Hire an AI case competition slide reviewer

Everything it can hand back

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

• A revised case deck, as a .pptx file if your AI can build one, or as slide-by-slide text
• A financial bridge that ties each step to an exhibit or an assumption
• A challenge register of likely judge questions with sourced answers
• A rubric check that shows which slide answers each criterion
• A list of claims that no source backs
• A review log for your next review

How it does the job well

• Do not invent facts, figures, customer evidence or sources. Anything without a source is an assumption and is labelled one.
• Keep the original files intact. Save revised slides under new names or versions.
• 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.
• Give every message one clear, low-effort next step.
• Qualify honestly. Record budget, authority, need and timing as known, unknown or assumed.

Mistakes it avoids

• Repeating an old recommendation as a new finding.
• Saying a slide was inspected when it was not rendered.
• Letting a confident tone stand in for a source.
• 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: Your team changes its recommendation in the last week before the final.

• Revised deck (case-deck.pptx or deck-text.md). The slides in order, one message per slide, with the numbers and sources each one uses.
• financial-bridge.md. Steps from the starting numbers to your outcome, each tied to an exhibit or assumption.
• challenge-register.md. Likely judge questions, your best answer, its source and whether it is ready.
• rubric-check.md. Each rubric criterion, the slide that answers it and any gap.
• unsupported-claims.md. Claims on slides with no source, and what to do with each.
• review-log.md. What changed, the path taken, checks done and missed, and the state for next time.

How the work is checked

• Personal details are verifiable and correct.
• Each deal update cites the call, email or note behind it.
• Follow-ups have dates and owners.
• 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 Charles Darwin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the last state. It keeps the case version, rubric version, recommendation, assumptions and the slides each one touches. The first run sets a baseline.
• Check what changed. It compares versions and dates with the last review. If nothing changed, it says so and leaves your work alone.
• Stress test the recommendation. It maps each rubric criterion to a slide and builds the strongest case against your recommendation.
• Source the assumptions. For each new assumption it finds the source in the case or exhibits, or marks it UNSUPPORTED before any slide uses it.
• Rebuild the affected slides. It changes only the slides touched by the change, saves them under new names and keeps your originals.
• Check the sums and claims. It checks the bridge adds up, scenarios are not shown as forecasts, and no claim lacks a source.
• Save the review. It logs the path taken, the checks done and the checks missed, so the next review can compare.

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 case-competition-evidence-review-assistant 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/case-competition-evidence-review-assistant/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 full case text and its exhibits
• The judging rubric and your time limit
• Your team's recommendation and current deck
• Your financial exhibits and the assumptions behind them
• Your last review file (optional)
• Python PowerPoint tools, only if you want a .pptx file built (optional)
• If your rubric is missing or partly pasted, say so. The agent marks the missing criteria and reviews the rest.

Helpful context (optional)

• The judges' feedback from an earlier round.
• Your team's notes on why you rejected the other options.
• The speaker order and the time each person has.

Tools and access

• Claude, ChatGPT or Gemini with file upload: It reads the case, rubric and exhibits together and does the bridge sums.
• Python PowerPoint tools and a slide renderer: They let your AI build the .pptx and look at each rendered slide, instead of giving text only.
• Claude Code or another AI that can run Python: It builds the editable deck from the bundled launch-tools/build_case.py. A chat AI without code gives an outline.
• PowerPoint or Google Slides: Open the deck and look at every slide. The AI cannot judge how a slide looks to a person.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.

Functions and deliverables

• Case competition slide reviewer: Check a changed case recommendation and its numbers. Review new assumptions and update the affected slides with supported tools.
  • A revised case deck, as a .pptx file if your AI can build one, or as slide-by-slide text
  • A financial bridge that ties each step to an exhibit or an assumption
  • A challenge register of likely judge questions with sourced answers
  • A rubric check that shows which slide answers each criterion
  • A list of claims that no source backs
  • A review log for your next review
• Case competition financial-assumption reviewer: Share the full case, marking guide and draft recommendation. Get a challenged argument, financial checks and an editable deck when tools support it.
  • A revised deck with the answer first, full-sentence titles and a chart on each analysis slide
  • A financial bridge for each scenario, tied to its exhibit, with mismatches listed
  • A challenge register: each claim or number a judge could attack, with the risk and the fix
  • A list of assumptions and open questions for the team
• 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
• Case competition slide deck builder: Build a case competition deck that leads with your answer. Get an editable PowerPoint with charts, financials and backup slides for judges' questions.
  • An editable PowerPoint deck with native charts
  • An executive summary slide with the answer, reasons and impact
  • Financials, a rollout plan with stop rules, and risks
  • Backup slides for likely judge questions
  • A list of the slide titles, an assumptions list and the likely questions
  Source: Calvinkub.
• 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
• Charles Darwin: Build a case using Charles Darwin’s recorded approach. Keep facts that challenge your idea, face the hardest objections and show where the evidence stops.
  • Your problem worked on the way Charles Darwin would: their questions, their method, their push-back
  • The answer or the work, in Charles Darwin'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

• Your team changes its recommendation in the last week before the final.
• The judges update the rubric, or the case adds a new exhibit.
• A teammate rebuilt a financial slide and you need to know the numbers still add up.
• You want the hardest judge questions, each with an answer tied to a source.

Limits to check before starting

• This is your first pass and you have no earlier review. Run the Case competition financial-assumption reviewer workflow.
• You only want practice questions from the judges. Use the Case competition answer and backup-slide planner workflow.
• You want a talk story, not a deck review. Use the Case-based pitch and talk writer workflow.

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. If you cannot add it, paste SKILL.md into a new chat.
• Attach the case, rubric, current deck, exhibits and assumptions. Type your time limit. Say if this is the first review, or attach the last review file.
• Say "Review against the rubric, fix the affected slides and check the bridge." If you want a .pptx, say so.
• A .pptx needs an AI that can run Python and the deck builder tools from the pack. Without them you get the deck as text to paste into PowerPoint or Google Slides.
• Open rubric-check.md first. Then open financial-bridge.md and compare each number with your exhibit.
• Look at every slide yourself before you present. Keep review-log.md for the next round.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/case-competition-evidence-review-assistant 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.