming every PDF.

### undefined — https://askfinz.com/for/developers


- Code in a real IDE: A VS Code-style web IDE with AI built in — read, edit and run across your project, not just a chat box pasting snippets.
- Bring AI into the browser: The extension puts the assistant on the pages you already work on, so help is one keystroke away without a context switch.
- Work natively on the desktop: The desktop app brings the IDE and assistant into a native window, sharing the same session as web.

## Guides (57)

### Agent-to-agent (A2A), explained — https://askfinz.com/guides/agent-to-agent-a2a-explained
Agent-to-agent (A2A) lets AI agents hand off tasks to each other — enabling more complex, multi-step work than any single agent can handle on its own.


A single AI assistant can do a lot. But some work is genuinely too large, too varied, or too parallel for one agent to handle end-to-end. Agent-to-agent (A2A) protocols define how AI agents can hand tasks to each other — breaking complex work into pieces, routing each piece to the agent best suited to handle it, and assembling the results. Understanding A2A helps clarify what is actually possible when AI systems are described as "agentic."

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="A coordinating agent splits a task and hands sub-tasks to specialist agents…

### AI agents vs. chatbots — the difference — https://askfinz.com/guides/ai-agents-vs-chatbots
AI agents vs chatbots explained simply: chatbots respond to questions; agents take actions and work through multi-step tasks on your behalf.


If you've heard "AI agents" mentioned alongside chatbots and wondered what the actual difference is, you're not alone. The two terms get used interchangeably in a lot of marketing copy, but they describe meaningfully different things — and the difference matters when you're thinking about what AI can do for your work.

The short version: a chatbot responds. An agent acts.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="A chatbot gives a single response; an agent plans and executes multiple steps">
  <rect class="box" x="6" y="40" width="220" height="64" rx="…

### The askFinz browser extension: AI wherever you browse — https://askfinz.com/guides/ai-browser-extension
The askFinz AI browser extension puts a full AI side panel on any webpage — research, summarise, and act without leaving the tab you're already on.


Most AI tools make you leave what you're doing. You copy a block of text, switch tabs, paste it in, get an answer, then switch back. The askFinz [browser extension](/extension) skips all of that — the AI panel lives alongside the page you're already on, so you never lose your place.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a webpage to an AI answer and a saved note, without leaving the tab">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rect class="box" x="196" y="40" width="150" height="64" rx="12"/>
  <rect class="box" x…

### AI chat across every major model, in one place — https://askfinz.com/guides/ai-chat-every-model
Stop juggling ChatGPT, Claude, and Gemini in separate tabs. askFinz gives you multi-model AI chat in one place — same prompt, every model, no switching.


There are more capable AI models available today than at any point in history. There are also more logins, more browser tabs, and more moments where you copy-paste a prompt from one window into another hoping the answer is better this time. askFinz closes that loop: one place to talk to every major model, compare what they give you, and keep your conversation history in one thread.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="One prompt sent to multiple models, answers compared and saved in one thread">
  <rect class="box" x="6" y="40" width="150" height="6…

### An AI coding workspace for whole projects — https://askfinz.com/guides/ai-coding-workspace
An AI coding assistant that works across your whole project — not just the line you're typing. Write, review, explain and iterate without switching tools.


AI autocomplete that finishes your current line is useful. An AI that understands the file you are in is more useful. An AI that understands the whole project — the structure, the dependencies, the decisions made three months ago in a file you have not opened today — is something else entirely. That is what askFinz Code is built around.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a coding task to reviewed, tested, understood code in one workspace">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rect class="box" x="196" y="40" w…

### Build dashboards with AI — no SQL — https://askfinz.com/guides/ai-dashboard-builder
An AI dashboard builder that turns plain-language questions into charts and live dashboards — so your data tells its story without a BI analyst in the way.


Most organisations are sitting on data they cannot easily see. The numbers are in a database somewhere, or a spreadsheet someone maintains, or a system that has a reporting tab nobody fully understands. Getting from "I want to know X" to a chart you can act on typically requires someone who knows SQL, a BI tool that takes days to configure, or a data analyst whose queue is already full.

An AI dashboard builder is coming to askFinz. The goal is simple: ask the question in plain language and get the chart — no query language, no BI license, no waiting.

<figure class="diagram">
<svg view…

### Turn your docs into a readable AI manual — https://askfinz.com/guides/ai-documentation
How an AI documentation tool transforms scattered internal docs into something anyone can query — so your team stops guessing and starts finding.


Most teams have more documentation than they realise. What they do not have is documentation that is easy to use. The onboarding guide lives in one folder, the process notes in another, the updated version of the policy somewhere nobody remembers. The information exists — it is just not *queryable*. An AI documentation tool changes that: instead of searching through files, you ask a question and the answer comes back from the documents themselves.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="Scattered docs becoming a queryable knowledge layer">
  <rect clas…

### AI for creative & media teams — https://askfinz.com/guides/ai-for-creative-and-media-teams
How creative and media teams use AI for creators to move from brief to publish faster — without losing the voice, the quality, or the creative control.


Creative work has two phases that feel completely different but are rarely separated cleanly: the part where ideas form, and the part where ideas become things. The first phase is irreducibly human. The second — research, drafting, iteration, formatting, scheduling — contains a lot of work that does not require creativity to execute. AI's place in creative and media teams is in that second phase: compressing the production cycle so more time goes to the first.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a creative brief to a drafted piece, iterated and…

### AI for education & learning teams — https://askfinz.com/guides/ai-for-education
How education teams use AI for education to build courses, support learners, and cut the prep work that crowds out real teaching.


Teaching is one of the most preparation-heavy professions there is. For every hour in front of students, there are hours behind the scenes: planning lessons, writing materials, researching topics, giving feedback, answering the same question seventeen different ways for seventeen different learners. AI does not replace any of that. It does mean that more of it can happen without the teacher carrying all the weight alone.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a learning objective to a drafted lesson, enriched with sources, ready to teach">
  <rec…

### AI in healthcare, used responsibly — https://askfinz.com/guides/ai-for-healthcare
How healthcare teams use AI for research, documentation, and patient-facing work — with the human always in control and every source visible.


Healthcare work demands more than speed. Every note, every summary, every piece of research exists in a context where the wrong answer has real consequences. The question is not whether AI has a place in clinical and healthcare settings — it already does — but whether it is used in a way that keeps the professional in control, the reasoning visible, and the patient's interests protected.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a clinical question to a sourced summary, reviewed by the professional, then shared">
  <rect class="box" x="6" y="40" wid…

### AI for legal teams — https://askfinz.com/guides/ai-for-legal-teams
How legal teams use AI for legal work — research, drafting, and document review — with the lawyer always in control and every source traceable.


Legal work carries a particular kind of professional responsibility. An answer that is wrong, incomplete, or untraceable is not just unhelpful — it can cause harm. The case for AI in legal settings is therefore more careful than in most: the tool must earn trust through transparency, not undermine it through convenience. Used correctly, AI can give legal professionals more time for the work that actually requires their expertise. Used carelessly, it creates exactly the risks it is supposed to reduce.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a legal…

### AI for markets and portfolios — https://askfinz.com/guides/ai-for-markets-and-portfolios
How an AI finance assistant helps investors and advisors track markets, review portfolio positions, and turn research into decisions — all in one place.


Market information is everywhere. The problem is not access — it is *making sense of it in time to act*. By the time you have pulled data from three sources, cross-referenced a position, and drafted a note on what it means, the window has often moved. An AI finance assistant is useful not because it knows more than you do, but because it removes the manual steps between having a question and having an answer worth acting on.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a market question to a researched position summary in one flow">
  <rect class="box"…

### AI for operations teams — https://askfinz.com/guides/ai-for-operations-teams
How operations teams use AI for operations to move faster on decisions, documentation, and cross-team coordination — without more tools to manage.


