Skip to main content
collaib

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

RFC-014 DRAFTAPPROVED 10:18 / PRIYA RAMAN
Detail60-second walkthrough

A 60-second review walkthrough: anchored comments, an @AI reviewer, and sign-off.

Try it on your own doc: start free.

SheetDetail A
DrawingReview walkthrough
RevisionA
Sheet 02

The way engineering teams review documents is broken.

NOTIONGITHUBLINEARSLACKTHE SPECTHE PRTHE TICKETTHE DISCUSSIONONE REVIEWERREBUILDS THE PICTURE
01

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.

02

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.

03

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.

Sheet02 of 07
DrawingExisting condition
RevisionA
Approved byPending
Sheet 03

How it works

Audit trail, as recorded
ActorClassEventTime
Claude Codeagent, run #a4f2, cred c7e1Published draft09:41
Priya Ramanhuman, lead engineerLeft 3 inline comments10:02
Claude Codeagent, run #b3c9, cred c7e1Replied to 2 comments10:03
Priya Ramanhuman, lead engineerApproved10:18
Step 01

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.

Step 02

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.

Step 03

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.

Sheet03 of 07
DrawingSequence of operations
RevisionA
Approved byPriya Raman, 10:18
Sheet 04

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.

Schedule 4.1Specification notes
ItemAssemblyNote
01AttributionYou know exactly who, or what, wrote every word. Agent identity is bound server-side to the credential used to publish, never caller-asserted.
02Review workflowCode-review-grade approvals for documents. Review states are first-class, not emoji reactions on a comment.
03Co-editingCRDT-anchored comments stay pinned to the exact passage they reference as the document is edited around them.
04ContextLink PRs, issues, and tickets to a document. Their live status shows in the context panel beside the doc.
05Human oversight by designAgent approvals are advisory until a human confirms. The approval gate is not a setting, it is how the system works.
06Append-only audit logAll mutations of tenant data write an event in the same transaction. Insert-only code paths, no update or delete surface.
07Scoped, expiring agent credentials90 days by default, revocable at any time, scoped read-only or read-write, bound to one organization.
08AES-256 encryption at restDocument content, review marks, comment bodies, and approval notes are encrypted with AES-256-GCM before storage.
09SOC 2 Type II plannedThe program has not yet started. Our subprocessors (Convex, Vercel, Fly.io) hold their own SOC 2 certifications.

Full details in our security overview.

Sheet04 of 07
DrawingAssemblies and spec notes
RevisionA
Approved byPriya Raman, 10:18
Sheet 05

One command, any agent

claude mcp add collaib https://app.collaib.space/mcp

15 tools, any agent runtime, no SDK required.

Sheet05 of 07
DrawingInstallation detail
RevisionA
Approved byPriya Raman, 10:18
Sheet 06Issued for construction

Getting started

Step 01

Sign in

Google or GitHub. No credit card, no sales call. Free while collaib is in beta.

Step 02

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.

Step 03

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/mcp
Sheet06 of 07
DrawingStart-up procedure
RevisionA
DetailNotice to proceed

Review your next RFC with your team and your agents.

Free while in beta. Google or GitHub.

Start free

Building this with us? Become a design partner.

SheetDetail B
DrawingSign-up
RevisionA
Sheet 07Issued for signature

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.

Signed  /  _______________________Date  /  ____________
Sheet07 of 07
DrawingDesign partner intake
RevisionA