Platform
Build in a query
what used to take a pipeline.
Agent observability, skill graphs, difficulty maps, personalization — each one is a single query against statements you're already recording. No ETL, no second instrumentation pass, no new infrastructure to run.
Shipped today: the API and the dashboard. Everything below is yours to build on top of them — one query away, not a promised feature.
Agent observability
Every tool call, decision, and outcome as a statement — then ask what an agent did last month, not just last session. Lifetimes, not sessions.
Skill graphs & proficiency
Belief state (FSRS) is computed per actor and concept from real behavior — a provable record of what someone knows, decaying honestly over time.
Difficulty & struggle maps
Per-item difficulty computed from the whole population's traces. Find where users struggle without instrumenting anything twice.
Audit & compliance evidence
The immutable ledger plus full export is the raw material for GDPR / EU AI Act workflows — evidence by architecture.
Personalization & reranking
The rerank endpoint orders candidates by an actor's actual history — recommendation infrastructure without shipping your data to a black box.
Multi-actor analytics
Humans, agents, devices, and systems in one queryable model — cross-actor questions become one query instead of four ETL pipelines.
Already running at consumer scale.
The same substrate you'd build on powers Swapp today — a live consumer feed where hundreds of thousands of real statements drive rankings, difficulty, and personalization, all computed from the ledger. You're not the experiment. Request a key.