Skip to main content

​
What you get

Your agents stop reasoning over a stale slice of abstracts and start reasoning over full-text findings, with quality filters and a link back to every source. And nobody on your team maintains a corpus pipeline any more.

​
Who it’s for

Engineers who own “the literature service” at an AI-for-science company — the one who inherited a scraped or licensed PubMed subset and now owns its refresh, its gaps, and its quality problems.

​
What it replaced at Owkin

Owkin builds AI tools for biopharma drug discovery. Its flagship product, K Pro, is an Agentic AI Scientist orchestrating specialized agents across clinical trial design, patient and population decisions, and early portfolio choices. Early versions of K Pro ran on a curated collection of PubMed abstracts. Serviceable, but it left agents reasoning from titles and summaries rather than full-text findings, with limited filtering for study quality and no built-in defense against hallucination.
“We went from maintaining a collection of PubMed abstracts to 200M+ full-text articles updated weekly, with hallucination safeguards built in. It’s exactly the kind of best-in-class building block we want to compose with, rather than rebuild.” — Lucas Brechot, Senior Product Manager, AI Products, Owkin

​
Why abstracts are the wrong foundation

1

The findings are not in the abstract

Effect sizes, conditions, populations, and limitations live in the body of a paper. An agent restricted to abstracts produces answers that are confident and shallow — the worst combination in a high-stakes domain.
2

A self-maintained corpus decays

Someone has to keep it fresh, handle schema drift, and explain the gaps. That work is invisible until it breaks, and it is never the thing your product is differentiated on.
3

Quality filtering has to be programmatic

Human researchers instinctively weigh recency, citation count, and journal reputation. Agents need those as parameters — year_min, citation_min, sjr_max — or they treat a 1998 case report and a 2025 meta-analysis as equivalent.
4

Grounding needs a link, not a claim

Every result carries a doi and a url back to the paper. That is what turns “the model says” into “this paper says”, which is the difference that matters to your users.

​
Making the swap

Point your retrieval layer at the MCP server or GET /v1/search, and map your existing corpus filters onto the parameters that replace them:
include_full_text_chunks requires a paid plan or an Enterprise API key and currently covers open-access papers. Pagination has the same plan gating — see rate limits.

​
What to check before you trust it

  • Run your old corpus and the new one side by side on the same queries before cutting over. You are looking for regressions on your niche, not average quality.
  • Check the filters actually narrow the way your old pipeline did. A corpus restriction you enforced at ingest becomes a per-request parameter, and it is easy to forget one.
  • Confirm coverage on your specific subfield. Full-text excerpts currently cover open-access papers, so a closed-access niche will look thinner than it is.
  • Keep the DOI. If your product cites papers, the doi and url are what make the citation checkable downstream.

Add a citable evidence layer to an agent you already ship

The same integration, framed as an addition rather than a replacement.

Benchmark literature providers against your own ground truth

How to decide whether the swap is actually an upgrade.

Best practices

Rate limits, grounding rules, and the five primitives.

All use cases

Browse the gallery by persona.