Operations is the connective tissue of every organisation — the function that keeps everything moving, coordinates across teams, and absorbs the work that does not belong anywhere else. It is also, typically, the function most buried in process: tracking, documenting, escalating, reporting, chasing. AI does not change what operations does. It dramatically changes how much of that load requires a human to carry it manually.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a process question to a drafted procedure, tracked and shared with the team">
  <rect…

### AI for research-heavy work — https://askfinz.com/guides/ai-for-research-heavy-work
How teams doing deep research use AI for research to move from scattered sources to a cited, defensible answer — without losing the trail.


Research-heavy work has a specific frustration: the ratio of time spent finding and organising material to time spent actually thinking about it is badly skewed. A researcher, analyst, or strategist might spend three hours pulling sources together before spending thirty minutes forming an opinion. AI does not replace the opinion — but it can reshape that ratio.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a research question to gathered sources, a synthesis, and a cited output">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rec…

### AI for wealth & finance teams — https://askfinz.com/guides/ai-for-wealth-and-finance-teams
How advisory, wealth and finance teams use askFinz to research markets, draft client-ready notes, and build dashboards — without juggling ten tools.


Finance work lives or dies on two things: getting to a defensible answer quickly, and being able to show your work. Most teams lose hours to neither — they lose them to *switching*: a tab for research, another for the spreadsheet, a third for the chart, a fourth for the memo. askFinz is built to collapse that into one place.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a question to a cited note and a shareable chart, in one place">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rect class="box" x="196" y="40" width="150" height…

### A second pair of eyes for health questions — https://askfinz.com/guides/ai-health-assistant
How an AI health assistant helps you understand medical information, prepare for appointments, and navigate decisions — without replacing your doctor.


Health questions are uniquely stressful to research. The information online is abundant but uneven — authoritative articles sit alongside outdated advice, and the search results rarely distinguish between them. You come away with more words but not necessarily more clarity. An AI health assistant is not a replacement for medical care. It is a way to walk into that care better prepared: with clearer questions, a better understanding of the terminology, and a calmer sense of what you are dealing with.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a health…

### A creative studio for AI rendering — https://askfinz.com/guides/ai-image-studio
How an AI image studio lets individuals and teams generate, iterate, and use visuals without design tools or waiting for someone with design skills.


Most work that needs a visual is not design work — it is communication work. A concept that needs illustrating, a presentation that needs a header, a prototype that needs to show how something might look. The people who need these visuals are rarely designers, and the solution is usually one of three things: wait for someone who is, pay for a service, or go without. An AI image studio offers a fourth path: describe what you want and see it rendered.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a description to a finished visual ready to use">
  <rect c…

### An AI inbox & calendar assistant — https://askfinz.com/guides/ai-inbox-and-calendar
An AI email assistant that reads, prioritises and drafts — so you spend less time processing your inbox and more time on the work that actually matters.


The inbox was never supposed to be the job. It is the channel through which the job arrives — requests, decisions, updates, invitations. But for most people, managing the inbox has become a significant part of the working day in its own right: reading, triaging, drafting, chasing, filing. askFinz Mail is built to reduce that overhead, so the time you spend on communication reflects its actual importance rather than the volume of it.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a full inbox to a prioritised, drafted, scheduled working day">
  <rect clas…

### Connect every tool into one AI knowledge base — https://askfinz.com/guides/ai-knowledge-base
How teams use askFinz as an AI knowledge base to surface the right answer from every document, note, and system — without digging through folders.


Most teams are not short on information. They are short on *findable* information. There's a document in one place, a note from last week in another, a decision made in a thread nobody can locate. The knowledge exists — it just isn't connected. An AI knowledge base changes that by giving every team member a single place to ask a question and get an answer drawn from everything the team already knows.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="Documents, notes and tools feeding into one searchable knowledge base">
  <rect class="box" x="6" y="40" width="14…

### Case law and contracts in plain English — https://askfinz.com/guides/ai-legal-assistant
How legal teams use an AI legal assistant in askFinz to research case law, review contracts, and produce plain-English summaries — fast and fully sourced.


Legal work involves two distinct skills: understanding what the law says, and explaining it clearly to someone who isn't a lawyer. Most of the time cost falls on the first part — reading through case law, cross-referencing statutes, reviewing contract language — before you can do the more valuable part of actually advising someone. askFinz **Legal** is coming to compress that research time, so more of the work stays at the level that actually matters.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a legal question to a plain-English briefing, in one place…

### Go live and build a community — https://askfinz.com/guides/ai-live-streaming
How creators use AI live streaming tools in askFinz to broadcast, engage their audience, and manage community channels — all from one place.


Going live has never been technically simpler. What still takes time is everything around the stream: writing the description, fielding chat, keeping the community engaged between broadcasts, and figuring out what actually landed with your audience. Most creators manage that across a handful of disconnected tools — a streaming platform, a community server, a notes app, a scheduler. askFinz **Stream** is coming to bring it together.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From preparation to community, all in one streaming workspace">
  <rect class="box…

### Your day's news, summarised by AI — https://askfinz.com/guides/ai-news-briefing
An AI news summary that reads the noise so you don't have to — filtered by topic, with verifiable sources and no algorithm deciding what matters to you.


The news does not get shorter. If anything, the amount of content competing for your attention at the start of each day increases, while the amount of time you have to process it does not. Most people respond by giving up on reading the news properly, or by spending more time than they should trying to extract the ten things that actually matter from the hundred that do not. askFinz News is a third option.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a noisy information stream to a focused, sourced daily briefing">
  <rect class="box" x="6" y="40" widt…

### AI-organised file storage — https://askfinz.com/guides/ai-organised-file-storage
AI file management that keeps your storage organised without you doing the organising — find anything fast, from anywhere, with the context you need.


The problem with file storage is not storage. It is retrieval. Saving a file takes seconds. Finding it six weeks later, when you remember roughly what it was about but not what you called it or where you put it, can take considerably longer. askFinz Storage is built around the assumption that a file is only useful if you can find it — and that finding it should not require perfect memory or rigid folder discipline.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a saved file to a found, contextualised, shareable asset">
  <rect class="box" x="6" y="40" wi…

### Every account, one place to see your money — https://askfinz.com/guides/ai-personal-finance
How individuals use AI personal finance tools in askFinz to track accounts, understand spending, and plan ahead — without logging into six separate apps.


Most people manage their money across more places than they realise: a current account here, a savings pot there, a credit card with a different bank, a pension somewhere else entirely. Each one has its own app, its own login, its own view of the world. The result is that you almost never see the whole picture at once. askFinz **Bank** is coming to change that — one place where every account is visible and your finances start to make sense together.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From scattered accounts to a clear financial picture, in one plac…

### A project tool that knows the rest of your work — https://askfinz.com/guides/ai-project-management
AI project management that links tasks to the research and conversations behind them — so nothing important gets lost in a tool your team forgets to check.


Most project tools have the same blind spot: they track *what* needs doing, but none of the *why* behind it. The decision thread is in Slack. The research is in a doc someone shared last month. The context that makes a task make sense is somewhere else — and over time, teams spend as much energy re-finding that context as they do doing the actual work.

[askFinz Projects](/apps/project) is different because it shares a workspace with everything else. The task knows about the conversation that created it. The brief is right there, not linked from a third-party tool.

<figure class="diagra…

### Property listings, distilled by AI — https://askfinz.com/guides/ai-real-estate
How buyers and agents use AI real estate tools in askFinz to research listings, compare neighbourhoods, and move from first question to confident offer.


Finding a property is easy. Making sense of the market around it — schools, comparable sales, planning history, neighbourhood trends — is where the real work begins. Most buyers and agents cobble together five or six sources and then try to hold it all in their head at once. askFinz's **Estate** workspace is coming to consolidate that into one place.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a listing to a confident offer, without switching tabs">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rect class="box" x="196" y="40"…

### AI research that cites its sources — https://askfinz.com/guides/ai-research-that-cites-sources
An AI research tool that doesn't just give you an answer — it shows where the answer came from, so you can trust it, share it, and defend it.


