Evidence maps, in motion

Map what the evidence says

Where research is dense, where it is thin

Examine Evidence is a web app for evidence synthesis: you search or import studies, screen and classify them with rules, AI reviewers and people, and build evidence maps that show where research is dense and where it is thin. Every decision, by a person or by AI, is recorded.

Your key is encrypted at rest and never shown again.

01 Import

Bring it all in

  • PubMed
  • OpenAlex
  • Semantic Scholar
  • RIS · CSV · Excel
  • Zotero · JSON

Any file. Columns mapped for you.
The table appears at once.

02 Screening

Screening: rules and AI read, you decide

Excluded studies sink, never vanish.

03 Classify

Classify it your way

Classes by rules, AI or people.

04 Map

See what is known

Hover a cell. Click to pin it.

Example evidence gap map with synthetic data: number of studies by outcome (rows) and intervention (columns)
ExerciseDietDrugEducationDigitalSurgeryCombined
Mortality1294230 (gap)187
Quality of life38241520110 (gap)29
Pain4653380 (gap)2714
Cost0 (gap)7110 (gap)960 (gap)
Adherence21172634400 (gap)12

People and AI, every call on record

  1. Ana include
  2. AI reviewer include reason saved
  3. AI reviewer exclude reason saved
  4. Ana overrides: include reason saved
  5. AI call failed Needs review
  6. Ana decides flagged, not guessed

06 Validate

Test the AI on your own calls

  1. 1 Take a sample
  2. 2 Mark it yourself
  3. 3 See where AI disagrees
  4. 4 Adjust, then run

Example agreement matrix with synthetic values: of 100 sampled studies, the AI and you both include 42 and both exclude 45; you include and the AI excludes 8; you exclude and the AI includes 5. Agreement 87 percent, kappa 0.74. These numbers are an example, not a result.

Nothing hidden

  • Every AI decision, visible

  • Failures are flagged, never silent

  • Every decision on record

  • Your data stays yours

How data and AI are handled

Pick your pace

Quick

free to start

Drop a file. Get a map.

Agentic

Beta

An agent works. Every step saved.

Prepare evidence maps for free in minutes

Make a map

Low cost by design

No per-seat AI subscription. Pay for what the AI actually uses, or bring your own key and pay the provider directly.

  • Per-seat AI subscriptionNone
  • Free accountSmall monthly AI budget
  • Your own API keyProvider price, no markup

See one up close

Mood × Strength

44 studies · synthetic
  1. Study 1Title placeholderRCT
  2. Study 2Title placeholderRCT
  3. Study 3Title placeholderCohort
  4. Study 4Title placeholderRCT
  5. Study 5Title placeholderReview

Example map, synthetic data. No real studies.

Open the example map

Know what the evidence says

About

What is Examine Evidence?

Examine Evidence is a web app for evidence synthesis: you search or import studies, screen and classify them with rules, AI reviewers and people, and build evidence maps that show where research is dense and where it is thin. Every decision, by a person or by AI, is recorded.

About Examine Evidence

Questions and answers

What is an evidence map?

An evidence map, also called an evidence gap map, is a table that counts the studies on a topic by two classifications, for example outcomes in rows and interventions in columns. Dense cells show where much research exists. Empty cells show possible gaps. A map shows where the evidence is; it does not say what the studies found.

Who is Examine Evidence for?

People and teams who need to make sense of a body of literature, for example to build an evidence gap map or a scoping review. Quick is for one person who wants a map fast. Studio is a full workspace for teams that search, screen and classify together.

Is Examine Evidence free?

Quick is free to start. Sign in with your email address, make a map and share it. A free account includes a small monthly AI budget. Studio is priced on request, and Agentic is in beta.

How does AI screening work, and how is it validated?

You define the question and the criteria. Rules and AI reviewers read each study and propose include or exclude, with a reason that is saved. To validate, take a sample, mark it yourself, see where the AI disagrees with you, adjust the instructions, then run it on the full set.

Does AI make decisions without me?

In Quick and Studio, no. AI proposes and people decide, and you can override any AI answer. Excluded studies are kept, not deleted. If an AI call fails, the study is flagged as needing review instead of being guessed. Agentic mode, in beta, lets an agent work for you, and every step it takes is saved so you can check it.

Which file formats can I import?

RIS, CSV, Excel, BibTeX and JSON files, and Zotero exports. Columns are mapped for you, and the table appears at once. You can also search PubMed, OpenAlex and Semantic Scholar from inside the app.

Where is my data stored?

On a server we run with Hetzner, a hosting company, and backed up to separate storage. The server is in Nuremberg, Germany, behind Cloudflare; see the privacy notice.

Can I use my own AI key?

Yes. Add your own provider key and Studio opens straight away; you pay the provider directly, with no markup, and the small monthly AI budget of the built-in agents stays. Your key is encrypted at rest and never shown again.