Hire an AI research evidence reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A summary sorted into well established, contested and single-study findings
• A source table with each source's type, quality and how much weight it gets
• A list of claims that only repeat one original source
• The gaps, meaning what was searched for and not found
• A confidence level with the reason for it

How it does the job well

• Only describe a source you were given or opened. If you know of a study that was not supplied, you may suggest it as "worth checking", never as evidence you reviewed.
• Point to the page, section or line a claim comes from when you can. If you only have an abstract or a link, say so.
• Count a claim once, however many sources repeat it. Name the original source if it can be found in the material. If not, write "origin not found".
• Do not pick the majority or the most convenient side. When sources disagree, show both and how strong each is.
• State what was not found. A gap is a finding, not an empty section.
• Trace claims to their primary source before repeating them. A statistic cited in ten places is still one data point if all ten trace back to the same original study.
• Grade every source's evidentiary weight explicitly. A peer-reviewed RCT and an opinion blog post are not equal evidence, even if they agree.

Mistakes it avoids

• Treating the number of sources as the strength of the evidence.
• Smoothing over disagreement to give one answer.
• Treating a newer source as better only because it is newer.
• Copying the profile's example rows as if they were the user's sources.
• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.

What a good result looks like

An example, not your task: You have a folder of papers, reports or articles on a topic and need one summary you can trust.

• Question and search limits. Your question in a searchable form, what was searched, the date range and what was left out.
• Source table. Each source with its type, quality, whether it stands alone and the weight it gets.
• Evidence summary. Findings sorted into well established, contested and single-study, with the sources for each.
• Repeated claims. Claims that many places repeat but that trace to one original source.
• Gaps. What was searched for and not found, so silence is not read as an answer.
• Confidence. A low, moderate or high rating with the reason, tied to the weakest key source.

How the work is checked

• Every important claim has a source or is marked as unverified.
• Disagreements between sources are named, not hidden.
• Limits and what to check next are listed.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Frame the question. It turns your question into a searchable one and says what would count as enough proof.
• Set the search limits. It records what was searched, the date range and what was left out, so you can see the coverage.
• Grade each source. Each source gets a type, a quality note and a weight. Opinion posts and copies of other sources get little or none.
• Trace repeated claims. It follows repeated numbers and claims back to their origin and counts them once.
• Sort the findings. It groups findings by theme into well established, contested and single-study, with both sides when sources disagree.
• State the gaps and confidence. It lists what was not found and sets confidence by the weakest key source, not the most quotable one.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id research-synthesist only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/research-synthesist/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The question you want the research to answer, in one or two sentences
• The sources you have, pasted or attached, such as papers, reports, articles or links
• How wide to look, such as the years and the places to cover (optional)
• What would be enough proof for you to act (optional)

Helpful context (optional)

• The full text of each paper, not only the abstract.
• A line on who will use the summary and what they will decide.

Tools and access

• Claude, ChatGPT or Gemini with file upload: It can read a stack of papers at once and quote the page a claim comes from. Web search lets it add sources.

Functions and deliverables

• Research evidence reviewer: Turn a pile of articles, papers or reports into one honest summary. See what is well backed, what is disputed and what is missing.
  • A summary sorted into well established, contested and single-study findings
  • A source table with each source's type, quality and how much weight it gets
  • A list of claims that only repeat one original source
  • The gaps, meaning what was searched for and not found
  • A confidence level with the reason for it
  Source: Michael Sitarzewski and Agency Agents contributors.
• Research paper evidence reviewer: Check how far to trust a research paper. Give it the paper and get a claims review with weak spots, limits and what would settle the question.
  • A verdict on how far to trust the main claim
  • A table of claims with their evidence and a rating
  • Problems ranked from major to minor, each tied to a part of the paper
  • A note on what is missing for someone to repeat the work
  • A test that would settle the question
  • Later work on the paper, marked as searched or from memory
  Source: Jacquard Labs.
• Paper claim evidence finder: With BGPT connected, search a topic or DOI. Get extracted paper claims, source notes and evidence gaps to verify.
  • An evidence table with these columns: claim, result, sample size, limits, DOI and source section.
  • One sample row reads: the claim in one line, the main number, how many took part, the author's stated limit, the DOI, and the table or figure.
  • A flag on any record that has no claim-level evidence.
  • Details of the experiment behind each claim.
  Source: K-Dense.
• Research paper summarizer: Give it a paper, article or report. Get the key findings, plain summaries and a comparison across sources.
  • The key findings of each source, with where each one appears
  • A plain summary of the method and its limits
  • A rough quality rating for each source, judged only from the text you gave it
  • A side-by-side comparison of two or more sources
  • Citations in the style you ask for, APA 7 if you do not say
  Source: Alireza Rezvani.
• Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
  • A research folder with claims, methods and results
  • Every claim linked to its supporting table or log
  • Results tables copied with exact numbers
  • A record of dead ends and decisions
  • A short report on what was filled in and what was missing
  Source: Orchestra Research.

Tasks you can use it for

• You have a folder of papers, reports or articles on a topic and need one summary you can trust.
• Everyone repeats the same statistic and you want to know where it first came from.
• You must tell your team or a client what the research says, including where the experts disagree.
• You are starting a new project and want to know what is already known before you spend money on your own study.

Limits to check before starting

• You want to know whether a trend is rising and worth acting on. Use the Trend Researcher agent.
• You want a health or outcome claim in your own document checked. Use the Clinical evidence reviewer.
• You want to compare software or tools you could buy. Use the Software tool comparison planner.
• You need a single fact checked right now. Open the original source, or ask your AI to search for it.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.
• State your question. Say who or what it covers, what you compare, and which result matters.
• Paste or attach your sources. If your AI can search the web, say whether you want it to add sources or stay within your pile.
• Type "Make the evidence summary. Trace repeated claims to their origin. Say what you did not find."
• Read the source table first. Check that the sources it marked strong are the ones you would trust.
• Open the original source for any claim you plan to quote.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/research-synthesist for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.