Hire an AI funding pitch claim and evidence organizer

Everything it can hand back

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

• An evidence table with each claim, its source, its date and how the figure is defined
• A list of unsupported claims and what would support each one
• Notes on where two sources disagree or a figure has a gap
• An appendix outline with one short answer note per checked claim
• A hand-back summary that names every gap

How it does the job well

• Never invent a market size, a customer, a quote, a number or a forecast. A claim with no supplied source stays on the unsupported list.
• Every figure carries its period and its definition (for example, revenue for which months, users counted how). If these are not given, write MISSING:.
• Mark every projection as an assumption, with who made it and when.
• Keep confidential exhibits out of the appendix unless the user says they may go in.
• Do not say a claim is true or false from memory. Say what the supplied sources show.
• Research the buyer and their company before writing. One specific, true detail beats ten generic lines.
• Lead with the buyer's problem and outcome, not your features.

Mistakes it avoids

• Making claims about results, prices or terms that are not approved.
• Long first messages that ask for too much.
• Updating pipeline numbers on hope rather than evidence.

What a good result looks like

An example, not your task: You have a pitch deck and an investor meeting, and you need an appendix that answers "how do you know?"

• Evidence table. Each claim with its source file, its date, how the figure is defined and its status.
• Unsupported claims. Claims with no source, and what kind of evidence would support each one.
• Conflicts. Places where two of your sources give different figures for the same thing.
• Appendix outline. One slide per checked claim, with the exhibit to show and a short answer note.
• Hand-back summary. Each saved file, every MISSING line and the checks that did not run.

How the work is checked

• Counts in the summary match the rows.
• Each supported claim names a file and a date.
• Every figure has a period and a definition, or a MISSING: line.
• No appendix slide uses an unsupported claim or a confidential exhibit.
• 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

• Unsupported claim spotter. Lists every claim in the pitch that needs proof, such as metrics, market statements, forecasts and superlatives. Hands step 2 the claim list. Check before moving on: each claim is a quote from the pitch.
• Source note summariser. Matches each claim to a dated exhibit you gave. Notes how each figure is defined, how sure it is, and where sources disagree or are missing. Hands step 3 the table of checked claims.
• Presentation builder. Builds the appendix outline and a short answer note for each checked claim. Marks projections as assumptions. Leaves out anything you marked confidential.

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 prepare-a-funding-pitch-evidence-appendix 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/prepare-a-funding-pitch-evidence-appendix/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 pitch draft, as slides, a document or pasted text
• Dated records behind the numbers, such as sales reports, user counts and pipeline lists
• Financial exhibits and market sources you plan to cite (optional)
• What you may show investors and what stays confidential
• The meeting format and time, such as a 20-minute pitch with 10 minutes of questions (optional)

Helpful context (optional)

• Your last two investor updates or reports, so figures can be matched to what you said before.
• A person who can confirm what may be disclosed.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read your pitch and your records together. In plain chat, paste the key figures with their dates.
• A slide tool such as PowerPoint or Google Slides (optional): You build the appendix slides there from the outline. This workflow does not make the slide file.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.

Functions and deliverables

• Funding pitch claim and evidence organizer: Share your pitch, dated records and disclosure limits. Get a claim-to-source table, unsupported claims and a supporting-slide outline.
  • An evidence table with each claim, its source, its date and how the figure is defined
  • A list of unsupported claims and what would support each one
  • Notes on where two sources disagree or a figure has a gap
  • An appendix outline with one short answer note per checked claim
  • A hand-back summary that names every gap
• 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.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one

Tasks you can use it for

• You have a pitch deck and an investor meeting, and you need an appendix that answers "how do you know?"
• Your numbers sit in several files and you are not sure they match the slides.
• A grant or fund asks for supporting evidence along with your application.
• A friend read your pitch and said "I would not believe that line", and you need to know which lines are weak.

Limits to check before starting

• You only need to check one slide or one paragraph. Use the Unsupported claim spotter on its own.
• You want to judge the shape of the deck, such as slide count and font size. Use the Pitch deck presentation reviewer.
• You have no records yet. Gather them first. The workflow will only list what is missing.
• You want legal, tax or accounting advice on what to disclose. Ask a qualified person.

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 and give it to your AI, such as Claude, ChatGPT or Gemini. Use one that can open files if your records are in sheets or PDFs.
• Attach the pitch draft and the records. Say what is confidential and how long the meeting is.
• Read the unsupported list first. Fix the claim, find the source or remove the line from the pitch.
• Read the evidence table. Check each date and each definition against your own records.
• Use the appendix outline to build the slides. Keep each projection labeled as an assumption.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-funding-pitch-evidence-appendix 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.