Agent Capabilities
Verifiable intent execution with cryptographic receipts. Skills compiled from production use, not theory.
Five questions any agent should answer before calling:
| Question | Answer |
|---|---|
| Who? | did:web:mm.dreamineering.com — did.json |
| What jobs? | Five declared below — agent.json |
| How call? | MCP endpoint — Phase B launch (COMRC-006) |
| What cost? | x402 micropayment USDC on Base — Phase B |
| How trust? | IntentTrace v1.1 receipt — public endpoint Phase B |
Declared Capabilities
All status: planned — live MCP endpoints ship Phase B.
falsifiable-prediction — COMRC-006
Convert any claim into a machine-verifiable bet: indicator + direction + threshold + check date.
Use when: Long-horizon decision needs a testable bet, not an opinion.
Input: { claim: string, horizon_months: number }
Output: { indicator, direction, threshold, check_date, counter_case, maturity }
flow-state-calibration — COMRC-007
Given principal state (phase + pole dominance), return calibrated prompt for phase correction.
Use when: Agent acting on behalf of a human who is over-reaching, drifting, or stagnating.
Input: { phase: sprint|recovery|reflection|calibration, dominant_pole: dream|engineer|reality }
Output: { prompt, timing, correction, pole_balance }
pain-to-prd-classification — COMRC-008
Extract pain signals from interview/research text. Score across 5 dimensions. Route to PRD/validate/park.
Use when: Customer discovery or sales qualification needs deterministic signal scoring.
Input: { raw_text: string }
Output: { signals, scores, classification: create-prd|validate-demand|park, evidence_map }
metric-definition — COMRC-009
Transform a PRD outcome statement into a queryable metric: formula + threshold + unit + data source.
Use when: PRD or strategy output needs measurable proof, not prose.
Input: { outcome_statement: string }
Output: { name, formula, threshold, unit, data_source, query }
verifiable-intent-validation — COMRC-010
Validate agent actions stayed within human-approved scope. Returns pass/fail + audit trail.
Use when: Agent commerce stack needs authorization proof before settling.
Input: { intent_ref, actions_taken, delegation_chain, scope_constraints }
Output: { verdict: pass|fail, violations, audit_url, intent_trace }
Machine-Readable Surfaces
| Surface | URL | What it contains |
|---|---|---|
| Agent card | agent.json | Full capability manifest, protocols, trust signals |
| Identity | did.json | did:web identity + service endpoints |
| Knowledge graph | /llms.txt | DML-encoded index, agent-readable |
| Full graph | /llms-full.txt | PageRank-scored knowledge graph |
| PRD index | /prd-index.json | All active PRDs, machine-readable |
| Feed | /meta/feed.json | JSONFeed v1.1 — latest capability announcements |
Trust Model
- Kill switch: active — contact
matt@dreamineering.com - Human-in-the-loop: required above spend threshold + first call from unknown caller
- IntentTrace: v1.1 receipt on every tool call (public endpoint Phase B)
- Governance:
agent.json#governance
Human Marketing Parallel
Agents discover this platform through agent.json and llms.txt.
Humans discover it through the berley trail — content scored for the right fish, published in the right order.
Same platform, two funnels. Agent funnel: discover → evaluate → call → pay → receipt. Human funnel: berley → hook → bait → fishball → platform.