Reference

All tools

70 tools across the full vision. 44 live in code today, 5 structurally registered as Phase 0 stubs (engine wiring deferred), 12 ship July 20, 2026 (action approval + trigger dispatch), and 8 ship in V1.1 (cross-app routing — lights up once users adopt multiple AI products on the substrate).

Memory(4 tools)

Read and write episodic memory. Search across episodes, conversations, knowledge-graph entities, and rules with one query.

Rules(4 tools)

Manage the user's behavioral rulebook. Rules have a lifecycle (candidate, active, suspended, retired) and full provenance.

Trust(2 tools)

Inspect and graduate per-(action class × counterparty) autonomy levels. Trust is earned, never assumed.

Action(10 tools)

Drive the action engine. Send-class operations route through approval; safe operations execute immediately.

Briefing(1 tool)

On-demand briefings synthesized from memory, calendar, and rule state.

Entity(2 tools)

Resolve canonical entities (people by default; pluggable types per ADR-0018) and walk their relationships.

Handler(6 tools)

Register, list, update, and rotate secrets for the customer-owned HTTPS handlers that receive Cortex-dispatched triggers. Per ADR-0019.

Trigger(3 tools)

Inspect dispatched triggers, view delivery history, and replay from the dead-letter queue. The outbound complement to action.* (pull-mode).

Routing(6 tools)

Choose which registered handler receives a trigger when a user has multiple AI products built on Cortex. The cross-app routing layer (V1.1).

Meta(3 tools)

Explainability surface — render "why did Cortex suggest this?" with substrate-grounded provenance. Promoted to public per ADR-0021.

Decision(2 tools)

Generalized decision inspection across triage, action_proposed, rule_fired, trust_transition. Per ADR-0021 §read-API.

Counterparty(5 tools)

Per-counterparty trust graph as a callable read surface — profile, list, activity, classify, trust posture. The moat API.

Commitments(5 tools)

Tracked promises with a lifecycle state machine. Auto-extracted from messages and meetings via consolidation; explicit writes route through the action engine.

Action Classes(3 tools)

Customer-extensible action classes per ADR-0022. Register {client_namespace}.{action_class} for your vertical without internal enum migrations.

Subscriptions(5 tools)

Inbound interest declaration — subscriptions, watchlists, alerts. Evaluator polled at 5-min cadence MVP; event-hooked V1.1+.

Feedback(1 tool)

Modification learning channel. feedback.signal + trigger.complete executed_modified outcome (ADR-0019 amendment) feed the per-counterparty learning hook.

Patterns(1 tool)

Read the rule-candidate / pattern-detector surface produced by consolidation Phase 2.

Insights(1 tool)

Narrative summarization on demand. V1.1+ — stub-ships at MVP.

Identity(2 tools)

Principal's identity model surface (roles, values, goals, constraints). identity.about_me live MVP; preferences V1.1+.

Availability(1 tool)

Principal's current availability state (focus / shielding / meeting). V1.1+ — stub-ships at MVP.

Agent(3 tools)

Self-describing surface — agent.version, agent.capabilities, agent.feature_flags. The runtime truth that pitch docs must match.