Prepare an evidence table of published findings on a named drug target

An evidence table of published findings, reviewed by a qualified person, with no dosing or treatment claims.

Choose one of three approaches. The steps for that option appear below.

Choose an option above. On a phone, swipe the tabs left or right to see all options →

Consensus: candidates, you fill the table

Consensus lists candidate papers. You open each one and fill the evidence table yourself from what it says.

  1. You

    Prepare the question

  2. Consensus

    Collect candidate papers

  3. You

    Fill the table

  4. You

    Qualified review

  1. Prepare the search question

    Use: You

    Have ready: the public target name, one question about published findings, and written exclusions: no dosing, no treatment advice, no claims that a drug works.

    Check

    Check the question asks only for published findings and excludes dosing and treatment claims.

  2. Collect candidate papers

    Use: Consensus

    Ask Consensus for candidate papers with citation, study type, model system, key finding and method.

    Details

    What to paste into the tool

    Task: A list of peer-reviewed papers on published findings about [target] in [area]. For each paper give citation, study type, model system (cells, animals or humans), key finding and method. Do not give dosing, treatment advice, or any claim that a drug works or is safe.

  3. Open papers, fill the table

    Use: You

    Open every paper you will use; fill one row each: citation with link, study type, model system, finding as stated, stated limit or 'not stated'.

    Check

    Check every row comes from a paper you opened; drop any paper you cannot open; no dosing or treatment claim appears.

  4. Get a qualified review

    Use: You

    Ask a qualified person such as a pharmacologist to read the table and cited papers and mark any misstated finding; fix or remove those rows.

    Check

    The qualified reviewer confirms each row matches its paper and nothing reads as a treatment claim.

Before you paste into any AI tool, remove any confidential information. Put it back at the end.

Tools in this workflow

Final check

Never paste credentials or full payment details.

Every row is checked against a paper you opened.

A qualified person reviews the finished table.

No dosing, treatment claim or recommendation is kept.

Nothing is submitted, published or decided by an assistant.

Do not treat the assistant reply as approval.

Check the result against your original inputs. Approve it before sharing or acting.

What still needs checking
  • Whether Consensus or Elicit find all relevant papers is not yet checked.
  • Consensus and Elicit plan limits and country/platform availability are not listed on the pages we checked.
  • Whether the user may paste the text of a given paper into the selected assistant depends on that paper's licence and was not checked.
  • Quality of the papers as evidence is not assessed by this workflow. The qualified reviewer decides.
  • The primary option is a judgement for a general user.

Share this page