Empowering equitable, rational policymaking through living evidence.

The Cambridge Traceable Accountable Pipeline (TAP).

What we're building

Systematic reviews start going out of date the moment they are published. Evidence TAP replaces them with living evidence databases that continuously ingest, screen, appraise and extract the research literature. Every claim stays traceable to its source.

The pipeline runs on local, self-hosted models and adapts to the decision at hand: rapid synthesis for urgent questions, expert verification where the stakes are higher. In our flagship study it reached 97% recall against a large-scale manual review.

It began in Cambridge's Conservation Evidence collaboration and is now expanding into education, with health and climate to follow.

  • Conservation
  • Education
  • more to follow

How the pipeline works →

Latest news

Sam Reynolds speaking to camera in the ai@cam film about the Conservation Evidence Copilot

A short film on the Conservation Evidence Copilot

Sam Reynolds and Lynn Dicks star in a short ai@cam film explaining where the Conservation Evidence Copilot fits into the wider Conservation Evidence project, and how it helps people find and pull together evidence by asking questions in plain language. It comes as the team reflects on how to talk clearly about very different kinds of AI, and on helping people navigate a fast-changing landscape.

linkedin.com →
  1. Mélanie Gréaux at the AI for Good Global Summit in Geneva Evidence TAP at the AI for Good Summit
  2. Sadiq Jaffer, Mélanie Gréaux and Sam Reynolds at Pembroke College Evidence TAP finds a home at Pembroke
  3. Sam Reynolds in the Zoology library during filming for ai@cam Filming the Conservation Copilot for ai@cam
  4. The Conservation Evidence Copilot landing page, inviting a conservation question Conservation Evidence Copilot enters private preview

Next 1 Oct 2026: Harnessing AI for Nature at Stanford

All news →

Papers

  1. AI-assisted Living Evidence Databases for Conservation Science

    Cambridge Open Engage, 2025

    The flagship pipeline: a self-hosted, end-to-end system that ingests, screens, and extracts structured data from the literature. It achieves 97% recall against a large manual review.

  2. Will AI speed up literature reviews or derail them entirely?

    Nature, 2025

    AI-generated “poison” papers threaten evidence synthesis. Traceable AI pipelines can form part of the defence.

  3. Careful design of Large Language Model pipelines enables expert-level retrieval

    PLOS ONE, 2025

    Well-designed hybrid retrieval pipelines reach expert-level performance on conservation evidence questions. Off-the-shelf LLMs fall short.

All papers →

The team

Computer scientists, conservation scientists and education researchers are working together at the University of Cambridge. We share a single living evidence engine and apply it wherever policy needs to know what works.

Computer Science

  • Anil Madhavapeddy Department of Computer Science & Technology
  • Sadiq Jaffer Department of Computer Science & Technology
  • Eleanor Toye Scott Department of Computer Science & Technology
  • Mark Elvers Department of Computer Science & Technology

Conservation

  • Lynn Dicks Department of Zoology
  • William Sutherland Department of Zoology
  • Sam Reynolds Department of Zoology
  • William Morgan Department of Zoology
  • Alec Christie Imperial College London

Education

  • Jenny Gibson Faculty of Education
  • Mélanie Gréaux Faculty of Education

In association with Rob Doubleday, Nicola Buckley and Alexandru Marcoci, across the Centre for Science and Policy and the Centre for the Study of Existential Risk.

With collaborators beyond Cambridge, plus the students, interns and alumni who have shaped the pipeline. Meet the full team →