The hardest problem with AI-generated research is not the quality of the answer — it is the silence about where the answer came from. You get a confident summary, a clean paragraph, a tidy list of conclusions. What you do not get is a way to check any of it. askFinz Research is built around a different assumption: an answer is only useful if you can verify it.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a research question to a cited, shareable answer in one place">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rect class="box…

### An AI search engine for people, agents and LLMs — https://askfinz.com/guides/ai-search-engine
An AI search engine that understands questions, not just keywords — built for people doing real work and for the agents and LLMs working alongside them.


Search was designed for a world where you knew how to phrase the right keyword. It works well if you already know roughly what you are looking for and how it is likely to be described. It works less well for the kind of questions that actually arise in the middle of complex work — questions that are half-formed, context-dependent, or genuinely open-ended. askFinz Search is designed for those questions.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a question to a synthesised, sourced answer — for people and for agents">
  <rect class="box" x="6" y="40"…

### Multi-account social posting & scheduling — https://askfinz.com/guides/ai-social-media-posting
How teams and creators use AI social media tools in askFinz to draft, schedule, and publish across multiple accounts — without toggling between platforms.


Posting consistently on social media sounds simple until you're actually doing it. Writing for multiple platforms means adapting tone and format for each one. Managing more than one account or brand means tracking what went out where and when. Scheduling ahead means maintaining a calendar across tools that don't share context. Most teams end up with a patchwork of apps that technically work but slow everything down. askFinz **Socials** is coming to replace that patchwork with one place.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a content idea to mult…

### A storefront native to your AI platform — https://askfinz.com/guides/ai-storefront
How creators and teams use an AI storefront in askFinz to sell products, manage orders, and handle customer questions — without a separate e-commerce tool.


Most storefronts are built for a separate context: you make the thing somewhere, market it somewhere else, sell it on a third platform, and handle support on a fourth. Every handoff is a small tax on your time. askFinz **Shop** is coming to put the selling surface inside the workspace where the rest of your work already happens.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From product to sale to happy customer, in one workspace">
  <rect class="box" x="6" y="40" width="150" height="64" rx="12"/>
  <rect class="box" x="196" y="40" width="150" height="64" r…

### Plan and book a whole trip in a paragraph — https://askfinz.com/guides/ai-travel-planner
An AI travel planner that turns a single prompt into booked flights, stays, and activities — without juggling airline tabs, hotel sites, or itinerary docs.


Planning a trip is one of those tasks that looks simple from the outside — you pick where you're going, find somewhere to stay, book a flight — and then you open the browser and ten tabs turn into twenty. Prices on one site don't include the fees shown on another. The hotel you liked sold out by the time you checked back. The itinerary you were building in a Google doc drifts away from the bookings you actually made.

[askFinz Travel](/apps/travel) is an AI travel planner that handles the whole chain from a single conversation — search, compare, book, and keep the itinerary up to date — wi…

### An AI tutor that follows your pace and progress — https://askfinz.com/guides/ai-tutor
How an AI tutor adapts to how you learn, remembers where you left off, and helps you go deeper on any subject — at any pace, on any device.


The best tutoring is responsive. It meets you where you are, adjusts when something is not landing, and moves at a pace that works for you rather than for a class of thirty. Most people have never experienced that kind of learning because access to it has always been expensive, scarce, or both. An AI tutor changes the economics without changing the principle: responsive, patient, personalised learning available whenever you want to use it.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="A learning session that adapts and remembers across time">
  <rect class="…

### Drag-and-drop AI workflow automation — https://askfinz.com/guides/ai-workflow-automation
AI workflow automation built for non-engineers — connect tools, trigger actions, and route decisions with a visual canvas that ships in beta on askFinz.


Most teams have a process that works — it just has too many manual steps in the middle. Someone checks a result and copies it into a form. Someone reads a summary and sends it to the right person. Someone checks whether a threshold was crossed and triggers the next step. These are not complex decisions. They're just repetitive, and the people doing them are too capable to be spending time on them.

AI workflow automation is coming to askFinz as part of the [Workflow workspace](/apps/workflow), currently in beta. It's a visual canvas where you connect steps, add AI decision points, and let…

### askFinz Cloud: every AI workspace, one login — https://askfinz.com/guides/askfinz-cloud-workspaces
askFinz Cloud gives you every AI tool — research, chat, code, charts, knowledge — under one login, accessible from any browser on any device.


The default way to use AI at work is to have several accounts at several providers, each one good at one thing, each one needing its own login. That adds up quickly to more switching than working. askFinz Cloud puts every workspace on a single [platform](/platform) under one login, so you can move between tools the way you move between rooms in the same building — not between buildings.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="One login gives access to every AI workspace — research, charts, knowledge, and code">
  <rect class="box" x="6" y="40" width="1…

### askFinz Desktop: your whole AI workspace, off the browser — https://askfinz.com/guides/askfinz-desktop-app
The askFinz AI desktop app brings your full workspace — browser, IDE, storage and AI — into a single native app that runs independently of your browser.


A browser tab is a fragile place to do serious work. It competes with every other open tab, it disappears if the window closes, and it can't interact with the files and tools sitting on your machine. askFinz [Desktop](/desktop) takes the full workspace out of the browser and puts it on your computer as a proper application — persistent, focused, and connected to what's already on your device.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From local files to AI-assisted work and saved output, all in a native app">
  <rect class="box" x="6" y="40" width="150"…

### askFinz OS: an operating system built around AI — https://askfinz.com/guides/askfinz-os
askFinz OS is an emerging AI operating system where AI assistance is part of the environment itself — not an add-on to an existing desktop.


Every current approach to AI on a computer follows the same pattern: you have an operating system, and then you have an AI tool installed on top of it. The AI is a guest in an environment not built for it. askFinz [OS](/os) is an early exploration of a different question — what does an operating system look like when AI is part of the environment from the start, not an afterthought?

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From boot to AI-native desktop — AI is part of every layer, not a separate application">
  <rect class="box" x="6" y="40" width="150…

### Automate the repetitive parts of your week — https://askfinz.com/guides/automate-repetitive-work
Automate work with AI by setting up workflows that handle the recurring, predictable tasks so your time goes to the work that actually needs you.


Most knowledge workers can name at least three or four things they do every week that follow exactly the same pattern. The weekly summary. The status update pulled from multiple sources. The report formatted, checked, and sent to the same people. These tasks aren't difficult — they're just reliably time-consuming, and they tend to land at the worst moments.

Automation isn't about replacing judgment. It's about not spending your attention on the parts of work that don't require it.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="A trigger starts a workflow th…

### Choosing AI tools for your team — https://askfinz.com/guides/choosing-ai-tools-for-your-team
A practical guide to evaluating the best AI tools for teams — what questions to ask, what traps to avoid, and how to tell capability from marketing.


Choosing AI tools for a team is harder than it looks. The category is crowded, the claims are large, and the demos tend to show the best-case scenario rather than the tenth-hour-of-use scenario that your team will actually live in. Most teams end up making the decision based on what's loudest rather than what fits.

A clearer approach starts with honest questions about your team's work — and then matches tool capability to those specifics.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="Identify your needs, evaluate fit, test with real work, then decide">…

### Turn data into a dashboard you can share — https://askfinz.com/guides/data-into-shareable-dashboards
Self-serve dashboards let anyone on the team build and share charts — no BI license or SQL needed, so decisions happen faster and everyone stays in sync.


Getting data into a chart that other people can see has always required more than it should. You either needed a BI tool, someone who could write SQL, or enough patience to wrangle a spreadsheet into something presentable. For most teams, that meant the people who understood the numbers weren't always the people who could share them — and decisions got made on stale exports or verbal summaries instead.

