Skip to main content
Private access is opening up — request an invite
askFinz
The platform

An AI workshopfor the workthat matters.

askFinz isn't a single chatbot. It's a workshop — different rooms for different kinds of work, all sharing one memory of you and one way of doing things. A fleet of specialist agents on call, dozens of workspaces with the door open, the right brain picked for the question, and a paper trail you can defend.

Go deeper: guides · integrations · compare · models

0+
Agents
0
Live workspaces
0
Model families
0
Surfaces
askfinz · liveworkshop/
workshop/
 ├── agents/
 │    ├── researcher    cites
 │    ├── coder         pairs
 │    ├── writer        drafts
 │    ├── analyst       charts
 │    ├── summariser    distils
 │    ├── browser       drives
 │    ├── mailer        triages
 │    ├── trainer       fits
 │    ├── workflow      schedules
 │    ├── search        retrieves
 │    ├── socials       posts
 │    └── finance       reads
 ├── workspaces/
 │    ├── chat       ·  research
 │    ├── code       ·  news
 │    ├── search     ·  data
 │    ├── train      ·  workflow
 │    ├── socials    ·  finance
 │    └── …          ·  more
 ├── models/
 │    └── reasoning  ·  chat  ·
 │        vision    ·  code  ·
 │        long-ctx  ·  audio
 └── reach/
      ├── extension
      ├── desktop
      ├── workflow
      └── api
one loginone memoryone workshop
0+
Live workspaces
0+
Agents
0
Unified login
0
Model lock-in

What we promise

06 of them

Answers worth quoting.

When askFinz answers a question, you can see where the answer came from. Cite it, share it, defend it.

Agents, not a chatbot.

Your work isn't all the same. askFinz pairs you with the right agent for what's in front of you — and routes between them when the work needs more than one.

A workshop, not a hammer.

Different surfaces for different work, but a single home, a single login, and one consistent way of moving between them.

Privacy that means something.

Sensitive work runs in its own room. We make this easy to verify.

Honest about what we ship.

If something is on the roadmap, we say so. If we change our minds, we'll write about it. We won't sell you what we haven't built.

Open at the edges.

Take your data with you, plug askFinz into your own tools. No quiet lock-in.

An agent run, end to end

route → plan → run → cite → verify

Five stages. No black boxes.

Every agent run takes the same shape, whether it's answering a question in chat, drafting a literature note, refactoring a service or sweeping across the news. You can watch each stage land. You can override at any stage. You can rewind any stage and re-run it without losing what came before.

The diagram on the right is alive — it walks through a single run on scroll-in. Watch the Run stage hand off to the satellite agents mid-pipeline; that hand-off is automatic, and you see who took the sub-task.

The long write-up
agent run · liveIdle
01 · Route
agent · selected
02 · Plan
04 steps · drafted
03 · Run
tools · live
04 · Cite
23 sources · linked
05 · Verify
claims · cross-read
Researcher
fetches · 11 sources
Writer
drafts · 1 paragraph
open web · your library · live tools
footnotes · re-read · result
01 · Route
02 · Plan
03 · Run
04 · Cite
05 · Verify
  1. 01
    Route.
    askFinz reads the shape of the question and picks the agent (or agents) that fit. You see who took it; you can override.
  2. 02
    Plan.
    The agent breaks the work into steps you can read before it starts — what it'll search, what it'll write, what it'll hand back.
  3. 03
    Run.
    It does the work. If a step needs another agent — a Researcher pulling sources for the Writer, a Browser checking a live page — the hand-off is automatic.
  4. 04
    Cite.
    Every claim it puts on the page links back to the source it came from. Footnotes are part of the structure, not glued on at the end.
  5. 05
    Verify.
    Before it finishes, it re-reads the draft against the cited sources. If a citation no longer supports the claim, it flags it instead of hiding it.

The model picking that happens at step 01 is its own discipline — see /models for how that decision gets made.

The agent roster

twelve you'll meet most

Twelve specialists you'll meet most.

