Run a recorded search, screen records against the stated criteria and extract outcomes into an evidence table — each line bound to the source and page behind it, for a named reviewer to sign.
Take the review question, the inclusion criteria and the sources in scope from the protocol.
02
Run the agreed search across the sources in scope for this build, and record it as run.
Reason
03
Screen records against the criteria as written, keeping the reason each decision turns on.
04
Extract design, population, comparator, outcome and result into the evidence table.
05
Mark preprints and translated text, and pull retraction and correction status with the record.
Decide
06
Hold any line whose source check fails — no page, no matching text, or a status that moved.
07
Route safety-relevant reports and out-of-scope questions to the team that owns them.
Out
08
Present the evidence table, the search record and the screening log for a reviewer to work from.
09
Retain the strategy, the records seen, every decision reason and each reviewer correction.
→Product statement
The agent searches, screens, extracts and cites inside the approval boundaries agreed during implementation; a named reviewer draws the conclusion.
Example workflow
One evidence pack, end to end
AgentHuman
1Question and criteria receivedReview question, inclusion criteria, sources in scope and the period the search covers
2Search run and recordedThe databases, registries and preprint servers in scope, with the strategy, filters and counts kept as run
3Records screenedEach record judged against the criteria as written, with the reason for the decision kept
4Data extracted and checkedCharacteristics and outcomes into the table, each line checked back to its source and page
No human action required
Stages 1 to 4 run without a person in the loop — the reviewer is not asked to read anything until the source checks have run. A safety-relevant report leaves for the safety team the moment it is seen.
5DecisionSplits on the source check and the confidence gate
Sources check out
Goes to the reviewer as a drafted pack.
Check fails or evidence is thin
Held with the failing lines marked.
Scientist or information specialist
Reads the pack against the search record, the flagged lines and what could not be sourced.
Sign off · Amend · Return to search
Signed off — handed back▼
6Pack assembled and filedWritten to the review file only where access and policy allow; the conclusion field stays empty
7Outcome evaluatedSource-check failures, screening disagreement, reviewer corrections and what went back to search
Corrections
Lines the reviewer rewrites or removes are counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Concluding that the evidence supports a use.
Any comparative, off-label or promotional statement.
Signing off a review, summary or evidence pack.
Grading certainty of evidence or risk of bias.
Automation boundaryAgent acts unaided
✓Run the agreed strategy and record it as executed.
✓Screen records against the criteria as written.
✓Extract characteristics and outcomes with the source and page.
✓Hold failing lines, mark preprints and route safety reports out.
Write actions run only inside the approval boundaries agreed during implementation. The conclusion is not one of them.
Deciding a retraction or concern can be ignored.
Screening the literature for safety reporting.
Releasing a pack outside the organisation.
Changing the criteria, strategy or source list.
Example output
One extracted line, annotated
Everything the agent puts in the table is attached to the record and the page it came from.
Evidence table · single extracted studyIllustrative example
Record
Retrieved from
Located at
Extracted
Confidence
Record status
Randomised trial report
Indexed database, full text
p. 6, table 2
Primary outcome, as reported
89%
Checked at the search date
As receivedThe record as the database returned it, beside the strategy that found it — nothing on this side is inferred.
Evidence usedFull text, not the abstractRetraction status pulledPage and table located
Why the status carries a dateRetraction notices reach the databases late, so the status carries the date it was checked.
ActionSign offAmendReturn to search
What the score decidesBelow the configured threshold the line is held for the reviewer instead of entering the table.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every record retrievedFrom the sources in scope
03Search & screening
Apply the protocol as written
Use the stated criteria, the agreed source list and the review's own extraction form.
01Approved path
Make the first pass checkable
Screening decisions and extracted lines arrive with their reason and their source, so a reviewer starts from something they can check rather than from the raw record set.
02Human review
Put reviewers on the flagged lines
Failed source checks, moved statuses and split judgements reach a named reviewer instead of the whole record set doing so.
