# Show HN: CrucibleFish

> Source: <https://github.com/alexisvalentino/CrucibleFish>
> Published: 2026-11-18 14:05:07+00:00

**Key takeaway:** CrucibleFish runs a 100-customer synthetic simulation with 2 + N provider calls (seven at the default SWARM_BATCH_SIZE of 20, twelve at 10) for roughly $0.10–0.15 per run, and lowers SWARM_BATCH_SIZE to 10 or SWARM_CONCURRENCY to 1 when an endpoint resets long or concurrent requests.

A local-first startup-validation workbench. One persistent AI guide, 100 synthetic customers, and three temporal floors (Day 1, Day 14, Day 30) let you pressure-test a startup idea before you invest more time in it.

The guide fronts a chat conversation. The workbench beside it exposes the underlying market graph, social contagion, customer memories, telemetry, feature triage, and market hypotheses.

**Important:** every result is a synthetic hypothesis, not customer research, a revenue forecast, or verified market sizing. The app shows a persistent disclaimer; **Read the limits** explains the full boundary. Use the output to design real tests, not to replace them.

I run a network of builders, and we catch ourselves reaching for AI too often. It is easy to generate a confident-looking plan and mistake it for real understanding. I wanted a place where an idea could be pressure-tested before anyone spends weeks building it: 100 synthetic customers with different habits and budgets, three time floors, social contagion, and a God's-eye pivot you can inject when the picture changes.

MiroFish was the inspiration for the swarm — the market graph, collective memory, and the ability to intervene in a running world. CrucibleFish keeps that spirit but stays local, dependency-free, and explicit about what the output is: a hypothesis workbench, not a prediction engine.

That is also why the disclaimer is the first thing you see, and why I added the **Evidence log**. Every week you can record what actually happened — interviews, churn, payments, the surprising thing a customer said — and the guide reasons over those real observations alongside the simulation. The machine proposes; you decide. Your own discernment comes first. The simulation is a mirror and a stress test, never the authority.

Requires Node.js 20 or newer. There are no package dependencies and no install step.

```
cd C:\Users\alexi\vscode\cruciblefish
npm start
```

Open **[http://localhost:4740](http://localhost:4740)**.

The PawsMatch demo loads automatically and needs no credentials. On a first visit you'll see a short onboarding tour (reopen it with the **?** button in the header) and the disclaimer strip under the header. Explore the demo first if you want to see the finished workbench before spending anything.

Open **AI connections** from the header:

- **OpenAI API key** — paste a key here, or set`OPENAI_API_KEY` in`.env` . Without a key you can still use the illustrative demo.
- **Response model** — used for the venture critic and guide chat. Defaults to`gpt-4o` .
- **Fast swarm model** — used for the ontology and customer batches. Defaults to`gpt-4o-mini` on official connections, or the response model on a custom endpoint.
- **Custom base URL** — any OpenAI-compatible Chat Completions endpoint. Structured Outputs (`json_schema` ) are attempted first, with`json_object` fallback.

Keys are sent only from the browser to the local Node server, then to your configured endpoint. They are never written into run JSON, run listings, or the settings API. **Remember keys in this browser** is opt-in; otherwise keys stay in tab-session storage. `.env` is gitignored.

A live run makes **2 + N provider calls**: one market ontology, one venture critic, and N customer batches (N = `100 / SWARM_BATCH_SIZE`). A custom Round-3 intervention makes N more calls.

Some endpoints reset long or concurrent requests. These optional `.env` settings make the pipeline more tolerant:

- `SWARM_BATCH_SIZE` — customers per batch, 5–20, default**20** . Lower to**10** if requests are reset.
- `SWARM_CONCURRENCY` — simultaneous batches, 1–5, default**2** . Lower to**1** if concurrent requests are reset.

With the defaults that is seven calls; with `SWARM_BATCH_SIZE=10` it is twelve. A batch that fails validation is retried once with a repair instruction. At official list prices a run costs roughly $0.10–0.15 with the default models; your endpoint's pricing may differ. Runs can take several minutes on slower providers — an animated progress panel shows each stage as it completes.

