Skip to main content

Development Workflow — Two-Layer Planning Model

How strategy and execution are separated between humans and AI agents in Bitcoinology.

The Model

Key Principle

Nobody prescribes how to implement. Only what "done" looks like.

  • Executives define milestones with verification criteria and human gates
  • Agents read those milestones, study the codebase, create their own work breakdown, and execute
  • Human gates are checkpoints where execution pauses for executive review

Two Layers Explained

Linear — The Executive View

Linear holds the strategic layer. Executives see projects, milestones, and high-level progress.

Each milestone has:

  • Verification criteria — concrete test that proves it's done
  • Human gate — executive must approve before next milestone starts

Beads — The Execution View

Beads (bd) holds the agent's work breakdown. The agent creates its own epics, tasks, and dependency graph.

The agent decides:

  • How many tasks to create
  • What dependencies exist between them
  • What order to execute
  • How granular to go

The /ship Loop

The Factory Droid runs the /ship command, which follows this cycle:

Milestone Verification Criteria

Each milestone has a specific test. The executive runs these to verify:

MilestoneVerificationHow to Test
Hybrid Search LiveExact terms return accurate resultsSearch "UTXO consolidation" in the app
BYOK Key Management LiveUser's key is used for LLM callsCheck OpenAI dashboard — query should NOT appear on our account
User Tiers EnforcedFree tier capped at 10/daySend 11 search queries as free user
Oracle AgentComplex queries decomposeAsk "How has Lightning narrative evolved?" — check sub-queries in trace
Citation GateNo ungrounded claims passReview 10 responses — every claim should cite episode + timestamp
Deep Research E2EFull pipeline worksRun flagship query, verify multi-step cited output
All 8 WorkflowsEach workflow functionalTest each with 3 example queries from PRD
Contextual EmbeddingsRetrieval improvesA/B comparison on 20 queries
Platform FeaturesEach feature worksManual test: X login, export, audio, analytics

Chain of Command

Tools

ToolRoleUsed By
LinearProject management, milestones, human gatesExecutives
Beads (bd)Task tracking, dependency graph, agent memoryAgents
Factory DroidAI implementation agentAutomated
Claude CodeCEO / orchestratorStrategic
GitHubCode hosting, PRs, CIEveryone
VercelProduction hosting, auto-deploy from mainAutomated

Key Files

FilePurposeAudience
AGENTS.mdAgent instructions, conventions, guardrailsDroid
.factory/droids/ship.md/ship command — autonomous implementation loopDroid
.factory/commands/ship.md/ship triggerDroid
docs/gap-analysis.mdWhat to build — 13 gaps, 3 phasesEveryone
docs/gap-analysis-technical-risk.mdSecurity & scalability findingsEveryone
docs/gap-analysis-user-journey.mdUX gap findingsEveryone

Established 2026-02-24. The two-layer model ensures agents have autonomy to plan while executives retain control at milestone boundaries.