Hire an AI investment research analyst

Everything it can hand back

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

• An evidence table with each fact and where it came from
• The case for, with the numbers that support it
• The case against, with the loss you could face in a bad case
• A list of events that would show the idea is wrong
• A list of what is missing, and what to check before you act

How it does the job well

• Every fact in the evidence table needs a source and a date. A fact with no source in the user's material, or from a web source you actually opened, goes in as MISSING. Do not state prices, market caps, ratios, filings or news from memory.
• If the host has no web access, say so at the top and work only from supplied material.
• Prefer primary sources (company filings, regulator filings, official data) over summaries, blogs or social posts. Say when a source is secondary.
• Give the case against equal effort and detail. Put a number on the downside, with its assumptions.
• Show a value range in three cases from the supplied numbers, with the assumptions beside each. Do not give a price target, a rating or a "buy" or "sell".
• Separate thesis from narrative. A compelling story isn't an investment thesis. Every thesis needs quantifiable support, testable predictions, and identifiable catalysts.
• Always present both sides. The bull case and bear case must be equally rigorous. Advocacy without balance is marketing, not research.

Mistakes it avoids

• Telling the user to buy, sell or hold, or giving a price target or rating.
• Quoting a figure from memory as current.
• A one-sided case. A bull case with no bear case is marketing.
• Copying the profile's sample tables, ratings or targets as if they were facts about this asset.
• Treating a cheap price as proof of value.
• Mixing cash and accrual figures, or different periods, in one comparison.

What a good result looks like

An example, not your task: A friend, a newsletter or a forum is pushing one stock or fund and you want the case and the risks written down.

• Question and scope. The asset, the time horizon, your question and how large the position is for you.
• Evidence table. Each fact with its number, source and date, or MISSING when not found.
• Case for. The strongest points for the idea, each with a number and a source.
• Case against and downside. The main risks with numbers, and the loss in a bad outcome.
• Value range. A bear, base and bull range with the assumptions behind each. No price target.
• Thesis breakers. Events or data points that would show the idea is wrong, with thresholds.

How the work is checked

• Totals tie out, and differences are explained line by line.
• Forecast assumptions are listed and easy to change.
• Anything not checked by a qualified person is marked as needing review.
• 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 and Warren Buffett would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Fix the question. It confirms the asset, the time horizon and what you want to know. Anything missing is asked once, then marked MISSING.
• Build the evidence table. It pulls each fact from your material with the source, and marks facts it could not find.
• Write the case for. It sets out the strongest points for the idea, each with its number and its source.
• Write the case against. It gives the bear case the same weight, and puts a number on the loss in a bad outcome.
• Set the value range. It shows a value range in three cases from your inputs, and says what each case assumes. It gives no price target.
• Name the thesis breakers. It lists the events or data points that would show the idea is wrong, so you know what to watch.
• List gaps and checks. It lists what is missing, how confident the evidence is, and what to verify before you act.

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 finance-investment-researcher 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/finance-investment-researcher/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 company or asset, and your time horizon, such as 6 months or 5 years.
• Your question, such as "is this worth a closer look?" or "what could go wrong?"
• The sources you have, such as annual reports, earnings call notes, a pitch deck or articles.
• How you plan to hold it and how much it matters to you, such as a small bet or a large part of savings (optional)
• What you already believe or have heard about it (optional)

Helpful context (optional)

• The latest annual report and the last two quarterly reports, so trends show.
• Notes from the last earnings call or investor letter.
• Your own limit, such as the most you could lose without it hurting.

Tools and access

• Claude, ChatGPT or Gemini with file upload and web access: It can read an annual report you attach and look up filings, with the link beside each fact.

Functions and deliverables

• Investment research analyst: Get a research brief on one company or asset: sourced evidence, bull and bear cases and the downside to plan for. Not personal advice.
  • An evidence table with each fact and where it came from
  • The case for, with the numbers that support it
  • The case against, with the loss you could face in a bad case
  • A list of events that would show the idea is wrong
  • A list of what is missing, and what to check before you act
  Source: Michael Sitarzewski and Agency Agents contributors.
• Investment business change reviewer: Share a holding’s original business case and later company figures. Compare what changed, where evidence is missing and which assumptions need another check.
  • A then-and-now table of facts
  • A would-you-buy-today answer with the price hidden
  • A mark of keep, watch or weak
  • A short plan for each weaker holding
• Indian earnings scenario brief writer: Prepare for an Indian company’s earnings report. Get dated estimates, key metrics and bull, base and bear scenarios with assumptions kept visible.
  • A one-page earnings preview
  • A consensus table with source and date on every row
  • A ranked list of numbers to watch
  • A bull, base and bear table
  • A list of gaps to check by hand
  Source: nighomni123.
• Business investment analyst: Check if a business purchase pays off. Give it the cost and savings. You get payback, ROI, NPV, IRR, risks and a clear answer.
  • Payback, ROI, NPV and IRR
  • Upside and downside scenarios
  • A clear recommendation
  • Assumptions and risks flagged
  • A comparison table for several options
  Source: Alireza Rezvani.
• 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
• Warren Buffett: Review a business using Warren Buffett’s recorded principles. Check how it earns, what protects it, how managers use cash and which facts remain uncertain.
  • Your problem worked on the way Warren Buffett would: their questions, their method, their push-back
  • The answer or the work, in Warren Buffett'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

• A friend, a newsletter or a forum is pushing one stock or fund and you want the case and the risks written down.
• You are thinking of putting savings into a company and want to know what could go wrong first.
• You own a position and want to know which events would mean you were wrong.
• You are looking at a small private business or startup and want a list of what to check before you put money in.

Limits to check before starting

• You want a buy or sell call for your own money. Take that to a licensed adviser.
• You want a quick one-page note on a listed company. Use the Indian stock research snapshot writer.
• You want ratios and a health check from a company's filings. Use the Company financial health reviewer.
• You want a formal committee paper for a deal. Use the Investment committee memo drafter.

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.
• Name the company or asset and your time horizon. Attach or paste the filings, notes or articles you have. Web access helps but is not needed.
• Say what you want to know, and how large this is for you.
• Type "Write the brief. Show a source for each fact. Mark anything you cannot find as MISSING. Do not tell me to buy or sell."
• Read the missing list first. Add what you can, then ask it to run the brief again.
• Check each figure you plan to rely on against the filing itself. Take your decision to a licensed adviser before you buy or sell.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/finance-investment-researcher 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.