Hire an AI case competition financial-assumption reviewer

Everything it can hand back

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

• 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

How it does the job well

• 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

• Market sizes, customer quotes or prices that are not in the case or your own sources.
• Calling a scenario a forecast. Label scenarios as scenarios.
• Saying a slide was checked when it was not rendered.
• Changing a number to make a total tie.
• Making claims about results, prices or terms that are not approved.
• Long first messages that ask for too much.

What a good result looks like

An example, not your task: Your recommendation is drafted and you want it attacked before the judges do.

• Revised deck (case.pptx). Editable slides with the answer after the title, full-sentence titles and real charts, or an outline if code cannot run.
• Slide titles and rubric map. The titles in order, and the slide that answers each rubric criterion.
• Financial bridge. Each scenario's start, steps and end, tied to its exhibit, with any mismatch shown.
• Challenge register. Each unsupported claim or weak number with its slide, risk, fix and who decides.
• Assumptions and open questions. Every assumption with its source or marked as one, and what the team must still answer.
• Hand-back summary. Each file, the sources used, every MISSING line and the checks that could not run.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The recommendation is on the slide after the title, and each rubric criterion points to a slide, or is marked MISSING: rubric.
• Every scenario total in the bridge matches its exhibit, or is a MISSING: line with both values.
• Every figure on a slide has a source note or is labelled an assumption.
• 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

• Rebuild the deck. Maps each rubric point to a slide, puts the answer after the title, writes full-sentence titles and gives each analysis slide one chart with real values.
• Build the financial bridge. Walks each scenario from start to end and ties each total to its exhibit. A total that does not match is listed with both values.
• Build the file. Uses the bundled build script to make an editable PowerPoint with native charts, then renders every slide to check it. Without Python you get an outline.
• Build the challenge register. Reads the final slides and lists every market claim, customer claim and forecast that no exhibit supports, ranked by risk, with a fix for each.

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 stress-test-a-case-competition-recommendation 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/stress-test-a-case-competition-recommendation/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, with every exhibit and its figures
• Your recommendation, as a draft deck, an outline or a few paragraphs
• The judging rubric and time limit (optional, but slide count and speaking time depend on them)
• Your own analysis, assumptions and sources (optional)
• Python with python-pptx, if you want the PowerPoint file built (optional)

Helpful context (optional)

• Judges' feedback from earlier rounds
• A past winning deck from the same competition, if you have it

Tools and access

• 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.
• Claude Code: It can run Python to build the PowerPoint file with real charts.
• PowerPoint or Google Slides: You edit and rehearse the final deck there.

Functions and deliverables

• 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
• 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.
• 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.
• PowerPoint deck change reviewer: Compare an old and a new PowerPoint deck. Get every changed message, chart number, note, link and slide move in one list.
  • A change register (deck-change-register.md) with each change, its slide, the before and after, and how sure the match is
  • Moved, added and deleted slides, kept apart from edited ones
  • Changes in text, chart and table data, speaker notes, comments, hidden slides and links
  • Before and after pictures of changed slides, when your AI can draw slides
  • A list of checks that passed, failed or did not run, and what is still open
• 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

• Your recommendation is drafted and you want it attacked before the judges do.
• A teammate rebuilt a financial slide and nobody has checked that the totals still tie to the exhibits.
• The judges' rubric is clear and you are not sure your deck answers each point.
• You have a deck full of market claims and few sources.

Limits to check before starting

• You have no case brief or no analysis yet: start with a plan, then use the Case competition slide deck builder.
• You want practice Q&A questions and answer notes: use the Case competition answer and backup-slide planner workflow.
• You already ran this once and only a number or the rubric changed: use the Case competition slide reviewer.

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 add it to an AI that can run Python, such as Claude Code. In Claude, ChatGPT or Gemini without code, you get an outline instead of a file.
• Attach the case, the exhibits, the rubric and your recommendation.
• Say: Follow the workflow, and mark any fact you cannot find in the files as MISSING.
• Open the deck and read only the slide titles. They should tell the whole story. Ask for rewrites if they read like labels.
• Check every bridge row against its exhibit, then work down the challenge register. Decide each fix as a team.
• Rerun it after big changes, or use the evidence review assistant for smaller ones.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/stress-test-a-case-competition-recommendation 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.