# Evaluating Agent Behavior

> Build agent behavioral evals — tool choice, steerability, constraint compliance. Triggers on "behavioral eval".

- Skill: `build-with-dhiraj/evaluating-agent-behavior` (Agent Skill)
- Install (CLI): `npx skillmds@latest add build-with-dhiraj/evaluating-agent-behavior`
- Raw SKILL.md: https://api.skillmd.com/api/skills/build-with-dhiraj/evaluating-agent-behavior/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: build-with-dhiraj (https://skillmd.com/u/build-with-dhiraj)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/build-with-dhiraj/evaluating-agent-behavior

---


# Evaluating Agent Behavior

Behavioral evaluations (evals) validate the agent's decision-making, such as tool choice and steerability.

## Workflow Decision Tree
1. **Does it need validation?**: If a prompt or tool change affects decision-making, it requires an eval.
2. **Choosing the Rig**:
   - **appEvalTest (AppRig)**: For UI-heavy or complex interactive flows.
   - **evalTest (TestRig)**: For logic-focused behavior.
3. **Policy Setting**:
   - **USUALLY_PASSES**: For new tests.
   - **ALWAYS_PASSES**: For established tests to lock in regressions.

## Checklist
- **Setup Workspace**: Initialize the test environment.
- **Write Assertions**: Define the expected tool calls or behavioral markers.
- **Verify**: Run the eval suite and analyze failures.
---
[google-gemini/gemini-cli](https://github.com/google-gemini/gemini-cli)