Built in, not an integration
A full AI workspace, right at your desk
Chat, compare models side by side, run a research pass and generate images from one surface, in the same office your team works in. Pick a mode in the composer, and in Chat the workspace routes each request to a suitable model for you.
Model APicked
- 1. Feature flag depends on Thursday's migration.
- 2. Announcement copy not yet reviewed.
Model B
- 1. Feature flag depends on Thursday's migration.
- 2. Announcement copy not yet reviewed.
Routing picks the model for each task, so nobody has to.
- Meet
- Capture
- Act
One surface, many modes
Chat, compare, research and images, in one place
Ask a quick question, compare how two models answer the same prompt, research a harder question, or generate an image, without switching apps. The mode is set when you send the first message, so a conversation stays what it started as.
- Chat with the model routed for the task
- Side-by-side model comparison
- Web-cited research, images and multi-step pipelines
Ask anything, or pick a mode first…
- ChatConverse with the best-routed model.
- CompareSend one prompt to several models, side by side.
- ResearchWeb-cited answers with sources.
- ImageGenerate images from a prompt.
- PipelineRun a multi-step, templated workflow.
Keys and budgets you control
Your providers, your keys, your spending limits
Admins add your AI providers' API keys once; they are encrypted at rest and used only on the server, never in the browser. Each member works within an allowance your admins set, and can see what they have used and what is left.
- Provider keys entered by admins, encrypted at rest
- Per-member budgets with an alert before the limit
- Usage by model, mode and surface
Your allowance
Eligible
$20.00
this month
Used
$7.40
37% of budget
Remaining
$12.60
resets 1 Oct
Budget meter
Next to your work
Answers that end up where the team can use them
The workspace sits in the same office as your docs, tracker and chat, so a useful answer is one paste away from the page or the ticket it belongs to.
- Lives next to docs, tasks and chat
- One sign-in and one set of permissions
- Works with the providers your organisation chooses
Release checklist
Mei L.Linked to WEB-139
Every release follows the same steps. Tick them off here so the whole team can see where things stand.
Before you ship
- Changelog written and reviewed
- End-to-end suite green on staging
- Release notes posted in #launch
Related
Works with the rest of the office
Do I have to pick a model?
Whose API keys does it use?
Is my data used to train models?
How is it different from a chatbot in a browser tab?
Ask, and get on with the work
The AI workspace lives in the same office as your team, with keys your admins control.