From a rough brief to a verified pull request - every step, on one platform.
Penling covers the whole arc of AI-native engineering work: understand the ask, structure it into specs, hand it to an agent over MCP, and watch it get built and proven. Here's the full surface area.
Brief analysis & signal extraction
Paste anything - a Slack thread, a doc, a voice-memo transcript. Penling extracts outcomes, constraints, and open questions you confirm.
Suggested focus areas
Penling proposes how to break a goal into focus areas, each becoming a four-part spec: definition, results, conditions, boundaries.
Plan → publish over MCP
A plan a human shapes, then publishes to any MCP-compatible agent. Penling stays the source of truth.
The live build canvas
Watch the agent work and steer it live. Files, events, and checks fill in with evidence as the build runs.
Dashboard & audit trail
Every initiative, every action, every decision - in one place, exportable as CSV or JSON.
Capture & understand the ask.
Real work doesn't arrive as a clean spec. Penling reads the messy version and pulls out what matters.
Paste anything. Penling extracts the signal.
Drop in a brief, a Slack thread, a transcript, or a rough idea. Penling reads the whole thing and surfaces outcomes, constraints, out-of-scope items, and open questions as confirmable chips - nothing is assumed.
- Nothing assumed. Every extracted signal is confirmable - edit or dismiss before it becomes spec input.
- Open questions surface early. Unresolved unknowns are flagged in a distinct warn state, not buried.
- Out-of-scope is first-class. The agent knows exactly where the boundaries are before it touches a file.
Structure into specs.
Penling suggests how to break a goal into focus areas. You decide what to spec - then each one grows a definition, results, conditions, and boundaries.
Every goal becomes a four-part spec.
Penling proposes focus areas from your signals; you accept, edit, or replace them. Each becomes a spec with a definition, expected results, acceptance conditions, and explicit boundaries.
- Specs, not tickets. Results and conditions become acceptance checks downstream.
- Checks are explicit. The agent knows exactly where the edges of each focus area are.
- Boundaries are explicit. The agent knows where the edges of each focus area are before writing a single line.
Plan it, then hand it off over MCP.
A plan a human shapes, then publishes to whatever agent you already use.
One plan, any agent, over MCP.
Penling drafts an implementation plan from the spec. A human edits and approves it, then publishes it to an MCP endpoint. Bring Claude Code, Cursor, or any MCP-compatible agent - Penling stays the source of truth.
- Human-in-the-loop. Plans are published, not auto-run. You approve before the agent touches code.
- Bring your own agent. Penling speaks MCP, so your tools just connect.
- The plan is versioned. A focus area can carry several plans over its life.
Watch the build happen. The agent works, you steer.
One screen, three live columns - files, events, and checks filling in with evidence.
Every commit, test run, and decision streams over the Penling API.
Human and AI on the same canvas - answer a clarification and the build resumes.
A build can't complete until every check is paired with passing evidence.
See it all in one place.
Brings that need you are always one glance away.
The dashboard that actually tells you the truth.
Every initiative, its readiness, what's building, paused, or shipped - with a full exportable audit trail. “Needs you” is always one glance away.
- Readiness you can trust. Status reflects verified checks, not vibes.
- “Needs you” is explicit. Open clarifications surface to the top.
- Full audit trail. Every actor, every decision, exports as CSV or JSON.
Every capability has an actor, an artifact, and an audit record.
Nothing happens off the record. Here's who does what, and what it leaves behind.
See the whole arc, end to end.
Bring a brief and an agent. Watch Penling turn it into a spec, a plan, and a verified pull request - with the receipts to prove it.