The editor for the agent era

Agents write.
You edit decide.

terser is your agent's favorite way to write documents — and yours to review them. Nothing ships without human sign-off.

Be part of the first wave — the first 100 seats are free

Works with the world's finest models

launch-notes.md
J C ai

Launch notes — v2 editor

The new editor ships with collaboration that we think is pretty solidholds up under real concurrency. Every participant — human or agent — submits steps to one authoritative log.

Agents don't get a side door. They connect over the same live protocol as the browser, and their edits land as tracked suggestions that are applied immediatelyawaiting human review.

Rollout begins next week, starting with design partners.

Get started

Up and running in a minute.

No SDK, no glue code — the editor, the CLI, and the MCP server are already wired together.

01

Sign up & create a doc

Create a free account and open your first document. The editor lives in the browser — live collaboration from the first keystroke, nothing to install.

Sign up free

02

Connect your agent

One command plugs Claude Code, Cursor, or any MCP client into your workspace. Grab an API key from the command palette and you're wired up.

$claude mcp add terser https://terser.dev/api/mcp

03

Give it the brief

Ask the way you'd ask a colleague. The agent reads your workspace skills and drafts straight into the live document.

you → claude

“Draft a design doc for the billing rework — context, options, decision.”

04

Review & accept

The draft lands as suggestions, attributed to its author. Accept, reject, or roll back — that's the loop.

Decision: ship usage-based billing behind a flag.

How it works

One document, with all interfaces.

Humans in the browser, agents over CLI and MCP, programs over the API — every interface is first-class, every edit is accounted for, and nothing lands without passing the review gate.

Humans

UI

the live browser editor

Agents

CLIMCP

Claude Code, Cursor, pipelines

Programs

API

typed HTTP · OpenAPI spec

launch-notes.md v214

One document, edited by whoever got there lasteveryone at once — every edit a tracked, reviewable step in one authoritative history.

same live connection · same suggestion rules · same review gate

Exported

PDFMarkdown

Shared

colleaguesorgs

Published

internet link

01

Agents do the writing

AI agents read, draft, and revise over the same live connection as your browser — via CLI or MCP. First-class authors, not a bolted-on assistant.

02

You do the deciding

Every agent edit lands as a tracked proposal, attributed to its author. Accept, reject, or roll back — nothing ships without your sign-off.

03

Every word accounted for

All authors converge on one authoritative history. Every revision is recorded, every conflict resolves, every word is recoverable.

Security

Secure by default. Yours by design.

Letting agents write into your documents takes trust. We earn it twice: by running like a security-first company, and by keeping your documents in storage you control.

Security is the day job.

An editor your agents write through sits inside your supply chain — we build and run it accordingly, to the standards you'd audit us against.

  • SOC 2 Type II controls
  • GDPR-aligned data handling
  • TLS in transit, AES-256 at rest
  • SSO, SAML & SCIM provisioning
  • Scoped, revocable API keys for every agent
  • Append-only history — every edit attributed, nothing erased

You own your data.

Bring your own storage: point terser at a bucket you own and every document, snapshot, and step of history persists in your infrastructure. Leave anytime — your documents were never anywhere else.

launch-notes.md v214

Stored in someone else's cloudyour bucket.

TLS in transit · AES-256 at rest

Your bucket

s3://acme-docs/terser

yours
AWS S3Google CloudAzure BlobS3-compatible

your region · your keys · your retention

Run it entirely on-prem.

Deploy terser inside your own perimeter — nothing leaves your network. And it never falls behind: we keep your on-prem instance current with every release, so the latest features and security fixes land for you without drifting onto a stale fork.

terser release latest · v214
kept up to date

your network

terser, self-hosted

running · v214

current

your hardware · your perimeter · latest release

The review gate

Suggestions, not silent edits.

Agent edits arrive as tracked changes in the document — green for proposed text, red for proposed cuts — each attributed to its author and waiting on your verdict.

  • Accept or reject suggestion by suggestion, or sweep a whole revision
  • Rollback is first-class: any accepted change can be unwound
  • Viewer, suggester, and editor roles enforce who can do what
Suggestions 3 pending
  • claude · agent

    holds up under real concurrency

  • claude · agent

    we think is pretty solid

  • claude · agent

    awaiting human review

The agent surface

Your agent already speaks terser.

A CLI for scripts and pipelines, a hosted MCP server for Claude, Cursor, and friends — both thin wrappers over the same command core the UI uses. No side door, no stale copies.

  • Same live OT connection as the browser — agents see edits as they happen
  • One command connects any MCP client
  • Typed HTTP API with an OpenAPI spec underneath
zsh — agent session

$ terser read launch-notes

# Launch notes — v2 editor …

$ terser edit launch-notes --suggest

3 suggestions submitted · v214

$ claude mcp add terser https://terser.dev/api/mcp

agents speak terser natively — CLI or MCP

The house style

Every author, one voice.

Writing skills are guidance documents — a style guide, tone rules, a doc template — that agents consult before they draft. Author them once in the editor; every connected agent writes your way.

