Hire an AI case competition answer and backup-slide planner

Everything it can hand back

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

• A list of the weakest spots in your recommendation, each with where it sits
• Practice judge questions for each spot, marked as practice
• An answer note for each question that cites a slide or exhibit, or says it is an assumption
• A brief for each backup slide: title, chart, point and source
• A list of missing facts and checks that could not run

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

• Writing questions from the case title or general knowledge instead of the actual deck.
• Answer notes that sound sure but cite nothing.
• Fixing a number to make it match. Report the mismatch instead.
• Saying a rehearsal went well when no rehearsal happened.
• 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 case competition final is a week or two away and the deck is nearly done.

• Weak spots. The five to eight weakest points in your recommendation, each with the slide or exhibit it sits in.
• Question bank. Practice judge questions grouped by weak spot, each with a rubric point and a source-backed answer note.
• Backup slide briefs. For each likely slide: a full-sentence title, the chart or table, the one point and its exhibit.
• Fact check. A check that terms, currencies, periods and figures match the exhibits, with any mismatch listed.
• Hand-back summary. Every file, the sources used, each 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 steps ran in order, and each one used the result of the one before.
• Every answer note cites a slide or an exhibit, or says ASSUMPTION. None cites something not in the files.
• Every question is marked PRACTICE. No past judge comment or rehearsal result was invented.
• 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 and Alan Turing would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Find the weak spots. Reads the deck and exhibits, lists the recommendation, the main numbers and the assumptions it leans on, and ranks the weakest.
• Write questions and answer notes. Writes tough practice questions for each spot. Each answer note cites a slide or exhibit, or says assumption, and is rated solid, partial or open.
• Brief the backup slides. Outlines a backup slide for the questions that need a chart or table, with its title, point and source. It does not build a file.
• Check the facts match. Checks terms, currencies, periods and figures against the exhibits. A mismatch is listed, never quietly fixed.

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-case-competition-judge-questions 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-case-competition-judge-questions/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 team deck, as slides or the text of each slide
• The case brief and every exhibit the judges can see
• The judging rubric (optional, but it lets each question point to a criterion)
• Your presentation time and Q&A time (optional)
• Weak points you already worry about (optional)

Helpful context (optional)

• A teammate to play the judge
• Feedback from earlier rounds, if you have it

Tools and access

• A chat AI that can read files: It reads the full deck and every exhibit in one run. Without file support, paste the text of each slide and exhibit.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.
• Any good chat AI: Arguing against your case and rewriting the text is work any strong chat AI does well with this skill.
• A friend who disagrees: A real doubter finds objections no list has.

Functions and deliverables

• Case competition answer and backup-slide planner: Share your deck, case evidence and judging criteria. Get practice questions, sourced answer notes and backup-slide outlines.
  • A list of the weakest spots in your recommendation, each with where it sits
  • Practice judge questions for each spot, marked as practice
  • An answer note for each question that cites a slide or exhibit, or says it is an assumption
  • A brief for each backup slide: title, chart, point and source
  • A list of missing facts and checks that could not run
• 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
• Pitch objection and answer writer: Find the toughest objections to your pitch or argument. Paste it and your evidence, get fair answers, open gaps and a rewrite that admits its limits.
  • A list of the hardest objections, each answered or marked as an open gap
  • A rating on each answer: solid, partial or open
  • The one fact that would sink your case
  • A plain note on what your evidence cannot show
  • A rewritten text with the objections built in
• 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.
• Text proofreader: Proofread your text for grammar, spelling and punctuation against a style guide. Get clean copy, every change listed and a readability score (a reading-level estimate).
  • Corrected text
  • Annotated list of every change
  • Reading-level estimate
  • Tone notes
  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
• 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
• Alan Turing: Turn a vague task into clear steps and a fair test. Apply Alan Turing’s recorded approach to models, objections and honest limits.
  • Your problem worked on the way Alan Turing would: their questions, their method, their push-back
  • The answer or the work, in Alan Turing'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 case competition final is a week or two away and the deck is nearly done.
• Your team can argue the recommendation, but nobody has tried to attack it.
• You want to know which numbers you cannot defend before a judge asks.
• You need backup slides ready for the Q&A round.

Limits to check before starting

• You have no deck or exhibits yet: use the Case competition slide deck builder first.
• You want the deck and its numbers checked, not practice questions: use the Case competition financial-assumption reviewer workflow.
• You want a person to play the judge live: this workflow writes the questions, and a teammate has to ask them.

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 Claude, ChatGPT or Gemini. Use your strongest model.
• Attach or paste the deck, the case exhibits and the rubric. Add your presentation and Q&A times.
• Say: Follow the workflow, and mark any fact you cannot find in the files as MISSING.
• Read the weak-spot list first. Correct anything the AI got wrong before you read the questions.
• Rehearse out loud. A teammate reads each question and judges your answer against its note.
• Tell your AI how each rehearsal went so it can update the notes. It never records one on its own.

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-case-competition-judge-questions 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.