Your coding agents got 10x faster. Your pipeline didn't.

The Control Plane for Agent Labor

Your coding agents got 10x faster. Your pipeline didn't.

Speed moved to the middle and left the ceremonies behind. Planwright inverts the two that are still human-paced: it turns your chaos — transcripts, decks, email, Slack — into objectives, and triages acceptance so you rule only on what needs judgment. Planning and acceptance finally move at agent speed, and every ruling is signed.

Connect your agentsSee how the acceptance gate works →

Claude Desktop · MCP

› planwright\_list\_objectives

↳ “Reposition homepage” · scheduled ↳ “SOC 2 export bundle” · scheduled

› planwright\_claim\_objective

↳ claimed · agent run started

The Problem

You bought the agents.

Coding used to be the bottleneck. Not anymore. Now the constraint is everything you didn't automate:

Planning

A human hand-typing tasks at UI speed to feed machines running thousands of times faster.

Acceptance

A senior engineer reading pull requests one at a time — which is exactly where velocity goes to die.

Make the middle free and infinitely fast, and the edges become the ceiling. That's not a tooling gap. It's Amdahl's law.

The Fix

Invert the two ceremonies coding agents can't remove.

Front bookend

Invert planning: chaos in, objectives out.

Your planning input was never tidy — it's meeting transcripts, decks, email threads, Slack. From inside Claude Desktop, Planwright synthesizes that raw signal into structured objectives with machine-checkable acceptance criteria. The old ceremony had a human write the plan and the tool record it. Planwright flips it: the agent drafts, you approve — at the speed of describing what you want.

Back bookend

Invert acceptance: triage, don't drown.

When objectives complete, Planwright picks them up and triages acceptance in Claude Cowork — combing the plain, mechanical criteria and clearing what it safely can, then routing the critical, judgment-bound items to you. The machine doesn't accept; it sorts. You stop reading every diff and start ruling only on what actually needs a human, so your scarce judgment gets concentrated instead of flooded. Every ruling is signed.

The Acceptance Gate

The machine doesn't accept — it sorts.

The state machine ensures a human rules on every judgment call before work reaches “done.” Mechanical criteria get cleared automatically; critical decisions route to you. Your sign-off is the change-approval control point your SOC 2 auditor is looking for.

Scheduled

Human

Human sets the objective and schedules it for agent pickup.

In Progress

Agent

Agent claims the work, plans, codes, and records diffs via MCP.

Acceptance

Human

Agent requests acceptance. A human reviews the diff, tests, and signs off.

Done

Human

Human approves. The audit record is sealed and hash-chained.

Every lane transition produces a hash-chained, cryptographically signed audit record. The chain is independently verifiable on the public trust page.

How It Works

Three primitives. One throughput unlock.

Turn chaos into objectives.

In Claude Desktop, Planwright synthesizes your transcripts, decks, email, and Slack into structured objectives with machine-checkable acceptance criteria. You approve intent instead of hand-authoring tasks.

Triage acceptance, don't drown in it.

When objectives complete, Planwright combs the mechanical criteria in Claude Cowork and clears what it safely can, routing only the judgment calls to you. The machine doesn't accept — it sorts.

Every ruling is signed.

Machine-cleared throughput stays accountable: each human decision is a hash-chained record, not an ad-hoc PR read.

The Board

Objectives flow. Agents execute. Humans approve.

Backlog1

Add webhook retry logic

Scheduled1

Migrate auth to PKCE flow

In Progress2

Implement ECDSA P-256 audit signing

claude-code

Add RLS policies for workspaces

cursor

Acceptance1

SSE transport for MCP server

claude-code

Done1

Database schema v1

codex

How It Works

Five steps. Zero busywork.

01

Write an objective

Describe the outcome you want. Not the steps. Not the implementation. A clear, atomic objective your agent can own end-to-end.

02

Your agent claims it via MCP

Claude Code connects to your Planwright board, picks up scheduled objectives, and starts working. No copy-pasting tickets. No context-switching.

03

Agent plans, executes, requests acceptance

The agent decomposes the objective, writes code, runs tests, and moves it to the acceptance lane. Every step recorded in the audit chain.

04

You review and sign off

Every acceptance is a cryptographic signature. Not a checkbox. A real approval with your identity bound to it.

05

Every step hash-chained and signed

Immutable audit trail from objective creation to final merge. SOC 2 evidence that writes itself.

Compliance

SOC 2 auditors are raising the bar on AI-generated code.

Under the 2026 Trust Services Criteria, auditors increasingly expect immutable, tamper-evident audit trails and documented change-approval controls for AI-driven changes. Most PM tools can't produce them. Planwright ships this as a core primitive — hash-chained, ECDSA P-256-signed, from the first objective to the final merge.

Audit Ledger — Workspace planwright-core

#00042a3f8c1d9e2b7...objective.transitionedin\_progress → acceptance2026-04-10T14:32:07Z

#000417e2b4f91c8a3...agent.run.completedclaude-code · 12 files changed2026-04-10T14:31:55Z

#00040d5c9a8b3f7e1...agent.run.startedclaude-code claimed OBJ-00172026-04-10T14:28:03Z

Read the compliance brief →

Get Started

One command. Every agent.

No tokens. No config files to hand-edit. Run the install command — your browser opens for GitHub login, and you're connected.

Claude CodeClaude DesktopCursorCodexAmpHermesOpenClawOther / Generic

claude mcp add planwright --transport http https://mcp.planwright.tools/mcp

Copy

Zero-config. Run this command and your browser opens for GitHub login. The connection is cached for future sessions.

1Run the connect command above

2Log in with GitHub in your browser

3Pick your workspace (if you have more than one)

For CI and service accounts that can't open a browser, generate a static token in Settings → MCP Token after signing in. Audit records attribute to the token creator.

Need more detail? Read the full Claude Code setup guide →

Pricing

Start free. Scale when you're ready.

Every plan includes the MCP server, audit chain, and board. Pay for seats and retention depth.

Free

$0

For solo developers trying agent-native planning.

• Up to 3 seats
• 1 project
• 30-day audit retention
• Community support
Get started free

Team

$15/seat/mo

For small teams shipping with agents every day.

• 4–10 seats
• Unlimited projects
• 1-year audit retention
• Public trust page
• GitHub App integration
Start free trial

Most popular

Business

$39/seat/mo

For teams that need compliance out of the box.

• 11–50 seats
• Unlimited projects
• 3-year audit retention
• Custom domain trust page
• Priority support
• Advanced analytics
Start free trial

Enterprise

Custom

For organizations with regulatory requirements.

• 51+ seats
• 7-year audit retention
• SSO / SAML (roadmap)
• SOC 2 attestation letter (roadmap)
• Dedicated support
• Custom integrations

FAQ

Questions teams shipping with AI ask.

Can I manage my Planwright board from Claude Desktop?

How does Cursor or Codex integrate with Planwright?

How is this different from Linear's built-in agents?

What does 'AI-client-native' mean in practice?

Does the audit chain satisfy SOC 2 Trust Services Criteria for AI-generated code?

How does the acceptance gate work for HIPAA-regulated teams?

Can we use Planwright for FedRAMP Moderate workloads?

How does this compare to Linear or Plane for regulated teams?

What's the difference between the audit chain and a git log?

Can FINRA-regulated teams use AI agents with Planwright?

Is there a self-hosted option for air-gapped environments?

How much does it cost?