CausalRAG v0.3
Loading verified build…

CAUSAL DECISION RUNTIME · LIVE PROBE

Don’t ask the model to sound certain.
Make uncertainty operational.

Compare competing hypotheses, choose the experiment that actually separates them, update belief, then decide. The page is rebuilt by GitHub Actions from the repository’s real deterministic examples.

See benchmark evidence

LOW AIRFLOW / HVAC

Which observation is worth buying?

1 · Hypotheses2 · Candidate actions3 · Observation4 · Decision
BELIEF STATE
H1Clogged filter
50%
H2Weak supply fan
50%

Equal priors. The runtime has not observed a discriminating outcome.

CANDIDATE ACTIONS
The language model prefers temperature. The runtime overrides that score because the modeled outcomes of the pressure test differ sharply under H1 and H2.
DECISION TRACE
  1. World model initialized
  2. Waiting for an observation
  3. Posterior not updated

GENERATED DURING DEPLOYMENT

The webpage carries evidence from the Python runtime—not hand-entered claims.

Every publish runs the no-key Bayesian example and seeded HiddenWorld suite. Failures remain visible because calibration and regret matter more than a polished success screenshot.

Identification30 seeded episodes
Mean posteriortrue hypothesis
Causal regretlower is better
Mean probesbefore intervention
Open GitHub Actions runtime output
Loading…