Penling penguin markPenling
01

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.
Penling · New initiativeAnalyze brief
Analyzing· PASTED 612 WORDS · 4 SIGNALS FOUND

Build a simple to-do app that works offline. Users should be able to add tasks, mark them complete, and delete them. Data should persist between sessions. Keep it minimal - no accounts, no sync, no backend...

Extracted signals · confirm to keepAI-suggested
OutcomeAdd, complete, and delete tasks
OutcomeData persists between sessions
ConstraintNo accounts, no sync, no backend
Out of scopeReal-time collaboration
?Open questionWhat offline storage strategy - localStorage, IndexedDB, or Service Worker?
NOTHING IS SAVED UNTIL YOU CONFIRM · EDIT ANY SIGNAL INLINE
02

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.
Penling · Todo AppSuggested focus areas
Suggested · pick what to spec3 suggested

Penling broke the goal into focus areas.

Task model & persistence
RWTA-1 · 4-part spec
Add / complete / delete UI
RWTA-2 · 4-part spec
Empty & loading states
RWTA-3 · 4-part spec
Add
Write your own focus area
EACH BECOMES A 4-PART SPEC: DEFINITION · RESULTS · CONDITIONS · BOUNDARIES
03

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.
Penling · RWTA-3Plan · published
Published to MCP· DRAFTED BY AI · EDITED BY PAUL

The plan a human shaped, handed to any agent.

01Scaffold project + configure bundler
02localStorage task store with persistence
03Add / complete / delete UI handlers
04Tests per each acceptance check
MCP endpoint · connected
penling://build/RWTA-3
· claude-code · cursor · any MCP agent
The build canvas · live

Watch the build happen. The agent works, you steer.

One screen, three live columns - files, events, and checks filling in with evidence.

PenlingRWTA-3Build #1
Building · live
Working tree
src/
index.html
store.js+48
app.js+12
tests/
store.test.jsnew
Event stream
Paul resolved clarification CL-12 - max length 25
just now
AI
Penling AI committed store.js - localStorage task store
12s ago
AI
Penling AI running acceptance check 03
now
?
What max length should the task input enforce?
Paul → 25 characters, don't enforce it.
Acceptance checks2 / 4
01Add task saves to store
store.test.js:14
02Complete toggles done flag
store.test.js:31
03Delete removes from list
running test…
04Persist survives page reload
awaiting build
EVIDENCE ATTACHES AS EACH CHECK PASSES
Real-time

Every commit, test run, and decision streams over the Penling API.

Collaborative

Human and AI on the same canvas - answer a clarification and the build resumes.

Self-proving

A build can't complete until every check is paired with passing evidence.

04

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.
Penling · My Penling
Dashboard · this week
3
Initiatives active
11
Checks verified
2
Need you
Real working ToDo AppBuilding
3 actions · 1 live
Billing portal v2Paused
clarification open
Search re-index jobShipped
PR #218 merged
At a glance

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.

Capability
Actor
Artifact produced
Audited
Signal extraction
AI suggests, human confirms
structured signals
Focus area suggestions
AI suggests, human picks
n-part specs
Plan generation
AI drafts, human edits
published plan
MCP build
agent builds, human steers
commits + PR
Clarifications
AI asks, human replies
Q&A log
Acceptance checks
AI verifies
check + test evidence

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.

Start free trialSee how it works