roast

---
name: roast
description: Use when someone wants a brutal, multi-angle pressure-test of a business idea before building it, ending in one GO / RESHAPE / KILL verdict and a cheap validation test.
category: Productivity
version: 1.0.0
tools: []
---

# Roast — 5-Angle Idea Panel → One Verdict

## What this does

The default is to agree with you. Roast is the opposite: convene a panel of five independent reviewers — **The Critic, The Champion, The Analyst, The Investigator, and The Customer** — who tear an idea apart and build it up from every angle, then synthesize everything into one honest verdict. Use it before sinking time and money into building the wrong thing.

The panel is adversarial on purpose. No reviewer is allowed to hedge or be polite. The point is to surface what the founder can't see because they're too close to it.

## Step 1 — Frame the idea

Start from whatever the user already gave you, then ask a tight set of clarifying questions so the panel has real context to work with. Ask only what hasn't already been provided. Keep it to 3-4 questions max, in one batch:

1. **The idea** in one or two sentences (what it is, what it does)
2. **Who it's for** and **how it makes money** (the buyer + the price/model)
3. **Your edge** — relevant skills, audience, or assets you already have
4. **Constraints** — budget, timeline, how fast you need first dollar

If the user says "just run it" or gives enough already, skip the questions and proceed. One round, then run the panel. Normalize the four inputs into a single shared brief paragraph before reasoning as each panelist, so all five judge the same thing.

## Step 2 — Run the 5-angle panel

Reason through all five perspectives against the same brief, giving each its mandate below. Each panelist must return: a one-line stance, their 3-5 sharpest points, the single most important thing the user must hear, and a 1-10 score on their own dimension (1 = walk away, 10 = no-brainer).

**1. The Critic — "What kills this?"** Assume the idea fails. Find the fatal flaws, the fastest way it dies, and the load-bearing assumptions that are probably wrong. Be ruthless and specific. No hedging, no "but it could work." Attack the weakest points.

**2. The Champion — "What's the 10x upside?"** Make the strongest possible case FOR the idea. Find the biggest upside, the 10x version, the adjacent opportunities and unlock points the founder isn't seeing. Fight for the potential. Be specific about where the real money and leverage could be.

**3. The Analyst — "Does the logic actually hold?"** Use no outside research. Reason purely from first principles: does the core mechanism make sense, do the incentives line up, is the underlying logic sound, does the math even work in theory? Strip it to fundamentals and say whether it holds together.

**4. The Investigator — "What does the real market say?"** Use web_search. Bring real-world evidence: who the existing competitors are, market size or demand signals, what comparable products charge, whether this is validated by what's already out there or contradicted by it. Cite what you find. Is the real world saying yes or no?

**5. The Customer — "Would I actually pay?"** Role-play the exact target customer described in the brief. React as them, in first person. Would you actually pay for this? What's your real objection? What would make you choose a competitor or just do nothing instead? What price feels right, and what would make you say yes today? Be the honest, slightly skeptical customer, not a cheerleader.

## Step 3 — Call the verdict

Once all five perspectives are worked through, act as the Judge. Read every panelist's findings, weigh them, and synthesize one decisive verdict. **Do not just average the scores.** Weight demand (Customer) and survival (Critic) heaviest and the bull case (Champion) lightest. Apply hard gates: a Customer who won't pay, or a fatal flaw the Critic landed, vetoes a GO. Name the widest disagreement between reviewers as the tension you must resolve, and resolve it in prose.

Fold in the **economics lens** yourself: rough pricing, realistic time-to-first-dollar, and whether the user can actually ship this fast given the edge they described. Then design the cheapest 48-hour test from the riskiest assumption the panel surfaced — map the riskiest dimension (demand, price, feasibility, differentiation, channel, or retention) to a concrete test with pass/fail signals.

Output the verdict in this exact shape:

```
## THE VERDICT: GO / RESHAPE / KILL
Confidence: [low / medium / high]

**The call in one line:** [the decision, plainly]
**Why:** [2-3 sentences resolving the panel's tension]
**Biggest risk:** [the single thing most likely to kill it]
**Biggest upside:** [the strongest reason to do it]
**Money read:** [rough price, time-to-first-dollar, can they ship fast]
**The cheapest 48-hour test:** [the smallest, fastest thing they can do
to validate the riskiest assumption BEFORE building anything]
**If RESHAPE:** [the specific pivot that fixes the fatal flaw while keeping the upside]
```

Then list the five panel scores in one line: `Critic X/10 · Champion X/10 · Analyst X/10 · Investigator X/10 · Customer X/10`.

## Rules

- Every reviewer stays in character. None of them hedges or softens. The value is in the friction.
- The Judge must make an actual call. "It depends" is not a verdict. Pick GO, RESHAPE, or KILL and own it.
- **Do not average the scores.** A high mean can hide a fatal split or a vetoed dimension — resolve the tension, don't paper over it.
- The cheapest 48-hour test is the most important output. It's how the user finds out if they're right without building the whole thing.
- Keep the final verdict skimmable. The panel does the depth; the Judge does the decision.

## Anti-Patterns To Reject

- Softening the verdict to spare feelings ("there's definitely something here…"). If it's a KILL, say KILL.
- Averaging the five scores into a mushy 6/10 and calling it a day.
- Letting the Champion's enthusiasm override a Customer who won't pay or a Critic who found the fatal flaw.
- Ending on advice with no falsifiable test ("go validate it"). Name the test, the cost, and the pass/fail line.
- Running the panel on a one-line brief so all five argue past each other.

## Distinct From (don't reach for the wrong tool)

A single market-first operator persona pressure-tests via the market-dominates thesis alone; use Roast instead when you want 360° coverage across five independent lenses rather than one. An enterprise C-suite advisory pipeline needs deep company-context onboarding and outputs a board memo; Roast is a zero-setup, solo-founder, 90-second gut check. A plan-interrogation mode asks one question at a time to reach shared understanding but never issues a GO/KILL call — Roast judges, that other mode only clarifies.