Self-serve dashboards change that. When anyone on the team can turn data into a shareable visual without a specialist, the gap between a question and a clear answer collapses.

<figure cl…

### Fine-tune and track AI models end to end — https://askfinz.com/guides/fine-tune-ai-models
A fine-tuning platform that handles training runs, version tracking, and evaluation — coming to askFinz for teams who need AI built on their own data.


General-purpose AI models are impressive until you need them to do something specific to your domain. A support model that doesn't understand your product. A classification model that doesn't know your categories. A summarisation model that doesn't match your house style. At that point, most teams face the same problem: fine-tuning is the right answer, but the infrastructure to do it well — track experiments, version models, evaluate outputs — is expensive and time-consuming to build yourself.

Fine-tuning and model tracking is coming to askFinz as part of the [Train workspace](/apps/train…

### From question to cited answer — https://askfinz.com/guides/from-question-to-cited-answer
How AI with citations lets you research faster, trust the results, and share work that stands up to scrutiny — without chasing sources after the fact.


Most people have had the experience of finishing a research task only to realise they can't remember where a key fact came from. The answer is there, but the trail isn't. That gap — between knowing something and being able to show where you learned it — is what makes a lot of AI-assisted research feel risky.

askFinz Research is built around a different starting point: every claim stays attached to its source, from the moment you ask.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From a question to a cited, shareable answer in one place">
  <rect class="bo…

### How AI model routing works (in plain English) — https://askfinz.com/guides/how-ai-model-routing-works
AI model routing explained: how platforms automatically match each task to the right AI model so you get better results, without choosing one yourself.


If you've used more than one AI tool, you've probably noticed that different models have different strengths. One is better at summarising documents; another is faster but handles nuance less well; a third is especially good at reasoning through complex problems. Choosing the right one for each task is possible — but it adds friction. You have to know which models exist, understand their differences, and remember to switch.

Model routing removes that decision from your plate. The platform handles the match.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="A t…

### Keeping work private when you use AI — https://askfinz.com/guides/keeping-work-private-with-ai
Private AI for business means knowing where your data goes, what controls you have, and how to use AI without exposing your team's confidential work.


AI tools have become genuinely useful for professional work — but the default settings of most popular tools were designed for consumer use, not for the confidentiality expectations that come with business and client work. The gap between "useful" and "private enough for professional use" is real, and it's worth understanding before you or your team starts pasting sensitive material into a chat window.

The good news is that privacy-conscious AI use isn't about choosing between capability and control. It's about understanding what the options are and picking the one that fits the work.…

### A live map of aircraft, ships & satellites — https://askfinz.com/guides/live-map-aircraft-ships-satellites
Track any flight, vessel, or satellite in real time from one map — without installing anything or stitching together separate live flight tracker tabs.


Open a flight tracking site and you get flights. Open a vessel tracker and you get ships. Want satellites? That's a third window. If you're coordinating a shipment, watching a cargo route, or just curious where a plane overhead is headed, you already know the frustration of bouncing between three separate tools that don't share a single frame of reference.

The [askFinz Map](/apps/map) puts all three layers on one canvas — live, together, now.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="One map, three live layers: aircraft, ships, and satellites">
  <rec…

### One sign-in for every workspace and device — https://askfinz.com/guides/one-sign-in-every-workspace
Single sign-on for AI tools that actually works across every askFinz workspace and device — no per-app logins, no session drift, no access gaps.


The login problem sounds trivial until you're in it. You open a new workspace, you're signed out. You switch devices, you start over. A team member needs access, you spend ten minutes figuring out which tool they need an account in. Someone leaves, and months later you discover they still had access to three systems nobody remembered they were in.

Access management is the least exciting part of any software stack, and it quietly causes the most friction. [askFinz Access](/apps/access) is the answer for teams using askFinz: one sign-in, working across every workspace and device, with the c…

### Bug reports, feature requests, community votes — https://askfinz.com/guides/product-feedback-board
How teams use a product feedback board in askFinz to collect reports, organise feature requests, and give their community a voice in what ships next.


Every product team eventually faces the same problem: feedback is everywhere. Bug reports arrive by email. Feature requests come through support tickets, social posts, and direct messages. Users vote with their feet, but rarely get a channel to vote with their voice. askFinz **Feedback** is already live and built to pull that together — one place where what your community says becomes something your team can actually act on.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="From scattered user feedback to a prioritised, visible roadmap signal">
  <rect class="bo…

### Talk to your spreadsheets with AI — https://askfinz.com/guides/talk-to-your-spreadsheets
How AI data analysis lets you ask questions of your numbers in plain English — no formulas, no SQL, no waiting on the one person who knows the pivot table.


There is always one person on the team who knows the spreadsheet. Everyone else works around them — sending requests, waiting for the column, hoping the formula is right. That bottleneck is not about the data; it is about access. AI data analysis is changing that by letting anyone on the team ask a question of their data in plain language and get a real answer back.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="A plain-English question turning into a chart and a summary">
  <rect class="box" x="6" y="40" width="160" height="64" rx="12"/>
  <rect class="box"…

### Put your whole team's knowledge in one place — https://askfinz.com/guides/team-knowledge-in-one-place
A team knowledge base powered by AI means anyone can find what your organisation already knows — without asking around or hunting through old files.


Every team has a version of the same problem: the answer already exists somewhere. A colleague wrote it up six months ago, or it lives in a PDF buried in a shared drive, or the right person knows it but isn't available right now. The knowledge is there — it's just not findable.

A team knowledge base changes that. When everything your team knows is in one searchable place, the question "does anyone know about X?" becomes "let me look that up."

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="Documents and expertise flow into a shared knowledge base, then out t…

### Use AI privately, on your own device — https://askfinz.com/guides/use-ai-privately-on-your-device
Private offline AI means your sensitive work stays on your machine — no cloud upload, no third-party access, no guessing what happens to your data.


Most AI tools work by sending your input to a server — a server you don't control, operated by a company whose data practices you're trusting. For personal tasks that's often fine. For work that involves confidential information, client data, or anything sensitive, the question of where your words go starts to matter.

Running AI on your own device is the answer to that question. Nothing leaves the machine. Nothing is stored remotely. The capability is entirely yours.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="Your data stays on your device — no cloud up…

### What are AI tokens and context windows? — https://askfinz.com/guides/what-are-ai-tokens-and-context-windows
What are tokens and context windows in AI? A plain-English guide to why they matter for how much an AI can read, remember, and cost per conversation.


Two terms come up almost every time someone gets serious about using AI at work: tokens and context windows. Both sound technical, but the ideas behind them are straightforward — and understanding them changes how you use AI tools more effectively.

## What is a token?

AI language models don't read text the way you do — one word at a time. They break text into smaller pieces called tokens.

A token is roughly a word fragment. "Unbelievable" might be three tokens. "cat" is one. Spaces, punctuation, and common short words each count separately too. As a rough rule of thumb, 100 words of…

### What is a large language model (LLM)? — https://askfinz.com/guides/what-is-a-large-language-model
What is an LLM? A clear, jargon-free explanation of large language models — what they are, how they learned, and what they're actually good at.


"Large language model" has become one of the most used phrases in tech, but it's often repeated without much explanation. Here's a plain-English account of what an LLM actually is, what it learned, and what that means for how you can use one.

## What it is

A large language model is a type of software trained to understand and generate text. It learned by processing enormous quantities of written language — books, articles, websites, code, and more — and finding the statistical patterns in how words and ideas relate to each other.

The "large" refers to scale: both the volume of train…

### What is a multi-model AI platform? — https://askfinz.com/guides/what-is-a-multi-model-ai-platform
What is a multi-model AI platform? A plain-English guide to why access to multiple AI models in one place produces better results and lower costs.


