Investors audit logic, not slides.
Find the structural flaws before the partner meeting.

Crucible is a free pitch deck audit — a forensic pass over the reasoning in your deck. It compiles the reasoning in your deck — the claims, the unit economics, the way the numbers relate to each other — and returns a Clarity Score out of 100 with the specific structural problems named and located. It is the same standard institutional investors apply, run before you pitch rather than after.

Most deck tools evaluate the presentation: layout, story arc, whether the narrative flows. Crucible evaluates whether the underlying business logic holds — whether the revenue model closes, whether the growth assumption survives its own maths, whether two slides contradict each other. Design feedback tells you how the deck reads. Crucible tells you what an investor will find when they check.

ChatGPT tells you whether your deck reads well — it optimizes for persuasion. The Crucible compiles whether the underlying physics hold, catching the structural kill shot a probabilistic model glosses over. That is the difference between flattery and diligence.

Same engine, opposite side of the table. The Crucible is free and built for founders auditing one deck — your own — before you pitch. Clarity is the institutional product investment firms run across a pipeline of deals, with the committee memo, provenance record and team workflow that context requires. The score means the same thing in both.

Before. A structural flaw found by an investor costs you that investor; the same flaw found beforehand costs you an afternoon. The expensive version of this feedback arrives as a pass you never get an explanation for. Run it while the deck is still yours to change.

It applies from pre-seed through Series B, but what it catches shifts. Early on, most findings are about coherence — whether your assumptions agree with each other. Later, they are about evidence — whether the numbers you claim are supported by what you can show. The one case where it adds little is a company with no deck and no model yet.

No — early is when it is most useful. Crucible does not require audited figures. It tests whether your assumptions are consistent with each other and with the story you are telling: whether the hiring plan matches the revenue ramp, whether the burn supports the runway you claim. Estimates can be coherent or incoherent, and that distinction is exactly what gets tested.

Fully free — no credit card, no trial expiry. Founder feedback is the free ingestion layer; the institutional Clarity tier is what funds pay for. You get a bulletproof deck; we get a smarter ecosystem.

No signup is required to run the Crucible. Compile your deck and read the verdict.

A PDF or PPTX deck — a financial model in XLSX is optional. A forensic pass takes minutes, before you ever walk into the room.

A deck as PDF or PPTX, and optionally a financial model as XLSX. If your deck lives in Google Slides, Figma, Canva or Notion, export it to PDF first — that export is what an investor receives anyway, so it is the honest thing to test.

The deck alone produces a score. Adding the model produces a better one, because it lets the engine check the deck's claims against the numbers underneath them — the most common place a contradiction hides. If you do not have a model yet, run the deck now and re-run once you do.

Your deck is processed to extract structural variables, never sold or shared, and never used to train a model. The file itself is held no longer than 30 days under our retention ceiling. The structural data derived from it persists and can include identifying details such as your name, so you can ask us to erase it. You retain full ownership of your IP.

No. Your submission and your score are private to you. We never sell, share, or surface your deck or score to any investor or third party.

Yes. The result is yours and we never surface it to anyone. Founders use it two ways: privately, to find and fix problems before pitching, or deliberately — bringing a scored, sourced audit into a conversation as evidence the numbers have already been stress-tested. The second is unusual, which is exactly why it lands.

No to both. We are infrastructure, not a fund and not a matchmaking service. We do not take equity, do not broker introductions, and do not pass your deck to anyone. A high score is not a referral — it is evidence your reasoning survives scrutiny, which is a thing you carry into your own conversations.

A Clarity Score is a 0–100 measure of how well the reasoning in a deck holds together. It comes from five scored pillars and three audit checks — problem, solution, business model, deal structure and the evidence behind them — not from design, wording, or how convincing the story sounds. The same score means the same thing for every deck, which is what makes it comparable.

The engine returns a verdict alongside the number. 85 and above is PRIORITY — high clarity, the logic holds. 70–84 is INVESTIGATE — adequate, with real questions left to answer. 50–69 is WATCH — low clarity. Below 50 is PASS. A kill shot is separate from the bands: a single terminal contradiction that floors the score to 0 regardless of every other strength.

Aim to clear 70, which is where the engine stops returning WATCH and starts returning INVESTIGATE. Below 50 it returns PASS. There is no separate bar by stage — the floors are identical for every deck — but what a band means does shift: a seed deck in WATCH usually has assumptions still to evidence, while a Series A in the same band has evidence that does not reconcile.

A 0 is not an error — it is a FATAL verdict from the JUDGE Protocol, triggered when the engine finds irreconcilable data it cannot compile around: revenue that contradicts itself across slides, a model that violates its own narrative, a claim with no support. Generative tools smooth these over to keep you happy; the Crucible exposes them, flagged to the exact page and cell, so you fix the fracture before an investor does. The score is the proof the engine works, not a sign it is broken.

No. Crucible does not predict outcomes, replace investors, or guarantee funding. It measures whether your investment reasoning holds together under the standard applied before capital is committed. Timing, market conditions, and fit with a particular fund all remain outside it. Investment outcomes stay uncertain; investment reasoning does not have to.

The business model, by a wide margin. Across 2,488 decks scored in a single four-week window, 67.0% scored below half marks on Business Model Physics — how the company actually makes money. Problem Definition, by contrast, failed in only 17.9%. Founders describe what is broken in the world well, and describe how they make money badly. The full benchmark is published in Where Pitch Decks Break.

Founder dependency is when the business only functions while one person is in every critical loop — sales that only close when you pitch, technical decisions only you can make, relationships held in your head. Yes, it surfaces as a structural finding, because it caps how fast the company can grow and is a common reason a promising deal stalls in diligence.

Work upward from something countable, not downward from an industry report. A top-down TAM — the market is worth billions, we need one percent — asserts a number without evidence that anyone will pay you. A bottom-up figure starts from identifiable customers, a real price, and a reachable segment. Crucible flags the top-down version because investors discount it on sight.

Yes, as many times as you want. Re-running after a revision is the point — it shows whether a change actually resolved the structural problem or just reworded the slide it appeared on. The engine is deterministic, so an unchanged deck returns an unchanged score, and any movement you see is movement you caused.

Sometimes the deck, often the business. A low score on narrative sections usually means you have not explained something you understand. A low score on Business Model Physics usually means the model itself does not close, and no amount of rewriting will change that. The value of the audit is telling you which of the two you are facing.