Skip to main content

​
When to use the Data Graph

The Data Graph is Tako’s index of what its curated data actually covers — every entity (companies, countries, teams, commodities…) and metric (revenue, CPI, win percentage…) as a node, connected by real relationships. Query it before Search so your agent composes queries that hit, pins the exact nodes it resolved, and honestly reports what’s missing. Reach for it when:

You want to know what Tako has before you search

Resolve a name (“Nvidia”, “inflation”) to real graph nodes and read what data exists for them — instead of spending searches on guesses.

You want deterministic grounding

Pin resolved node ids into Search via sources.data.node_ids for guaranteed retrieval candidacy — or add strict: true to return only cards matching your nodes.

You want real relationships, not model memory

Competitors, subsidiaries, industry peers, cohort members — read them off named graph edges like rel:competes_with and members. A database read replaces the LLM-recalled lists that produce hallucinated comparisons.

You want honest gaps

When the graph can’t ground part of a question, your agent can say so — “Tako has X and Y, but not Z.” An empty result is an honest answer, not a failure.
No general-purpose AI-search API — Exa, Perplexity, Tavily, Brave — exposes a typed knowledge-graph traversal your agent can query before it searches. The closest analogues are the symbol-search endpoints of financial data APIs; the Data Graph extends that pattern to Tako’s whole curated index, with relationships.

​
The three endpoints

​
Free to call, easy to explore

No credits consumed

Graph calls use the same X-API-Key header as every Tako endpoint and consume no credits — they’re bounded only by rate limits (180/minute, 10,000/day). Discovery is free; spend your credits on the searches it grounds.

Explore the graph at tako.com/data

Browse the Data Graph visually with your Tako account — search any entity or metric, walk its relationships, and see exactly what your agent will see before you write a line of code.
The Data Graph is in beta, and it’s a guide — not a guarantee. A node’s related metrics come from the datasets that cover that entity, so a listed metric is strong evidence, not proof of that exact combination. And the graph is not the whole index: stock prices, market quotes, rankings, and overviews often live outside it, yet Search has them. Confirm coverage with a search; treat a thin graph result for a well-covered entity as a cue to search anyway, not to declare a gap.

​
Example — discover, then search grounded

1

Resolve the entity

Returns nodes with id, name, aliases, subtype — pick the company node and keep its id.
2

See what data exists for it

Metrics matching “revenue”, ranked by popularity and match strength — the combinations Tako actually covers.
3

Search, pinned to what you resolved

Pinned nodes get guaranteed retrieval candidacy plus a strong boost; organic results are unaffected.

​
Next steps

  • For your coding agent → — the complete build reference: every parameter, label boosts, relation kinds, response shapes, and the common mistakes.
  • Building an agentic app? Install the tako-graph-agent skill (card at the top of this page) — it packages the whole discover → ground → report-gaps loop for your coding agent.