Most people who start using AI begin with one tool: a single chatbot, a single provider, one model. That works fine for getting started. But teams that use AI seriously — across different tasks, with different priorities — tend to hit a ceiling. Not because AI isn't useful, but because no single model is best at everything.

A multi-model AI platform is the answer to that ceiling. It's a product that gives you access to multiple AI models from different providers — in one place, under one interface, without needing separate subscriptions, logins, or workflows for each.

## Why no single…

### What is an AI workspace? — https://askfinz.com/guides/what-is-an-ai-workspace
What is an AI workspace? A plain-English explanation of how purpose-built AI workspaces differ from chatbots, and why teams are switching to them.


"AI workspace" is a term that gets used loosely — sometimes to mean a chatbot with a nicer interface, sometimes to mean something genuinely different. It's worth being precise, because the difference matters if you're deciding whether one is worth adopting.

A chatbot is a single-surface conversation. You type, it responds, you close the tab. An AI workspace is something built for sustained, varied work — multiple capabilities in one place, with memory that persists across sessions, and tools that connect to each other rather than starting from scratch each time.

<figure class="diagram"…

### What is MCP (Model Context Protocol)? — https://askfinz.com/guides/what-is-mcp-model-context-protocol
MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and data sources in a structured, interoperable way.


AI assistants are increasingly useful on their own — but their real potential comes when they can reach outside the conversation and interact with the tools and data you already use. Model Context Protocol (MCP) is an open standard that defines how that connection works. Understanding it helps you see why AI assistants that support it are meaningfully different from ones that don't.

<figure class="diagram">
<svg viewBox="0 0 740 150" role="img" aria-label="MCP connects an AI assistant to external tools and data through a standard interface">
  <rect class="box" x="6" y="40" width="150"…

### What is prompt engineering? — https://askfinz.com/guides/what-is-prompt-engineering
What is prompt engineering? A practical, plain-English guide to writing better AI prompts — and when it genuinely matters vs. when it doesn't.


"Prompt engineering" sounds like it might require a computer science degree. It doesn't. At its core, it just means writing better instructions for an AI — being clearer, more specific, and more deliberate about what you ask and how you ask it.

That said, there are real patterns and techniques that consistently produce better results, and it's worth knowing them.

## Why prompts matter

Language models are pattern-matching systems. They produce outputs that follow from inputs. A vague input tends to produce a vague output. An input that gives the model context, constraints, and a clea…

### What is retrieval-augmented generation (RAG)? — https://askfinz.com/guides/what-is-retrieval-augmented-generation-rag
What is RAG? A plain-English explainer on retrieval-augmented generation — how it works, why it matters, and when teams use it.


If you've ever asked an AI chatbot something specific — "What does our refund policy say?" or "What did the Q3 report conclude?" — and gotten a confident but wrong answer, you've encountered the core problem that retrieval-augmented generation (RAG) was designed to solve.

AI language models are trained on large amounts of text up to a certain date. After that, they know nothing new. They also know nothing private — no internal documents, no company wikis, no proprietary research. RAG is the technique that bridges that gap.

## The basic idea

RAG splits the job into two steps: first r…

### One AI workspace instead of ten browser tabs — https://askfinz.com/guides/one-workspace-instead-of-app-switching
App-switching quietly eats your day. Here's how teams consolidate research, writing, code, and dashboards into one AI workspace — with a single login.


Count the tools open in your browser right now. For most knowledge workers it's somewhere north of ten — and the cost isn't the tools themselves, it's the *gaps between them*. Every switch is a small reset: find the tab, remember where you were, copy something across, lose your train of thought. Those minutes add up.

askFinz is built around a simple idea: bring the work to one place instead of carrying it between many.

## What "one workspace" actually means

It doesn't mean one giant app that does everything badly. It means **purpose-built spaces that share a single login, a single m…

## Integrations (26)

- **Connect Airtable to askFinz — search every base and table** (https://askfinz.com/integrations/airtable): Bring Airtable into askFinz Knowledge so every base, table, and record is searchable and usable in plain language. Coming to askFinz soon.
- **Connect Asana to askFinz — AI search for tasks** (https://askfinz.com/integrations/asana): Bring Asana into askFinz Knowledge so every task, project, and goal is searchable in plain language. Coming to askFinz soon.
- **Connect BigCommerce to askFinz — search your catalogue** (https://askfinz.com/integrations/bigcommerce): Bring BigCommerce into askFinz Knowledge so every product, order, and customer record is searchable in plain language. Coming soon.
- **Connect Box to askFinz** (https://askfinz.com/integrations/box): Box AI integration: search enterprise content stored in Box and bring it into askFinz Chat and Research instantly.
- **Upload a CSV to askFinz — search and chat with any dataset** (https://askfinz.com/integrations/csv): Upload any CSV into askFinz Knowledge and every row becomes searchable and usable in Chat and Research in plain language. Coming soon.
- **Connect Dropbox to askFinz** (https://askfinz.com/integrations/dropbox): Dropbox AI integration: search and cite files stored in Dropbox directly from askFinz Chat and Research.
- **Connect Figma to askFinz — search your designs** (https://askfinz.com/integrations/figma): Bring Figma into askFinz Knowledge so every file, frame, and design decision is searchable in plain language. Coming to askFinz soon.
- **Connect GitHub to askFinz** (https://askfinz.com/integrations/github): GitHub AI integration: search repos, pull requests, issues, and docs from GitHub inside askFinz Chat and Research.
- **Connect GitLab to askFinz** (https://askfinz.com/integrations/gitlab): GitLab AI integration: search merge requests, issues, and wikis from GitLab inside askFinz Chat and Research.
- **Connect Google Drive to askFinz** (https://askfinz.com/integrations/google-drive): Google Drive AI integration: search every doc, sheet, and slide from one workspace and use them in Chat and Research.
- **Connect Jira to askFinz — AI search for tickets** (https://askfinz.com/integrations/jira): Bring Jira into askFinz Knowledge so you can search tickets, track blockers, and discuss sprint health in plain language. Coming soon.
- **Connect Linear to askFinz** (https://askfinz.com/integrations/linear): Linear AI integration: search issues, projects, and roadmap context from Linear inside askFinz Chat and Research.
- **Connect Microsoft Teams to askFinz** (https://askfinz.com/integrations/microsoft-teams): Microsoft Teams AI integration: search channels, chats, and meeting notes from Teams inside askFinz Research and Chat.
- **Connect Notion to askFinz** (https://askfinz.com/integrations/notion): Notion AI integration: search your wikis, databases, and notes from askFinz and cite them in Chat and Research.
- **Connect OneDrive to askFinz** (https://askfinz.com/integrations/onedrive): OneDrive AI integration: make every file in your OneDrive searchable and usable inside askFinz Chat and Research.
- **Connect Power BI to askFinz — search your dashboards** (https://askfinz.com/integrations/power-bi): Bring Power BI into askFinz Knowledge so every dashboard, dataset, and report is searchable and citable in plain language. Coming soon.
- **Connect Proton Drive to askFinz** (https://askfinz.com/integrations/proton-drive): Proton Drive AI integration: search privacy-first file storage and use your documents inside askFinz without compromising control.
- **Connect Salesforce to askFinz — search your CRM with AI** (https://askfinz.com/integrations/salesforce): Bring Salesforce into askFinz Knowledge so every account, opportunity, and contact is searchable in plain language. Coming soon.
- **Connect SAP to askFinz — search your ERP data with AI** (https://askfinz.com/integrations/sap): Bring SAP into askFinz Knowledge so every record, report, and process is searchable in plain language across your organisation. Coming soon.
- **Connect SharePoint to askFinz** (https://askfinz.com/integrations/sharepoint): SharePoint AI integration: search your intranet, wikis, and shared libraries without leaving askFinz Chat or Research.
- **Connect Shopify to askFinz — search store data** (https://askfinz.com/integrations/shopify): Bring Shopify into askFinz Knowledge so every order, product, and customer record is searchable in plain language. Coming to askFinz soon.
- **Connect Slack to askFinz** (https://askfinz.com/integrations/slack): Slack AI integration: find decisions buried in threads, cite past conversations, and use them in askFinz Research and Chat.
- **Connect a SQL Database to askFinz — search your data** (https://askfinz.com/integrations/sql-database): Bring any SQL database into askFinz Knowledge so every table and record is searchable without writing queries. Coming to askFinz soon.
- **Connect Trello to askFinz — search boards with AI** (https://askfinz.com/integrations/trello): Bring Trello into askFinz Knowledge so every board, card, and checklist is searchable with AI. Coming to askFinz soon.
- **Connect Zendesk to askFinz — search every ticket** (https://askfinz.com/integrations/zendesk): Bring Zendesk into askFinz Knowledge so every ticket, macro, and resolution is searchable in plain language. Coming to askFinz soon.
- **Connect Zoom to askFinz** (https://askfinz.com/integrations/zoom): Zoom AI integration: search meeting transcripts and recordings from Zoom inside askFinz so no conversation is lost.