  • Skills are ordinary documents: edit them live, version them, review changes as suggestions
  • Served to agents over CLI and MCP before a word hits the page
  • Share the workspace and the whole team — humans and agents — writes to one standard
Writing skills served to every agent
  • style-guide House voice: plain, direct, no filler serving
  • design-docs Specs run context → decision → trade-offs serving
  • release-notes Changelog entries: terse, user-facing, present tense serving

claude read terser://skill/style-guide before drafting

The sharing model

Share wide. Stay in control.

Invite a person by email, grant a whole organization in one row, or mint a link anyone can open — three grant kinds, one dialog, the same roles everywhere.

  • Viewers read, suggesters propose tracked changes, editors decide
  • Share from anywhere: the dialog, the CLI, or an agent over MCP
  • Links are viewer-only by design — every edit carries its author, so write access never rides an anonymous URL
Share “Launch notes” viewer · suggester · editor

People

  • mara@acme.com editor
  • sam@studio.dev suggester
  • jo@acme.com invited viewer

Organizations

  • Acme Inc suggester

Link access

terser.dev/l/u3K9fQx… viewer

anyone with the link can view — no account needed

The history

One log. The whole story.

Every step — human or agent, draft or verdict — appends to one authoritative, replayable history. The audit trail isn't a feature on top of the document; it is the document.

  • Server-authoritative OT: conflicts resolve, nothing forks
  • Every word recoverable, every author accountable
  • Replay the log and you have the document — at any version
History append-only · every step recorded
  • v211 john Drafted the rollout section committed
  • v212 claude Suggested: tighten "collaboration" paragraph accepted
  • v213 claude Suggested: cut "applied immediately" pending
  • v214 john Accepted 2 suggestions · rolled back 1 committed

Use cases

Where terser earns its keep.

Anywhere a document has to track a moving target. The agent keeps the draft moving; a human keeps it true.

Engineering decision logs

Architecture calls get captured while the discussion is still warm — the agent drafts the decision record from the thread, options and trade-offs included. The log stays honest because writing it down costs nothing.

agent drafts the record from the thread you sign the decision

adr-031-event-bus.md

claude · suggesting

Decision: adopt NATS over Kafka — ops cost dominates at our scale.

Documentation that stays current

Wire an agent to your merges. It walks the docs, finds what each change made stale, and files the fix as suggestions — page by page, attributed and reviewable.

agent proposes updates on every merge you approve what's true

docs/authentication.md

claude · suggesting

Sessions expire after 24 hours30 days, refreshed on use.

Release notes & changelogs

The agent reads the merged PRs and writes user-facing notes in your house style — terse, present tense, no commit hashes. Release week becomes a review pass.

agent writes from the merged PRs you cut what doesn't matter

changelog.md

claude · suggesting

v2.4 — share a doc with your whole organization in one row.

Specs & RFCs

Review feedback lands as tracked suggestions, the agent folds it into the draft, and the open questions stay visibly open until a human settles them.

agent folds in the feedback you settle the open questions

rfc-usage-billing.md

claude · suggesting

Pricing: both models at launchmetered only — seats return in phase two.

Incident postmortems

While you're still firefighting, the agent reconstructs the timeline from logs and channels into a draft. The analysis and the action items stay human.

agent assembles the timeline you own the lessons

postmortem-2026-06-04.md

claude · suggesting

14:02 deploy 8841 ships · 14:09 p99 ×4, pager fires

Runbooks & onboarding guides

Agents that follow runbooks notice stale runbooks first. When a step doesn't match reality, the fix arrives as a suggestion instead of a Slack complaint.

agent flags drift as it works you accept the patch

runbook-key-rotation.md

claude · suggesting

3. Run scripts/rotate.shterser keys rotate --all.

Word of mouth

Taken at their word.

We pointed an agent at the changelog and stopped dreading release week. The notes draft themselves overnight — I just show up with the red pen.
ML

Mara Lindqvist

Head of Platform, Nordwind Systems

In Notion the AI rewrites the page and you hope you'd notice. Here every agent edit is a suggestion with an author on it — accept, reject, roll back. Legal signed off in a week.
DO

Devon Okafor

Staff Engineer, Brightline

Our decision log went from tribal knowledge to an actual log. The agent drafts the record while the discussion is still warm; we just sign it.
PR

Priya Raghavan

Director of Engineering, Hatch Labs

01 / 02

Pricing

Start free. Scale by the seat.

The full editor, the CLI, and the MCP server are in every plan — you pay for the people, never the agents.

Personal

$0 free forever

The whole single-player product — your documents, your agents, and the full review loop.

  • Unlimited documents
  • Agents over CLI & MCP — one alongside you
  • Tracked suggestions — accept, reject, roll back
  • Full revision history
  • 3 writing skills
  • PDF & markdown export

Team

most teams start here

$5 / seat / month

Share the workspace. Humans take seats — agents ride along free.

  • Everything in Personal
  • Unlimited agents in parallel
  • Organizations & member management
  • Viewer / suggester / editor roles
  • Share links anyone can open
  • Unlimited writing skills
  • Threaded comments

Start 7-day free trial

Free for the first 100 sign-ups

no credit card needed

Enterprise

Custom

For organizations with their own rules about identity, storage, and audit.

  • Everything in Team
  • SSO & SAML
  • SCIM provisioning
  • Audit log export
  • Bring your own storage
  • Dedicated support & SLA

Put your agents to work.

Open a document, connect an agent, and keep the final cut.