calibrate-claim-confidence

SkillCommunication

Lets your agent soften overly confident wording in outgoing messages when it is running on uncertain information.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the calibrate-claim-confidence skill

About this capability

When the agent's epistemic state (GCCRF) indicates low empowerment and falling certainty, hedges out confident absolutes ("definitely", "always", "100%") in outgoing messages.

What this skill tells your AI

The instructions your AI receives, as published by bitterbot-ai/bitterbot-desktop in skills/calibrate-claim-confidence/SKILL.md and read by ahel’s review.

Bitterbot has an epistemic state (the GCCRF reward function) that quantifies how empowered the agent feels by its current knowledge: high empowerment means it has corroborated context, low means it's running on uncertain ground. When the agent is about to send a message containing confident absolutes ("definitely", "certainly", "always", "100%") but its empowerment is low and its certainty is dropping, this interceptor rewrites the message into hedged language.

This is the canonical example of state-binding: no other agent framework reads gccrf.empowerment to decide whether to hedge an outgoing statement.

What you'll see

When the agent is uncertain, you will see softer language: "likely" instead of "definitely", "typically" instead of "always", "it appears" instead of "obviously". When it is confident (high empowerment, rising certainty), absolutes are left intact.

Implementation

Built-in interceptor calibrate-claim-confidence:default lives in src/agents/skills/builtin-interceptors/calibrate-claim-confidence.ts. Fires up to 6 times per session.

Signals

GitHub stars
2k
Forks
417
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
calibrate-claim-confidence
Source
github.com/bitterbot-ai/bitterbot-desktop