What we're building

Conventional systematic reviews are slow and costly, and they start going out of date the moment they are published. Yet policymakers often need current, context-specific evidence within narrow windows. Evidence TAP replaces one-off reviews with living evidence databases that keep updating as new research appears.

At its core is a traceable AI pipeline. It ingests the literature across many sources and languages, screens it for relevance, appraises study design, and extracts structured data. Every output remains traceable to its original source. The pipeline runs on local, self-hosted models, pairing keyword and semantic retrieval with a statistically principled stopping rule.

TRACEABLE ACCOUNTABLE PIPELINEINGESTeverything published, in any language or formatSCREENsifted for relevance to the questionAPPRAISEquality grading of study strengthEXTRACTstructured dataLIVING EVIDENCE DATABASEalways current, every entry traceable to its sourceSYNTHESISEa living review, per questionPOLICYMAKERS"what works forpeatland restoration?"PRACTITIONERS"how do I help pollinatorson my farm?"EDUCATORS"does tutoring closeattainment gaps?"RESEARCHERS"where is theevidence thin?"

97% recall against a large-scale manual review, in our flagship study.

The pipeline adapts to the decision at hand. For urgent questions it can synthesise all of the available evidence rapidly with minimal human checking, flagging gaps for follow-up; where the stakes are higher, experts verify each stage. Every verification is retained and feeds back into the models, so the system keeps improving. The trade-off between speed and accuracy is transparent and quantifiable.

It began in conservation, through Cambridge's Conservation Evidence collaboration, and is now being applied to education. Health, climate and other fields will follow. The longer-term aim is a global mesh of self-hosted nodes that shares evidence equitably across and within countries.

  • Conservation
  • Education
  • more to follow

How it started

Evidence TAP grew out of the Conservation Evidence Copilots project and has broadened, discipline by discipline, into a general living evidence pipeline.

  1. 2022

    Undergraduate beginnings

    Initial group projects at Cambridge explore whether AI can help screen the vast conservation literature, made possible by the decades-long corpus of evidence assembled in the Conservation Evidence database.

  2. 2023

    Conservation Evidence Copilots

    The project formally begins, supported by the ai@cam initiative as “AI-Driven Conservation CoPilot: Revolutionising Biodiversity Solutions”, working with the Conservation Evidence database of 1.6 million screened papers and 8,600 summarised studies.

  3. 2024

    First LLM evaluations

    Early preprints show that carefully designed pipelines can reach expert-level retrieval, while off-the-shelf LLMs fall short. The project is selected as an ai@cam flagship challenge.

  4. 2025

    The living evidence pipeline

    A working paper sets out a self-hosted, end-to-end pipeline, which in an initial evaluation reached 97% recall against a large-scale manual review.

  5. 2026

    Evidence TAP

    The project broadens beyond conservation into education, with health and climate to follow, and becomes Evidence TAP.