Comparison

Prova vs Constitutional AI

Constitutional AI shapes how a model is trained. Prova governs what any model does at runtime, and signs the record.

BOOK A CALL

Constitutional AI is a training methodology (RLAIF against a principle list) that shapes a model's behavior before you ever call it. Prova is a runtime control plane: it enforces policy at the gateway, scores each run, bounds what an agent may do, and signs every decision, on any model, including closed APIs you did not train. The two are complementary, not substitutes.

FeatureProvaConstitutional AI
Shapes model behavior at training timeNoYes
Governs any model at runtime (incl. closed APIs)YesNo
Per-run verdict + policy enforcementYesNo
Gateway enforcement (block before the call)YesNo
Ed25519-signed receipts, verifiable offlineYesNo
Per-agent IAM (revocable capabilities)YesNo
Change behavior without retrainingYesNo
Runtime autonomy boundariesYesNo
EU AI Act / FDA / SEC / HIPAA evidence exportYesNo
Improves the base model itselfNoYes

Where Prova is different

Works on models you did not train

Constitutional AI only helps if the model was trained with it. Prova governs any model at runtime, including closed-source APIs and open weights you pulled off the shelf.

Per-call evidence, not aggregate hope

Training improves average behavior. It cannot show that a specific decision on a specific day was in policy. Prova signs that evidence per call.

Change the rules without retraining

Tightening a Constitutional principle means a training run. Tightening a Prova policy or revoking an agent capability takes effect on the next call.

Bottom line

Use Constitutional AI (or any alignment training) to shape the base model. Use Prova to govern, enforce, and sign what the model does in production. They pair cleanly.

Govern any model at runtime, no retraining.