Hire an AI investment argument and contrary-evidence review

Everything it can hand back

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

• A claim ledger: each claim, the evidence it needs, its source and date, and whether the filings support, contradict or say nothing
• The evidence that cuts against the thesis, with where to find it
• Open research questions for each claim with no proof
• A committee discussion outline: the thesis, the counter-case and the unanswered questions
• A list of facts it could not check

How it does the job well

• Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
• Show the calculation, inputs and period for every figure.
• Label actuals, estimates and forecasts clearly.
• Send tax, legal and regulatory questions to a qualified professional.

Mistakes it avoids

• Inventing facts, metrics, dates, permissions, quotes or completed actions.
• Applying a prior step's output without checking its meaning and source.
• Re-running successful steps with unchanged inputs or hiding a failed check.
• Treating these portable instructions as a connected service or an installed schedule.
• Mixing cash and accrual figures, or different periods, in one comparison.
• Rounding or formula errors that do not tie back to totals.

What a good result looks like

An example, not your task: You wrote a thesis and want to know which claims no filing backs up.

• CLAIM LEDGER. Each claim, the proof it needs, the source and date, and whether the filings support, contradict or say nothing.
• COUNTER-CASE. The evidence that cuts against each claim, and where to find it in the filings.
• OPEN QUESTIONS. One question and a place to look for each claim that has no proof.
• COMMITTEE OUTLINE. A discussion outline with the thesis, the counter-case and the unanswered questions, and no target price.
• MISSING and CHECKS MISSED. Each gap, what it stops, and every check that failed or could not run.

How the work is checked

• Supporting and adverse evidence use comparable periods; absence of evidence is not evidence a risk is absent.
• Every factual claim, figure and date traces to a source or is clearly labeled as an assumption.
• The original source files stay intact, and revised files have distinct names or versions.
• Each required component check ran, or the run stopped and says which check could not pass.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Benjamin Graham would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Unsupported claim spotter. Lists each claim in the draft and the exact evidence it needs. Treats financial claims as high risk. Hands step 2 the claim list with the proof wanted for each.
• Source note summariser. Reads each filing for evidence that supports or challenges each claim. Keeps source dates and states what it did not read. Hands step 3 the claims with evidence, marked supports, contradicts or silent.
• Presentation builder. Drafts a committee discussion outline that sets out the thesis, the counter-case and the open questions. Makes no target price. Needs your reader and time limit.

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 build-an-equity-thesis-counterevidence-brief 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/build-an-equity-thesis-counterevidence-brief/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

• Your research thesis draft, as a memo, note or list of points
• The dated filings and exhibits behind it, such as annual and quarterly reports (from the company's investor page or a regulator's site)
• The as-of date and your investment horizon
• Who will read the outline, and by when (optional)
• Your earlier notes on the company (optional)

Helpful context (optional)

• Filings in full, with their dates, not excerpts.
• Your thesis draft in your own words.
• A named reviewer who will argue the other side.

Tools and access

• A chat AI that can read files: It reads the full filings. A pasted summary hides the clauses that cut against a claim.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.

Functions and deliverables

• Investment argument and contrary-evidence review: Check an investment argument against dated sources. Get supported claims, contrary evidence and questions that still need research.
  • A claim ledger: each claim, the evidence it needs, its source and date, and whether the filings support, contradict or say nothing
  • The evidence that cuts against the thesis, with where to find it
  • Open research questions for each claim with no proof
  • A committee discussion outline: the thesis, the counter-case and the unanswered questions
  • A list of facts it could not check
• Unsupported claim spotter: Find the claims in your draft that need a source before you publish. Each one is ranked by risk, with the kind of source to look for.
  • A summary of how many claims need support
  • A table of claims ranked by risk
  • The kind of source that would settle each
  • Internal conflicts in your draft
  Source: Pro Skill Packs.
• Source note summariser: Paste an article, talk or chapter into this source note summariser. You get each claim, how well it is backed, the gaps and three quotes to keep.
  • Every claim with a quote and location, and the evidence behind each rated
  • The gaps and assumptions
  • What it adds to your question, three quotes to keep, and an 80-word summary
• Presentation builder: Turn your outline, report or notes into a slide deck built for your audience. Get a presentation builder result in Marp, reveal.js, PPTX or Google Slides.
  • A complete slide deck file in your chosen format
  • A takeaway headline on every slide
  • A suggested chart, image or layout for each slide
  • Speaker notes for each slide
  • A list of claims for you to check before you present
  Source: Burhan Sebin.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Benjamin Graham: Learn to separate price from value using Benjamin Graham’s recorded frameworks. Check the evidence, the downside and the room for error.
  • Your problem worked on the way Benjamin Graham would: their questions, their method, their push-back
  • The answer or the work, in Benjamin Graham's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You wrote a thesis and want to know which claims no filing backs up.
• A colleague's thesis lands on your desk and you have to challenge it.
• The investment committee meets soon and someone will argue the other side.
• You suspect you only gathered evidence that agreed with you.

Limits to check before starting

• Your thesis is a university dissertation. Use the Thesis defence outline and question planner workflow.
• You want a valuation or a target price. This builds none. Use the Equity valuation scenario reviewer workflow to test your assumptions.
• You have no dated filings. The ledger will show claims with no evidence, but it cannot supply facts.
• You want a buy or sell recommendation. This tests a thesis. A person makes the decision.

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 workflow pack and give it to an AI that can read files, such as Claude, ChatGPT or Gemini.
• Attach your thesis draft and the filings. Paste the as-of date and your horizon. Say who will read the outline.
• After step 1, check that every claim in your draft is on the list, including the ones you think are obvious.
• After step 2, read each claim marked contradicted or silent. Check the source date, and that supporting and adverse evidence come from comparable periods.
• Fill every MISSING line before the outline goes to a committee. Nothing here sends or publishes anything.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-an-equity-thesis-counterevidence-brief 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.