Hire an AI research comparison report writer

Everything it can hand back

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

• An outline with the items to compare and the fields to answer for each
• One research file per item, with unsure answers marked
• One report with a contents list and a section per item
• Gaps shown as gaps, since unsure answers are left out

How it does the job well

• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

Mistakes it avoids

• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.
• Over-generalising across places, periods or groups.

What a good result looks like

An example, not your task: You must compare ten or more tools, vendors or competitors.

• Research outline. The list of items to compare and the questions to answer for each one.
• Item files. One file per item, with answers, their sources and any unsure answers marked.
• Report. One document with a contents list and a section per item, with unsure answers left out.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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

• Build the research outline. Builds a first list of items and the questions to answer for each, searches the web for items and fields that are missing and asks you to confirm.
• Research each item. Works through the outline in batches, skipping items already done, saving a file per item and marking answers it could not confirm. You approve each batch.
• Build the report. Reads every item file, lets you choose the numbers for the contents list, then builds one report with a section per item and leaves out unsure answers.

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 compare-a-list-of-options-and-get-one-checked-report 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/compare-a-list-of-options-and-get-one-checked-report/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 topic, such as "AI note-taking apps for small teams"
• The time range that matters, such as since 2024
• Any items you already know must be included (optional)
• The fields you care about most, such as price, users or limits (optional)

Functions and deliverables

• Research comparison report writer: Set the items and questions to research. Check each option and combine supported answers into one report, with gaps left clear.
  • An outline with the items to compare and the fields to answer for each
  • One research file per item, with unsure answers marked
  • One report with a contents list and a section per item
  • Gaps shown as gaps, since unsure answers are left out
• Research outline builder: Turn a research topic into items to compare, fields to study, and saved outline files.
  • List of items to research
  • Questions to answer for each item
  • Web-sourced additions
  • Outline file for later steps
  Source: Weizhena.
• Item-by-item researcher: Give it a research outline. Get a checked file per item, with answers or uncertainty noted.
  • One result file per item
  • Fields filled or marked unsure
  • A record of finished items for resuming
  • Batch-by-batch progress
  Source: Weizhena.
• Research results report builder: Build one research report from many result files, with a contents list and only checked answers. Uncertain values are left out.
  • Single Markdown report
  • Contents list with chosen fields
  • Every field covered per item
  • Uncertain values left out
  Source: Weizhena.
• 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 must compare ten or more tools, vendors or competitors.
• You need a market or literature map with the same questions asked of each item.
• You want a report where every answer has a source and gaps are visible.

Limits to check before starting

• You only have about three items to compare: search each one yourself, it is faster.
• You need a decision memo or a final pick: run this first, then give the report to the Narrative decision memo writer as its evidence.
• You need one deep answer on a single company or paper: ask your AI one focused question and check the source yourself.

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 handoff pack from this page. It is a zip with HANDOFF.md and the three skill files this workflow uses. Unzip it and keep them together in one folder.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md". It needs a setup that can search the web and save files.
• Give the topic and time range. Trim the list of items and fields when it asks.
• Approve the first small batch before it does the rest.
• Choose which numbers show in the contents list of the report.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/compare-a-list-of-options-and-get-one-checked-report 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.