Simple on the surface. A system underneath.
You ask a question. Set a goal. Give it direction. Follow what the Factory does with it.
- 01“Are there new product bugs?”
- 02“Build a Factory for this goal.”
- 03“How is my backlog?”
- 04“Why isn’t this moving?”
- 05“What is it doing now?”
- 06“Fix this.”
- 07“Did this issue come back?”
What matters. What is noise. What needs you.
Your domain decides which sources to read. Similar reports can share a work identity; similarity alone does not prove a shared cause.
- 01Declared sources
- 02Normalize signals
- 03Stable identities
- 04Evidence & causal families
- 05Material work
- 06Owner answer
Reliability adapters can interpret feedback and production evidence. Family membership needs canonical evidence; a distinct database failure must remain distinct. Raw inputs retain their provenance. No source is universally connected by default.
One goal. A work system built around it.
Start with northstar init. It creates a scaffold; the Domain Builder and readiness gates determine what is ready to run.
$ northstar init \ --dir packs/content-factory \ --slug content-factory \ --goal "Build an evidence-based content system"
- 01Goal
- 02Domain manifest
- 03Capabilities & sources
- 04Tools & permissions
- 05Evidence & verification
- 06Initial work
- 07Readiness
The pack defines work types, measurable goals, source adapters, guardrails, autonomy and executor posture. Bootstrap reconciles capabilities against the canonical map before READY. Credentials and integrations still require configuration. The original Content Factory was manually configured.
Show me what matters now.
Actionable work, current execution, evidence waits, owner decisions and outcomes each have a place. A large count is not a measure of progress.
- 01Project identity
- 02Latest snapshot
- 03Work projection
- 04Receipts + intents
- 05Lifecycle reconciliation
- 06Owner view
Every cloud read is scoped to the selected project. The local publisher derives work state from canonical backlog and receipts. An accepted request is not execution. ARVO and Content never share a backlog merely because titles look alike. Unknown or stale state stays visible.
Know the wait. Know the way forward.
Autonomous does not mean never blocked. Know what is blocked, who can resolve it, and which evidence allows work to resume.
- Affected work
- This investigation
- Needed
- A reproducible failure
- Wakes when
- New evidence is accepted
- 01Canonical interruption
- 02Category
- 03Item / mission / Factory scope
- 04Required action or evidence
- 05Resolution receipt
- 06Resumption evidence
OWNER, EXTERNAL, PROVIDER, EVIDENCE and RUNTIME / INFRA are different causes. Scope is shown only when recorded. Older receipts may not establish mission scope or human involvement. A fallback receipt proves an executor handoff; later progress must prove that work continued.
One current task. A reason. Real progress.
See the active executor and the last durable result separately. An alive process can still be making no measurable progress.
- Why
- Only a recorded selection reason
- Executor
- Observed local worker
- Progress
- Last durable receipt, not heartbeat
- 01Checkpoint
- 02Actionable work
- 03Selector
- 04Authority check
- 05Single execution seat
- 06Executor
- 07Durable receipts
The watch wakes the Factory. The selector chooses eligible work within authority. The execution seat protects the local loop. Executor liveness, wake schedule and durable progress are separate signals. Selection rationale is shown only when published, never invented from a title.
Your request enters the system. It does not skip the system.
Chat expresses intent. The local Factory accepts or rejects it, converges it with existing work where appropriate, then chooses when it is eligible.
- 01Chat / MCP intent
- 02Cloud receipt
- 03Local pull
- 04Canonical intake
- 05Selection & execution
- 06Independent verification
- 07Cloud readback
MCP can append project-scoped intake, roadmap priorities and supported Advisor decisions. Local pull materializes canonical work. Executors change the project; verifiers evaluate evidence; the ledger remembers. Execution-gate decisions still need the supported local resolution path. A connector installed in ChatGPT or Claude is a separate setup step.
Keep the recurrence. Refine the response.
A fix does not erase the problem’s history. New evidence can reopen work and motivate a refinement.
- 01Fix
- 02Independent check
- 03New contradictory evidence
- 04Recurrence / reopening
- 05Durable lesson
- 06Governed next work
Canonical receipts preserve earlier fixes and new evidence. Strategic memory can carry lessons into future work. Framework retrospectives propose changes; they do not grant themselves authority to modify policy. A proposal, an adopted rule and a verified improvement are different facts.
Five views. And a time machine.
One screen per question an owner actually asks. The screens below use sample data; the interface is in Italian.
The project changes. The operating rules don’t.
The pack teaches the kernel what sources, tools, evidence and outcomes mean here.
Product / Reliability
Reduce material product risk.ARVO provided the original reliability experience. Its public cloud view is coming online; no live release-readiness number is implied.Marketing / Content
Build a compounding content system.danielepelleri.com has published outputs. Observed execution and measured audience growth are separate facts.Sales / Revenue
Keep qualified opportunities moving.The cross-domain sales proof exercises the shared kernel. Live CRM connections and commercial outcomes are not claimed.Why the answer can be trusted.
One project identity
Content work stays with Content. Switching to ARVO must change every read.One execution seat
A second worker cannot simply take the same local seat.Intent is not execution
“Received in cloud” still means the Mac may not have read it.Merged is not deployed
A merge receipt does not prove the release reached users.The worker cannot certify done
An executor’s “finished” is not an independent verdict.Waiting is a real state
Missing evidence keeps work parked with a wake condition.A blocked item need not stop everything
Independent work can continue when the authority and selector permit it.Cloud guides. Local executes.
Your phone reads state; your machine operates the repository.Configured is not live
A configured publisher is not proof of a fresh observation.Done must reconcile
External delivery and local lifecycle must agree.Three flows. One project history.
Cloud holds observations and intent. The project’s local Factory owns execution and durable evidence. No chat session becomes the source of truth.
Observe
- 1Sources
- 2Domain adapters
- 3Canonical evidence
- 4Cloud read model
- 5Web / MCP readback
Direct
- 1Chat client + MCP
- 2Cloud intent
- 3Local pull
- 4Canonical intake / decision
- 5Eligible work
Execute
- 1Backlog / roadmap
- 2Selector + Governor
- 3Local executor
- 4Independent verifier
- 5Ledger / governed learning
Now see a real Factory.
Current observations, with their age and limits made visible.





