PlanWright
AI & Agents

AI & Agents

AI & Agents

Planwright is built for agents from day zero. Agents connect via a native MCP server, operate within a strict permission boundary, and produce a signed audit trail for every action they take.

How agents work

Model

Planwright is MCP-native. Agents don't receive webhooks — they call tools.

Agents connect via the Planwright MCP server and operate through structured tool calls. Every state change flows through the server, which validates the transition, appends a signed audit record, and notifies the human reviewer. Agents never mutate board state directly.

Agent lifecycle — steps in order

What the agent doesMCP tool
Select the projectplanwright_set_repo
Find scheduled workplanwright_list_objectives
Claim an objectiveplanwright_claim_objective
Post a decomposition planplanwright_append_plan
Request human review when doneplanwright_request_acceptance

Agent guardrails

Permissions

Agents operate within a strict permission boundary. Some things are intentionally off-limits.

CAN

List objectives in any lane

NOT

Transition objectives between lanes directly

CAN

Claim a scheduled objective

NOT

Self-approve — only humans can move work to Done

CAN

Post a decomposition plan

NOT

Modify or delete audit chain records

CAN

Request human acceptance

NOT

Bypass strategic classification at claim time

AI-created objectives

Creation

Agents can propose objectives and initiatives — humans decide what gets scheduled.

Agents can propose new work based on what they observe during a run. Proposed objectives land in the Backlog lane and stay there until a human schedules them.

What agents can propose

What the agent wants to createMCP tool
A new objective — missing test, regression, API gap, docs gap, compliance controlplanwright_create_objective
A new initiative grouping related follow-on workplanwright_create_initiative

Strategic alignment enforcement

Classification

Every objective must carry a strategic classification before it can be claimed.

Before claiming, an agent must provide a strategic classification if the objective doesn't already have user-assigned one — BUILD, GROW, TRUST, or SCALE — along with a confidence score from 0 to 1. Low confidence is fine: the system records it and surfaces it for human review. An objective with no classification cannot be claimed. This ensures every piece of work can be traced to a strategic intent, and that the portfolio allocation data in the Strategic Focus report is always complete.

GitHub-aware planning

Git integration

Agents follow a branch strategy returned at claim time and attach trailers to every commit and PR.

When an objective is claimed, the response includes a branchStrategy — either branch-pr or direct. The agent must follow it. Every commit must include both the Planwright-Objective and Agent-Run trailers so Planwright can attribute changes to the correct objective and run. Every PR opened by an agent must include the Planwright-Objective trailer in its body so the diff is linked automatically via GitHub webhook.

GitHub Integration →

Connect your agent

Pick your agent for a setup guide.

Advanced