1. **New simulation** — fill in the brief: name, one-line pitch, target customer, geography, business model (who pays vs. who uses), pricing and packaging, traction, unfair advantages, and optional**seed material** . Seed material is the highest-return accuracy lever: paste real interview quotes, support logs, or analytics notes.
2. Add current features (tick the ones that need routine manual typing) and planned roadmap items with categories. **Load PawsMatch preset** fills a worked example.
3. **Run 100-customer simulation** and watch the progress panel: market graph, venture critique, each customer batch, then telemetry.
4. **Simulation** view — move among Day 1, Day 14, and Day 30; filter the 100 customers; inspect social threads and episodic memories.
5. **Venture critique** — feature triage, the four-stage data flywheel, the 90-day plan.
6. **Market & capital** — market graph, sizing hypotheses, and a VC shortlist. Verify all of it externally.
7. **Guide conversation** — ask about results, or about a customer by number (`#42` ) or name. The guide is a reasoning partner, not an oracle.
8. **God's-eye pivot** — inject a Day-30 intervention. Only Round 3 changes; identities and Rounds 1–2 stay immutable.
9. **Evidence log** — record one real observation per week with cohort size, measured/estimated status, a linked run and hypothesis, an optional success threshold (e.g. paying rate ≥ 20%), the numbers, and a note. The form opens with a short "how to fill this in" guide and a worked example. Export or import the log as JSON/CSV. Entries stay in this browser.
10. **Include weekly evidence in this run** — the new-simulation form appends the last eight observations to the seed material, labelled as real observations. Uncheck it to keep evidence conversation-only.
11. **Calibration** — compare a linked run's predicted Day-30 active, paying, churn, and GMV with what you observed. A built-in 30-second guide explains what to read; bars show simulated vs real values, differences are spelled out in plain language, thresholds show PASS/MISS, and a summary shows the average gap and range across weeks. Estimated entries are de-emphasised.
12. **Explore demo** restores the original illustrative PawsMatch run at any time.

- Feed real evidence into the seed-material field.
- Run a few variations and keep patterns that stay stable; ignore numbers that swing wildly.
- Ask the guide to challenge assumptions, not to predict revenue.
- Validate important claims with real interviews, product analytics, and primary sources before committing time or money.
- Watch the Calibration summary over several weeks: a stable range matters more than a single week's gap. Use the threshold verdict as a falsifiable check, not a verdict on the whole idea.
- The output is a test plan, not the test result. See **ROADMAP.md** for the weekly experimentation direction.

```
npm test       # 24 tests, mocked providers, no paid calls
npm run check  # syntax check across all JavaScript modules
```

The suite covers provider normalization and streaming, Structured Output fallback, exact batch sizing, ontology and social-thread validation, stable demo telemetry, immutable Round-3 deltas, weekly evidence storage, MIME types, demo reset, and credential exclusion from saved files. Tests disable `.env` before loading modules, so they stay hermetic even when you have a real key configured.

A full live run was verified with real credentials; automated tests do not make paid calls.

```
app/
  lib/          OpenAI client, orchestration, prompts, schemas, demo data, telemetry, env
  public/       Vanilla JS workbench, styles, local icons, Montserrat assets
  scripts/      Test and syntax-check suites
  server.mjs    Local HTTP, SSE progress, run persistence, static files
data/sessions/  Saved live runs (gitignored; credentials excluded)
types/          TypeScript declarations for the shared data model
qa/             Historical browser evidence and QA reports
ROADMAP.md      Experimentation direction and phased plan
PRODUCT.md      Product truth and constraints
DESIGN.md       Design-system record
```

Automated tests mock provider calls. Model entitlement, endpoint quirks, latency, and billing can only be verified with your credentials. No image service, Zep, or OASIS dependency is used; the guide avatar is a local initial and all computation runs in this local Node process.