04Build an evidence trail
Retain the strategy as run, the records seen, each screening reason, the extracted line with its source and page, the confidence and the reviewer's correction — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Bibliographic databasesPubMed / MEDLINE · Embase · Web of Science Scopus · Cochrane Library
Registries & preprintsTrial registries · preprint servers WHO ICTRP · EU CTIS
Full text & statusPublisher full text · library holdings Crossref · Retraction Watch data
Agent
Research-literature copilot
Runs the search Screens and extracts Routes to review
Four cohorts, one pack. The failure rate counts lines whose source check failed or whose extracted value a reviewer had to change, because a scanned or translated report behaves nothing like a well-indexed trial.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Scanned pre-2000 full text
4.7%
3.0×
Review
Non-English source articles
3.4%
2.2×
Review
Preprints and conference abstracts
2.7%
1.7×
Watch
Well-indexed randomised trials
1.2%
0.8×
Normal
Bar: source-check failure lift vs. indexed-trial baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A failed check does not close with the pack it came from
A line the reviewer had to correct changes the strategy, the extraction form or the status check that let it through — and the next pack is measured against that.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Source-check or extraction failures rise in a record cohort.
02Diagnose
The search record is what makes this reproducible; that is what it is for.
03Improve
The strategy, form or status rule is changed under version control.
04Verify
Affected records are searched, screened and extracted again.
05Learn
The failed line stays as a test case and the form carries the correction.
Learn → DetectThe return edge. A change to the criteria or the strategy is a protocol change — agreed and recorded before the next search runs, not after.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, search and screening, extraction and status checks, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and claim-boundary definition.
02Source, database and licence assessment.
03Review question, criteria and protocol scoping.
04Search strategy build and strategy recording.
05Screening logic and decision-reason capture.
06Extraction form and source-and-page binding.
07Retraction, correction and preprint status checks.
08Reviewer sign-off workflow.
09Claim-scope guardrails and safety routing.
10Evaluation suite and regression records.
11Review-platform and document integration.
12Observability, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne review questionProductionProduction integrationAdvancedSeveral programmes / sources
Introduced at Pilot
Recorded search strategy✓✓✓
Screening against stated criteria✓✓✓
Extraction with source and page✓✓✓
Retraction and preprint status checks✓✓✓
Claim-scope guardrails and safety routing✓✓✓
Reviewer sign-off✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Review-platform and document integration—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Several databases and licensed sources——✓
Multi-programme and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the databases and licences in scope, review types, question volume, review controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01The review question, criteria and protocol→Review question, criteria and protocol scopingWeek 1
02Where your claim boundary sits and who signs→Claim-boundary definition and sign-off rulesWeek 1
03Access to the databases and licences you hold→Source, database and licence assessmentWeek 2
04A search your information specialist has already run→Search strategy build and strategy recordingWeek 2
05Your extraction form and how outcomes are recorded→Extraction form and source-and-page bindingWeek 3
06Packs that went wrong — a bad citation, a retracted paper→Evaluation suite, regression records and failure-mode testingWeek 4
07Named scientists, reviewers or information specialists→Reviewer sign-off workflow, then pilot packs and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 carries both the cohort slices and the first packs a reviewer reads.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Review question, criteria and the claim boundary agreedW2Databases, licences and the search strategy recorded as runW3Screening reasons, extraction form and source-and-page bindingW4Source-check testing, status checks and cohort slicesW5Review-platform integration, first reviewed packs and correctionsW6Production validation, sign-off on live questions and Agent Care handover
Reading the bandBars cover only the weeks their work is named in. Week 2 builds the search record; a strategy nobody can rerun later is where a review quietly comes apart.
At the end of W6Your reviewers sign, and nothing the agent produced leaves unsigned. Agent Care then watches the corpus and the status checks.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Biotechnology AI agent
Build a literature copilot around the review you already run.
Show us a review question, the sources you licence and the pack a reviewer signs today. If your reviewers cannot reproduce a search from its own record, extraction is the wrong place to start, and we will say so in the first week.