## Comparisons (7)

### askFinz vs ChatGPT — https://askfinz.com/compare/askfinz-vs-chatgpt
A fair askFinz vs ChatGPT comparison — and a multi-model ChatGPT alternative that puts every leading model in one place.


If you've searched "askFinz vs ChatGPT", you're probably already using ChatGPT for everyday tasks and wondering whether there's something better suited for work that goes beyond a single conversation. The short answer: ChatGPT is an exceptional conversational AI; askFinz is built for the kind of work that needs research, charts, code, and institutional knowledge to happen in the same place.

## Side-by-side

| Dimension | ChatGPT | askFinz |
|---|---|---|
| What it's best known for | OpenAI's conversational AI assistant, widely used for writing, coding help, and Q&A | A multi-model wor…

### askFinz vs Claude — https://askfinz.com/compare/askfinz-vs-claude
A fair askFinz vs Claude comparison — and a Claude alternative that adds every other leading model plus workspaces beyond chat.


Claude is one of the most capable AI assistants available today. If you are deciding between using Claude directly and using askFinz, the honest answer is: it depends on what "using AI" means to you.

## What each one is

**Claude** is Anthropic's AI assistant. You can chat with it at claude.ai or call it via API. It is a single model family — Haiku, Sonnet, and Opus — built around careful, nuanced responses. It excels at writing, analysis, coding, and long-document work.

**askFinz** is a multi-model workspace. Claude is one of the models you can use inside it — alongside others from…

### askFinz vs Google Gemini — https://askfinz.com/compare/askfinz-vs-google-gemini
A fair askFinz vs Google Gemini comparison — and a Google Gemini alternative built for research, charts, and code across any ecosystem.


If you're comparing Google Gemini and askFinz, the question is usually about fit: does your AI belong inside your Google Workspace, or do you need a workspace built around the full shape of the work — research, charts, code, and knowledge — regardless of where your files live? Both are capable; the right answer depends on where your work actually happens.

## Side-by-side

| Dimension | Google Gemini | askFinz |
|---|---|---|
| What it's best known for | Google's AI assistant and AI features across Google Workspace (Docs, Sheets, Gmail, Meet) | A multi-model workspace for research, ana…

### askFinz vs Grok — https://askfinz.com/compare/askfinz-vs-grok
A fair askFinz vs Grok comparison — and a Grok alternative that brings every leading AI model together with workspaces beyond chat.


Grok is xAI's AI assistant, known for a conversational style and tight integration with X. If you are weighing Grok against askFinz, the honest answer is: it depends on what you want "using AI" to feel like day to day.

## What each one is

**Grok** is xAI's AI assistant. You can chat with it through X and xAI's own apps. It is built around xAI's own model family and a direct, conversational personality, with access to current information.

**askFinz** is a multi-model workspace. Rather than one model and one chat window, it lets you reach several leading AI models in one place, and la…

### askFinz vs Microsoft Copilot — https://askfinz.com/compare/askfinz-vs-microsoft-copilot
A fair askFinz vs Microsoft Copilot comparison — and a Microsoft Copilot alternative for teams working beyond the Microsoft 365 ecosystem.


If you're weighing Microsoft Copilot against askFinz, the practical question is usually: does your AI need to live inside your existing Microsoft 365 environment, or do you need a workspace that can reach beyond it? Both are serious tools — the difference is in where each one is at its strongest.

## Side-by-side

| Dimension | Microsoft Copilot | askFinz |
|---|---|---|
| What it's best known for | AI assistance integrated across Microsoft 365 — Word, Excel, Teams, Outlook, and more | A multi-model workspace for research, analysis, visualisation, and knowledge work |
| AI models avai…

### askFinz vs Notion AI — https://askfinz.com/compare/askfinz-vs-notion-ai
A fair askFinz vs Notion AI comparison — and a Notion AI alternative purpose-built for research, charts, and code before you write a doc.


Notion AI and askFinz both aim to make knowledge work faster, but they start from different places. Notion AI enhances a document and database workspace you may already rely on. askFinz is built from scratch around AI — bringing research, charts, code, and a knowledge layer together before a single document is written.

## Side-by-side

| Dimension | Notion AI | askFinz |
|---|---|---|
| What it's best known for | AI writing and summarisation features built into the Notion workspace | A multi-model workspace for research, analysis, visualisation, and knowledge work |
| AI models avail…

### askFinz vs Perplexity — https://askfinz.com/compare/askfinz-vs-perplexity
A fair askFinz vs Perplexity comparison — and a Perplexity alternative that turns cited research into charts, code, and shared knowledge.


If you're comparing askFinz and Perplexity, you're likely after something richer than a web search — you want answers you can act on. Perplexity is a well-regarded AI-powered answer engine; askFinz is a workspace where the answer becomes a briefing, a chart, or a shared knowledge base without leaving the page.

## Side-by-side

| Dimension | Perplexity | askFinz |
|---|---|---|
| What it's best known for | AI-powered answer engine with real-time web search and cited responses | A multi-model workspace for research, analysis, visualisation, and knowledge work |
| AI models available |…

## Research notes (9)

### A workshop, not a chatbot — https://askfinz.com/research/a-workshop-not-a-chatbot
Why purpose-built spaces for real work beat a single do-everything assistant — and what gets lost when we flatten everything into one box.


# A workshop, not a chatbot

There is a satisfying simplicity to the idea of one assistant that does everything. You type a question and the right answer arrives. The interface is a blank box. The promise is infinite surface area.

We spent a long time thinking about whether that was the right way to build askFinz.

We decided it wasn't.

## The blank-box problem

A blank text box is a great interface for an incidental question. It is a poor interface for work. Work has shape. A research session has a different rhythm to a charting session, which has a different rhythm to drafting…

### Owning your tools again — https://askfinz.com/research/owning-your-tools-again
Something important shifted when professional tools became subscriptions. Here is what it means to reclaim control, portability, and your own workflow.


# Owning your tools again

There was a period — not so long ago — when software came on a disc, installed on your machine, and worked as long as you chose to use it. The relationship was simple: you paid once, the tool was yours. You could customize it, keep it running an old version while you finished a project, and know that Tuesday's update wasn't going to change what your workflow depended on.

That world is largely gone. In its place is one where your tools are services, your access is conditional, and the decisions made by a company you have no relationship with — about pricing, ab…

### Software should earn its keep — https://askfinz.com/research/software-should-earn-its-keep
On the difference between tools that finish work and tools that demo well — and why "impressive" is not the same as "useful."


# Software should earn its keep

There is a category of software that is spectacular in a fifteen-minute demonstration and exhausting to use for fifteen hours. The demo is tight. The narrative is clean. The features that look impressive on a screen recording are front and centre. The features that would help you finish a real task on a hard Tuesday afternoon are somewhere in the settings menu, or missing entirely.

