Date: September 2, 2025
Status: SUPERSEDED (2026-07-26 — Arch fix-or-delete ruling 2026-07-25, decisions.log ~23:35 PT; PM-flagged per the #1322-supersession precedent). The runtime methodology/ package this ADR specified was deleted as a zero-importer dead island; the pyramid’s ideas live on as the cohort’s prose discipline (evidence-required, verify-first, completion-theater pattern family, the #1452 CI-arbitrated gate). Design lineage: docs/internal/architecture/current/design-record-methodology-as-code-2025.md.
Authors: Lead Developer (Claude Sonnet 4), Code Agent
Reviewers: Chief Architect, PM
AI agent coordination in the Piper Morgan project suffered from “verification theater” - agents claiming task completion without providing concrete evidence of functionality. This led to:
The core problem: agents could say “I implemented X” and we would accept that claim without requiring verifiable proof.
We implement a Three-Tier Verification Pyramid as the foundational framework for all agent coordination, requiring systematic evidence at each level before proceeding.
Level 3: Evidence Collection (Concrete Proof Required)
↑
Level 2: Integration Verification (Coordination Validated)
↑
Level 1: Pattern Discovery (Archaeological Search)
Problem: 60-80% of requested features already exist in some form Solution: Mandatory archaeological search before any implementation Implementation:
Problem: Features work in isolation but break system coordination Solution: Validate coordination requirements and dependencies Implementation:
Problem: Claims without verifiable proof lead to verification theater Solution: Concrete evidence required for all completion claims Implementation:
class VerificationPyramid:
async def verify(self, task: Dict[str, Any]) -> VerificationResult:
# Level 1: Pattern verification (find existing)
# Level 2: Integration verification (validate coordination)
# Level 3: Evidence verification (prove completion)
DISCOVERY_COMMANDS = {
'python': ['grep -r "{pattern}" --include="*.py"'],
'architecture': ['find docs/ -name "*.md" -exec grep -l "{pattern}" {} \\;'],
'methodology': ['grep -r "{pattern}" methodology/']
}
Risk: Agents circumvent verification requirements Mitigation: Framework integrated into core agent coordination protocols
Risk: Verification overhead slows legitimate work Mitigation: Caching and pattern recognition optimize repeat searches
Risk: Evidence requirements become bureaucratic Mitigation: Evidence types tailored to task types, automated where possible
Framework Operational: When agents cannot claim success without evidence Pattern Discovery: Finds existing implementations before allowing rebuilds Integration Assurance: Validates coordination requirements before deployment Evidence Standards: Concrete proof required, no theoretical solutions accepted
Rejected: Led to the verification theater problem we’re solving
Rejected: Doesn’t scale with AI agent speed and volume
Rejected: Misses coordination failures and duplicate work prevention
Rationale: Addresses all three core problems (theater, duplication, integration) with systematic approach
This ADR will be reviewed after Phase 2 implementation and full integration deployment. Framework will evolve based on:
Next Steps: Deploy Phase 2 evidence collection refinement, then integrate framework into active agent coordination workflows.