Questions, answered

It is a denoised, entity-resolved market-fact layer for AI agents. It turns the raw stream of financial news and tracked-actor posts into typed, deduplicated facts - one canonical ID per company and coin across both equities and crypto - plus dated canonical events, a knowledge graph and a crypto hype-velocity detector. It is the ETL an agent would otherwise build itself.

AI trading, research and optimization agents, and the developers and quants who provision them. Your agent reasons over clean, structured facts instead of parsing a raw-headline firehose.

We do not compete with them - we are the layer you read before them. Raw-data APIs give you prices and headlines; we give you denoised, entity-resolved facts and events on top, so the raw firehose becomes cheap to reason over. Think of us as the substrate an agent consults first.

No. This is informational market intelligence - convenience and provenance, not investment advice and not a claimed price edge. Every forward call is logged before its horizon and graded honestly (hit-rate, Brier, calibration) at /track. We sell the clean substrate, not a promise.

About 91% of generic headlines are dropped at ingestion - a recent run distilled 28,179 raw items to 2,402 typed facts with zero false positives in review. Only facts that carry a type, a resolved subject and (where present) a magnitude survive.

One canonical identity per company or coin: NVDA, Nvidia, @nvidia and $NVDA all resolve to a single ticker. An agent can deduplicate entities across the whole feed instead of treating four spellings as four things. We favor precision over recall - it returns null rather than a wrong merge.

Structurally important, dated early-warning events the council grades with a p_canonical score - the layer that flags an inflection before consensus. Two verified signature cases (a quantum export-control move and an HBM supply shift) were caught early, dated and traceable. It is provenance of timing, not a return claim.

Fetch the OpenAPI 3.1 spec at /openapi.json (or generate an MCP server from it), then send your key in the X-API-Key header. Start with /api/docs (no key) for the catalog. Errors are honest: 401 unknown key, 403 above your tier, 429 with Retry-After on rate limit. Every request is metered.

Three cumulative tiers: Free (see the full scope in one call), Signal ($19/mo - honest track record, canonical events, dated evidence, typed facts, entity resolution) and Intelligence ($99/mo - the full knowledge graph, fundamentals, world-compass, regime and risk). Every request is metered, so per-query pricing for autonomous agents is on the roadmap.

It is in private beta. Public launch follows our first canonical-maturity milestone - we would rather prove the honest track record than sell a promise. Join the waitlist at /pricing and we email you on launch day.

Every fact is dated and traceable to its authoritative source, canonical IDs are stable, and the forward track record is public and honest (control group and global false-discovery rate disclosed) at /track. Trust for a facts product is verifiable provenance, not accuracy claims.