We have a name for this in our heads: demo-ware. It earns attention without earning its keep.

## The demonstration problem

The problem with optimising for demos is subtl…

### Speed is a feature, trust is the product — https://askfinz.com/research/speed-is-a-feature-trust-is-the-product
Raw speed captures attention. Reliability and provenance are what make an AI tool worth depending on — and they are harder to build than fast.


# Speed is a feature, trust is the product

The first thing most people notice about a capable AI tool is the speed. A research question that once required hours of reading and synthesis arrives in seconds. A chart that required a data analyst takes minutes. The latency compression is real, and it is genuinely startling the first time you encounter it.

Speed is a good feature. It is not the product.

## What speed alone doesn't solve

Speed answers the question "how fast can I get an output?" It doesn't answer the more important question: "how much can I rely on what I'm getting?" T…

### We tell you which model wrote your answer — https://askfinz.com/research/tell-you-who-wrote-the-answer
On visibility, citations, and why knowing which model answered you is not a technical detail — it is a question of trust.


# We tell you which model wrote your answer

Most AI products hide their machinery. The answer arrives as if from a neutral, authoritative place — no name on the door, no indication of who thought through the question or what that thinking was built on. The interface is polished precisely to make you stop asking where things come from.

We made a different choice. We tell you which model produced your answer. And we think that choice matters more than it might appear.

## Why provenance is not a technical detail

When a colleague answers a question, you automatically factor in what y…

### The case against one big model — https://askfinz.com/research/the-case-against-one-big-model
Monoculture is fragile in agriculture, in finance, and in AI. Here is why relying on a single model is a structural risk disguised as simplicity.


# The case against one big model

Simplicity is appealing in tooling. One provider, one interface, one model to understand and work with. When that model is good, the appeal strengthens — why reach for variety when the thing in front of you is already capable?

This is a reasonable heuristic for individual sessions. It is a fragile strategy for anyone building on AI capabilities or relying on them for serious work.

## The monoculture problem

The analogy that keeps coming back to us is agriculture. Industrial monocultures are extraordinarily productive — until a blight arrives. The…

### The hidden cost of switching tabs — https://askfinz.com/research/the-cost-of-switching-tabs
Tool-sprawl isn't just an organisational inconvenience. Every tab switch carries a cognitive tax that quietly drains the best hours of your day.


# The hidden cost of switching tabs

Nobody thinks of themselves as a tab-switcher. They think of themselves as someone getting work done. The tabs are just infrastructure — the route between having a question and finding an answer, between noticing something and doing something about it.

But if you watch your own work closely enough, the infrastructure is the work. The ten seconds it takes to context-switch between a research tool and a charting tool and a note and a spreadsheet don't show up on any time-tracking report. They accumulate in a different account: the one that keeps score…

### The web became the operating system — https://askfinz.com/research/the-web-became-the-operating-system
A POV on where serious work now happens — and what it means to build tools for a world where the browser is the desktop.


# The web became the operating system

There was a period, not that long ago, when serious work happened in desktop applications. The file was on your machine. The software was installed. The data lived locally. The browser was for browsing — a window you opened to look things up and then closed when the real work began.

That division has quietly dissolved.

## The shift that already happened

For most knowledge workers, the browser is now where work lives. Documents, spreadsheets, project management, communication, data analysis, financial modelling — the list of things that have m…

### Your work is not our training data — https://askfinz.com/research/your-work-is-not-our-training-data
A plain statement of where we stand on using customer work to improve our systems — and why we think the line matters for the whole industry.


# Your work is not our training data

There is a version of AI development where customers and product are in an extractive relationship: users do work, the system learns from that work, and users receive an incrementally improved product in exchange for surrendering something they didn't know they were giving away.

That model is easy to run and easy to justify. It produces results. It also makes a quiet assumption that we don't accept: that your work belongs, in some functional sense, to us.

It doesn't.

## What privacy usually means in this space

The AI industry has developed…

## Infrastructure

Full details: https://askfinz.com/infrastructure

askFinz doesn't run its own data centers — it builds on best-in-class providers, described here by function and city.

**Live stream ingest** (European Union (Finland))
Receives and packages live video before it reaches viewers.
Certifications: ISO/IEC 27001:2022, BSI C5 Type 2, KRITIS / NIS-2, PCI DSS 4.0, Audited TOMs

**Source code & version control** (European Union (Netherlands))
Stores and versions the platform's source code and build history.
Certifications: ISO/IEC 27001, ISO/IEC 27017, ISO/IEC 27018, ISO/IEC 27701, ISO 22301, ISO 9001, SOC 1 / 2 / 3, CSA STAR, PCI DSS, GDPR

**Primary object storage** (European Union (Netherlands))
Holds your files, media and encrypted data at rest. First-line storage for every upload and workspace asset.
Certifications: SOC 2 Type 2, ISO 27001, HIPAA, GDPR & UK GDPR, CCPA / CPRA, PCI-DSS, GovRAMP, TX-RAMP, TPN Blue Shield, HECVAT, VPAT / Section 508

**Object storage backup (live mirror)** (European Union (Germany))
Live mirror of all primary object storage — syncs every 60 seconds. Activates automatically if primary storage is unavailable, with instant failover and no data loss beyond the last 60-second window.
Certifications: SOC 2 Type 2, ISO/IEC 27001:2022, HIPAA, PCI, GDPR, SEC / FINRA, Data Center Security

**Media & file storage** (European Union (Netherlands))
Serves uploaded media and documents from close to you.
Certifications: ISO 27001:2022, ISO 27701:2019, ISO 27018:2019, ISO 27017:2015, SOC 2 Type II, PCI DSS 4.0, FedRAMP Moderate, GovRAMP, C5:2020, EU Cloud CoC, Global CBPR / PRP

**Content delivery & DNS** (Global edge — 300+ cities)
Routes every request to the nearest edge and resolves our domains — the reason pages load fast wherever you are.
Certifications: ISO 27001 / 27701, SOC 2 Type II, C5 Type 2, HIPAA, PCI DSS 4.0.1, CSA STAR, ENS, IRAP, ISMAP, Cyber Essentials, EU Cloud CoC

**SMS & voice communications** (Global carrier-grade data centers)
Delivers verification codes, alerts and voice calls.
Certifications: ISO 27001, SOC 1 / 2 Type II, PCI DSS, HIPAA, HDS, NIST 800-53 / FISMA High, ITAR, TISAX, Uptime Tier, ISO 22301 / 20000 / 9001, Climate Neutral DC Pact

**Transactional email** (European Union (Ireland))
Sends account, security and notification emails.
Certifications: SOC 2 Type II, GDPR, TLS 1.3, Encryption at rest, Point-in-time backups, Annual pen-testing

**Payments & billing** (European Union (Ireland))
Processes subscriptions and payments — card details go straight to a certified processor, never to askFinz.
Certifications: PCI DSS Level 1, SOC 1 / 2 Type II, SOC 3, ISO/IEC 27001, PSD2 / SCA, 3-D Secure, GDPR, Global CBPR / PRP, Encryption at rest

### Compliance glossary

#### Information security management
- **ISO/IEC 27001**: The international standard for an Information Security Management System (ISMS).. Our providers run a systematic, independently audited security program, so your data sits on rigorously managed foundations.
- **ISO/IEC 27017**: Cloud-specific security controls that extend ISO 27001.. Cloud services we build on follow controls designed for cloud risks like tenant isolation and admin operations.
- **SOC 2 Type II**: An AICPA audit of security, availability and confidentiality controls measured over a period of time.. Independent proof the providers' controls actually operate day-to-day — not just on paper.
- **SOC 1**: An AICPA report on controls relevant to financial reporting.. Assurance around billing- and finance-related processing.
- **SOC 3**: A plain, publicly shareable version of the confidential SOC 2 audit.. Lets a provider share independent proof of its security controls openly — no confidentiality agreement required.
- **CSA STAR**: The Cloud Security Alliance's Security, Trust, Assurance & Risk program.. Cloud-specific, registry-published transparency on a provider's security posture.
- **BSI C5**: Germany's Federal Office for Information Security (BSI) cloud criteria catalogue; Type 2 tests operating effectiveness.. A rigorous EU cloud-security benchmark that incorporates ISO 27001.
- **Audited TOMs**: Technical & Organizational Measures under GDPR Art. 32, externally audited.. Documented, verified safeguards specifically around personal-data processing.
- **Cyber Essentials**: A UK NCSC-backed baseline cyber-security certification.. Independently verified baseline cyber hygiene.
- **TISAX**: The Trusted Information Security Assessment Exchange.. Shared, audited information-security assurance across vendors.

