Skip to main content

​
What you get

One row per record: include, exclude, or flag for human review — each with the criterion that decided it and a supporting quote. The most labour-intensive step in evidence synthesis, turned into something a human checks rather than performs.
Consensus gives you the primitives for this — filters, pagination, abstracts, and study types. It is not a packaged screening product, so you are building the workflow yourself. Customers ask us for this regularly; treat the recipe below as the current best path.

​
Who it’s for

Anyone running a systematic or scoping review — graduate students, methodologists, evidence synthesis units. Traditionally two people screen every abstract independently, which is where the weeks go.

​
The prompt

​
Calibrate before you scale

1

Have a human screen 100 records first

Screen a random sample by hand, then run the agent over the same 100 and compare. You are measuring agreement, and more importantly reading the disagreements.
2

Fix the rubric, not the model

Almost every disagreement traces to a criterion two humans would also read differently. Rewrite the criterion until it is unambiguous, then re-run.
3

Watch the FLAG rate

A near-zero flag rate means the agent is deciding cases it cannot actually decide from an abstract. Somewhere between 5% and 20% is normal depending on how much your criteria depend on methods detail.
4

Escalate borderline records to full text

For flagged records, re-request with include_full_text_chunks=true using the criterion as the query, and screen the excerpts instead.

​
Narrowing before you screen

Every filter you apply is a record you do not have to screen — but each one also risks dropping an eligible study, so record what each rung costs you.
Use the filter ladder and keep the count at each rung, because a reviewer will ask.

​
Audit requirements

Follow the grounding rules. Screening specifically needs: total records retrieved, records after deduplication, screened, included, excluded by criterion, and flagged. Excluded counts must be reported per criterion — PRISMA requires reasons, not a single total.

​
What to check before you trust it

  • Never let the agent be the only screener on a published review. It is a first pass that a human adjudicates, and journals will ask who screened.
  • Check the excluded pile, not just the included one. False exclusions are invisible in the output and fatal to the review.
  • Re-screen after any criterion change. A mid-run rubric edit makes the earlier verdicts incomparable.

Build a PRISMA-ready search corpus

The step before screening: assembling the records.

Write the search-strategy section of your methods

Turn the log into the paragraph reviewers require.

Best practices

Filter ladder, grounding rules, and the five primitives.

All use cases

Browse the gallery by persona.