A featured slice of the roster — one job rarely sits with one agent. A research note pulls in the Writer for the draft, the Researcher for the sources, the Browser for the live check, the Analyst for the chart. Work routes between them automatically — you watch the hand-offs, you keep the editorial call.

The full roster

Workspaces

29 rooms · 21 open today

One workshop, many rooms.

The workshop has a room for the day-to-day, a room for serious writing, a room for code, a room for the news, a room for the numbers — and a long tail of specialist rooms for the work that doesn't fit anywhere else. Each one has its own door, its own tools, its own memory of what you did last time. The hallway between them is what makes it a workshop and not a tab graveyard.

Browse every workspace
chat.askfinz.ai·research.askfinz.ai·code.askfinz.ai·news.askfinz.ai·search.askfinz.ai·dash.askfinz.ai·storage.askfinz.ai·train.askfinz.ai·workflow.askfinz.ai·mail.askfinz.ai·docs.askfinz.ai·finance.askfinz.ai·med.askfinz.ai·edu.askfinz.ai·data.askfinz.ai·charts.askfinz.ai·knowledge.askfinz.ai·estate.askfinz.ai·travel.askfinz.ai·stream.askfinz.ai·shop.askfinz.ai·legal.askfinz.ai·map.askfinz.ai·create.askfinz.ai·project.askfinz.ai·bank.askfinz.ai·socials.askfinz.ai·feedback.askfinz.ai·access.askfinz.ai·

Models

07 families · the right brain for the question

The right brain for the question.

We work across model families instead of crowning one. Each family earns its turn on the kind of work it's actually best at — and we tell you which one wrote each answer, in a small badge you can click through.

Routing is intent-aware but never invisible. Pin a family per workspace, override per turn, or hand us a key for a model you already pay for.

Want even more choice? The browser extension adds 380+ more AI models, ready to use right alongside the cloud ones.

How we choose
  • 01
    Reasoning

    The slow, careful brains. Used when an answer has to defend itself.

  • 02
    Chat

    Conversational, fast, broadly capable. The default for everyday turns.

  • 03
    Vision

    Reads a screenshot, a chart, a whiteboard alongside the words.

  • 04
    Code-tuned

    Stronger at refactors, tests and reading unfamiliar codebases.

  • 05
    Long-context

    For when the question carries a hundred pages with it.

  • 06
    Audio · TTS

    Read out a briefing, transcribe a meeting, draft a script meant to be heard.

  • 07
    Open-weight

    Self-hostable families when residency and independence are hard constraints.

Moving between rooms

4 of 29 · one thread, four shapes

One thread. Many hands.

The same question gets a different shape in each room. Chat answers fast. Research cites four sources. Code drafts the diff. News converges on the three things that broke overnight. Pick the room that fits — the memory of you follows.

The mock on the right cycles between four workspaces every couple of seconds. Click a tab to pin it.

chat.askfinz.ai
you · just now
Compare the two proposals — what did they actually agree on?
  • Agreement · 01
    Both honour the 2030 emission target without amendment.
  • Agreement · 02
    Both keep household rebates tied to taxable income.
  • Divergence · 01
    Proposal B accelerates the industrial-grid phase-out by 18 months.
  • Divergence · 02
    Proposal A relaxes the coastal carve-out; B keeps it.
model · reasoning · 3.2s

What you'll use it for

04 ways in
  • If you research for a living
    Branch a thought, cite as you go, hand a defensible note off.
  • If you write code
    Pair on the work between commits — the refactor, the test backfill, the design doc.
  • If you need to read the news
    One briefing across many sources. Hear it, don't just read it.
  • If you run an operation
    Connect what you already use, automate the bits that should be automated, watch what matters.
Access

The workshop is open.
Walk in.

Request access and we'll route you to the workspace that fits the shape of your work first. If you'd rather read the long version before you reach for it, the manifesto and the trust write-up are linked below — both honest about what's in the room today and what isn't.