#### Privacy & data protection
- **GDPR / UK GDPR**: The EU and UK General Data Protection Regulation.. Lawful processing and your data-subject rights are honored across the EU and UK.
- **EU Model Clauses**: Standard Contractual Clauses for lawful international data transfers.. A lawful basis for any cross-border data flow.
- **ISO/IEC 27701**: An international privacy-management standard that extends ISO 27001 from security into how personal data is handled.. Shows a provider runs privacy as a formal, audited program — and their evidence directly supports our own GDPR compliance.
- **ISO/IEC 27018**: A code of practice for protecting personal data (PII) in public clouds.. Constrains how providers handle personal data — e.g. it isn't used for advertising.
- **EU Cloud CoC**: A GDPR Article 40 approved code of conduct for cloud providers.. The provider's GDPR compliance is independently verified for its cloud services.
- **CCPA / CPRA**: California's consumer privacy laws.. Privacy rights — access, deletion and opt-out — for California users.
- **Global CBPR / PRP**: International Cross-Border Privacy Rules & Privacy Recognition for Processors certifications.. A recognized framework for moving data across borders responsibly.

#### Payments & regulated data
- **PCI DSS**: The Payment Card Industry Data Security Standard (v4.0).. Card data is handled only in a PCI-compliant environment — safe billing and payments.
- **PCI DSS Level 1**: The highest PCI DSS tier, for processors handling the largest card volumes, audited annually by a Qualified Security Assessor.. Card payments run through a top-tier-certified processor — your card details never touch askFinz.
- **PSD2 / SCA**: The EU Payment Services Directive 2 and its Strong Customer Authentication requirement.. European card payments are authenticated to EU regulatory standards, such as a second factor at checkout.
- **3-D Secure**: An EMV authentication protocol (3DS2) that verifies the cardholder during online payments.. Adds a fraud check and shifts liability, protecting you and us on card payments.
- **HIPAA**: The US health-data protection law (Health Insurance Portability and Accountability Act); a Business Associate Agreement is available. Covers protected health information (PHI) and ePHI in compliance with HIPAA and HITECH, as administered by HHS.. Lets us and healthcare customers handle protected health information where needed, such as the med workspace.
- **CJIS**: Criminal Justice Information Services — standards set by a division of the US FBI for the privacy, security, durability and protection of Criminal Justice Information (CJI) and other critical data.. Storage infrastructure supports law-enforcement and justice-sector customers who must maintain CJIS compliance.
- **FERPA**: The Family Educational Rights and Privacy Act — imposes specific technical and administrative requirements for education IT planners, InfoSec organizations and compliance officers receiving U.S. Department of Education aid.. Educational institutions and EdTech customers can store and process student data in compliance with FERPA.
- **SEC / SEA**: U.S. Securities and Exchange Commission and Securities Exchange Act rules (17 CFR 240.17a-4) — third-party record-keeping services must provide an undertaking letter to customer organizations. Effective May 2023.. Financial-services customers who are SEC-regulated can obtain an alternate undertaking letter for compliant record retention.
- **HDS**: The EU 'Health Data Hosting' (Hébergeur de Données de Santé) certification.. Health data can be hosted within the EEA to a regulated standard.
- **ITAR**: US International Traffic in Arms Regulations data-handling controls.. Providers support controlled-data handling, e.g. US-person access restrictions.

#### Government & national security programs
- **FedRAMP**: US federal cloud security authorization (Moderate).. A government-grade security baseline underpins our edge and storage.
- **NIST 800-53 / FISMA**: The US federal security control catalogue and risk baseline (High).. A stringent, well-known control baseline underpins the infrastructure.
- **GovRAMP**: US state & local government cloud authorization (formerly StateRAMP).. Public-sector-grade assurance.
- **TX-RAMP**: The Texas Risk & Authorization Management Program.. Meets Texas public-sector security requirements.
- **KRITIS / NIS-2**: German & EU critical-infrastructure operator obligations, certified per §8a BSIG.. Infrastructure held to critical-service resilience and security duties.
- **ENS**: Spain's Esquema Nacional de Seguridad (National Security Framework).. Meets the Spanish national security framework.
- **IRAP**: Australia's Information Security Registered Assessors Program.. Australian government-grade security assessment.
- **ISMAP**: Japan's government cloud security assessment program.. Japanese public-sector-grade assurance.

#### Reliability, quality & sustainability
- **ISO 22301**: The standard for business continuity management.. Providers plan for disruptions, so the platform stays available through incidents.
- **ISO/IEC 20000-1**: The IT service management standard.. Mature, repeatable operations behind the services we depend on.
- **ISO 9001**: The quality management system standard.. Consistent, documented service quality.
- **Uptime Tier**: Uptime Institute Tier certification for data-center design, facility and operations.. Physical infrastructure engineered for high availability.
- **Climate Neutral DC Pact**: A European pledge for carbon-neutral data centers by 2030.. Greener hosting for your workloads.
- **TPN**: Trusted Partner Network (Blue Shield), aligned to MPA content-security best practices.. Media and content stored to film-industry security standards.
- **HECVAT**: The Higher-Education Community Vendor Assessment Tool.. Vetted for use by universities and research institutions.
- **VPAT / Section 508**: A Voluntary Product Accessibility Template against Section 508 guidelines.. Services remain accessible to users with disabilities.

#### Provider data-protection practices
- **TLS 1.3**: The latest transport-layer encryption protocol.. Data in transit is strongly encrypted everywhere it crosses a network.
- **Encryption at rest**: Stored data is encrypted, with row-level encryption for sensitive tables.. Stored data is unreadable if storage media are ever compromised.
- **Point-in-time backups**: 30-day retention, globally replicated backups.. Recoverability against data loss or a regional outage.
- **Annual pen-testing**: Third-party offensive security testing at least annually.. Vulnerabilities are found and fixed proactively.

## Company & trust

- About (https://askfinz.com/about): The company, its structure, and the principles behind it. A subsidiary of PAUL V | Holdings.
- Trust centre (https://askfinz.com/trust): Routing transparency — which model ran, which provider, why. Data and training stance: your content is never used to train models.
- Security (https://askfinz.com/security): Security practices, controls, and the ongoing audit programme.
- Legal (https://askfinz.com/legal): Terms of service, privacy policy, data processing agreement, and all policy documents.
- Live status (https://askfinz.com/status): Real-time platform health per service.
- Brand (https://askfinz.com/brand): Logo files, brand guidelines, and visual identity.
- Careers (https://askfinz.com/careers): Open roles at askFinz.
- Changelog (https://askfinz.com/changelog): Recent platform updates, new workspaces, and shipped features.
- Contact (https://askfinz.com/contact): Get in touch with the team.

## Get started

- Request access: https://askfinz.com/beta — join the private-access waitlist.
- Pricing: https://askfinz.com/pricing — choose a plan.
- API access: https://askfinz.com/api — programmatic access to the router, agents, and citation layer.

## Alternate brand names

askFinz, askfinz, AskFinz, Askfinz, ask finz, ask finn, askfinn, askfin, finz, finz AI, finz LLM.