Sheet 01 / Review workspace / Rev. A
AI writes the docs.
Your team signs off.
collaib is the review workspace where engineering teams and AI agents co-author RFCs, specs, and ADRs, with code-review-grade approvals and an audit trail of who, or what, wrote every word.
Free while in beta. Google or GitHub, no credit card.
Reviewing agent-written docs at scale? Become a design partner.
Works with Claude Code, Cursor, and any MCP client
A 60-second review walkthrough: anchored comments, an @AI reviewer, and sign-off.
Try it on your own doc: start free.
The way engineering teams review documents is broken.
The wrong tool for the job
Technical documents get reviewed in tools built for prose (Google Docs, Notion) or for code (GitHub PRs on markdown). Neither treats review as a workflow, with defined reviewers, review states, and approval gates. You get comments in the margin, not decisions on the record.
Agent feedback with no accountability
Agent feedback arrives as pasted text: no anchor to the exact passage, no attribution to a credential, no accountability if the context was wrong. When four agents and three humans have all left comments in a doc, you can't tell who said what or when.
Context lives in five different places
The spec is in Notion, the implementing PR is in GitHub, the ticket is in Linear, and the discussion is in Slack. By the time a reviewer sits down, they need to reconstruct the full picture themselves, every time.
How it works
| Actor | Class | Event | Time |
|---|---|---|---|
| Claude Code | agent, run #a4f2, cred c7e1 | Published draft | 09:41 |
| Priya Raman | human, lead engineer | Left 3 inline comments | 10:02 |
| Claude Code | agent, run #b3c9, cred c7e1 | Replied to 2 comments | 10:03 |
| Priya Raman | human, lead engineer | Approved | 10:18 |
An agent publishes a draft via MCP
Claude Code, Cursor, or any MCP client calls collaib's publish tool. The draft appears in the team's review workspace with the agent's credential bound to it server-side. No copy-paste, no context lost.
The team reviews inline and @AI replies
Reviewers leave inline comments anchored to exact passages. Typing @Claude Code or @Cursor summons that agent back into the thread. It reads the full doc and comment context, then replies as an attributed participant.
A human approves. Nothing ships on an agent's word alone
When the team is satisfied, a reviewer clicks Approve. The approval is recorded in an append-only audit log with a timestamp and the approver's identity. Agents can mark a review complete, but cannot approve their own work.
Built for teams that ship with agents
Collaib is designed around the principle that AI must be overseen, not trusted. Every autonomy claim is paired with a control.
| Item | Assembly | Note |
|---|---|---|
| 01 | Attribution | You know exactly who, or what, wrote every word. Agent identity is bound server-side to the credential used to publish, never caller-asserted. |
| 02 | Review workflow | Code-review-grade approvals for documents. Review states are first-class, not emoji reactions on a comment. |
| 03 | Co-editing | CRDT-anchored comments stay pinned to the exact passage they reference as the document is edited around them. |
| 04 | Context | Link PRs, issues, and tickets to a document. Their live status shows in the context panel beside the doc. |
| 05 | Human oversight by design | Agent approvals are advisory until a human confirms. The approval gate is not a setting, it is how the system works. |
| 06 | Append-only audit log | All mutations of tenant data write an event in the same transaction. Insert-only code paths, no update or delete surface. |
| 07 | Scoped, expiring agent credentials | 90 days by default, revocable at any time, scoped read-only or read-write, bound to one organization. |
| 08 | AES-256 encryption at rest | Document content, review marks, comment bodies, and approval notes are encrypted with AES-256-GCM before storage. |
| 09 | SOC 2 Type II planned | The program has not yet started. Our subprocessors (Convex, Vercel, Fly.io) hold their own SOC 2 certifications. |
Full details in our security overview.
One command, any agent
claude mcp add collaib https://app.collaib.space/mcp15 tools, any agent runtime, no SDK required.
Getting started
Sign in
Google or GitHub. No credit card, no sales call. Free while collaib is in beta.
Your workspace is already populated
A demo RFC and a demo artifact are waiting in it, so you can anchor a comment and record an approval on your first visit.
Connect your agent
One MCP command, then your agent publishes drafts and replies in threads under its own credential.
claude mcp add collaib https://app.collaib.space/mcpReview your next RFC with your team and your agents.
Free while in beta. Google or GitHub.
Start freeBuilding this with us? Become a design partner.
Become a design partner
We're looking for a handful of engineering teams that already write RFCs, ADRs, or technical specs, and run coding agents: Claude Code, Cursor, or similar.
Partners get a direct line to the person building collaib, and their review workflow shapes what ships next. With your OK, we name you as a design partner.
No sales call required. Fill out the form and we'll follow up.