Skip to main content

​
What you get

An agent that already does something valuable, now grounded: every claim it makes traces to a real paper, and “the literature does not answer this” becomes an answer it can give. The integration is a tool registration, not a re-architecture. Owkin shipped theirs to users in days.

​
Who it’s for

Product engineers whose agent works but overclaims — it reasons well and cites nothing, and your users have started noticing.

​
How it went at Owkin

Owkin exposed Consensus to K Pro’s orchestrator the same way it exposes its other tools. That architectural fit is the whole story: no new retrieval service, no corpus to maintain, no bespoke ranking layer.
“The Consensus MCP slotted directly into our agentic stack and gave K Pro’s capabilities a dramatic upgrade overnight.” — Lucas Brechot, Senior Product Manager, AI Products, Owkin
Agents now ground their reasoning in full-text literature with programmatic controls for recency, citation count, and journal reputation — the filters a human researcher applies instinctively when judging whether a paper is relevant and credible.

​
Wiring it in

Choose by auth model rather than by preference: MCP when each user should search under their own account and limits, REST when the integration needs one shared quota and programmatic pagination.

​
What separates a grounded agent from a decorated one

1

Decompose before retrieving

One search per user question is the most common cause of thin answers. Split the question into subquestions and give each its own search with its own filters.
2

Retrieve excerpts, not just abstracts

Request include_full_text_chunks=true so the generation step reasons over results paragraphs rather than the introduction.
3

Enforce grounding at generation time

Require a doi or url on every claim and drop unsupported sentences. Make “the literature does not answer this” a first-class output rather than a failure state.
4

Surface the filters you applied

Show the study types, years, and quality thresholds used. A researcher cannot trust a result set whose inclusion criteria are hidden.
5

Cache on the full parameter set

Cache on every parameter, not the query string alone, with a short TTL so new literature still lands.

​
What to check before you trust it

  • Check the unanswerable case. Ask your agent something the literature genuinely does not settle. If it produces a confident cited answer anyway, your grounding rule is decorative.
  • Spot-check citations against claims. A real paper attached to a claim it never made is the failure that survives review.
  • Watch your rate limit under real traffic. Per-user OAuth spreads load across accounts; a shared service key concentrates it. See rate limits.
  • Do not hide the filters. If your product narrows to Q1 journals by default, say so in the UI.

Swap a hand-maintained paper corpus for full-text search

When you already have a corpus and want it gone.

Answer one question with many parallel searches

The retrieval pattern that makes a grounded agent good rather than merely cited.

Best practices

Rate limits, grounding rules, and the five primitives.

All use cases

Browse the gallery by persona.