Small words.
Big possibilities.
Choose a rule. Watch it become an answer.
of a data engine
Start with nine words.
Keep the condition. It changes the answer.
Open full labMore sources, evidence tools, clustering and workers.
Signal Foundry
Turn scattered words into useful answers. Run a tiny data factory, break its assumptions, and follow the evidence.
Read a source parcel. Split it into sentences: did the refund condition survive? Compare with the starting setup, then try an exact identifier query.
Remove a source. Turn meaning down to zero. Retrieve one more chunk. Follow what changes across answers, briefs and search.
Order desk
A customer was billed twice. Can your factory find the rule and keep its conditions intact?
Loading sources…
The order could not be loaded.
Start freshSource documents · read or remove
Words → meaning → evidence
Choose an order to start the floor.
Decision bench
Whole documents keep conditions together. Sentences isolate a precise fact but can lose nearby context.
0 = exact word coverage. 1 = vector similarity. Neither score proves a claim.
| Chunk | Baseline score | Current score | Status |
|---|
Model & scoring detail
This teaching model mixes query-word coverage with normalized cosine similarity: weight × (cosine + 1) / 2 + (1 − weight) × coverage. It uses precomputed 384-dimensional MiniLM embeddings. No model weights download to your browser.
RAG means retrieving evidence before composing an answer. Here the composition is a rule-based demo, and quote rules are authored for these fictional missions. Production Atomize uses a richer retrieval and generation pipeline.
Evidence inspector
Claims to check: a high rank is only a candidate. Open a parcel or citation to read the source words.
Demo composition · no live LLM
Meaning Garden
Whole source passages group by real cosine similarity. Moving a point on screen cannot change its group — the underlying score decides that, not pixels. Authored conflict links are shown separately from similarity.
| Chunk | Document | Source text | Group | Similarity and authored relationship |
|---|
Night Shift
A simulated pipeline: workers pull queued jobs, a broker can go down, and a cache can go stale. Nothing here reaches a real queue, cache or service. Every displayed value is computed by this turn-based simulation, not measured from production.
Scenario capacity is 2 provider slots. Set workers to 4 to see two workers wait while the shared resource stays full.
| Layer | Teaching distinction |
|---|---|
| Long-running work | Railway hosts long-running Node workers in the reference architecture. |
| Broker | BullMQ uses Redis as its broker; this simulation does not contact either service. |
| Response and site cache | A separate response/site KV cache can be fresh, stale, or refreshed independently of broker availability. |
| Scheduled refresh | A Cloudflare Worker can run refresh work; that is distinct from Workers KV storage. |
| Transformer attention | A transformer attention KV cache is a separate model-runtime mechanism and is not simulated here. |