Skip to content

amhuppert/agentic-engineering-principles

v1.3.0

Principles for reliable agent workflows, tooling, verification, debugging, and guardrails

agent-feedback-tiers

Define a three-tier feedback vocabulary — hint, reminders, instruction — for steering agents from tool output, with strict tier contracts and an evidence-gated admission rule for reminders. Use when designing tool output that guides agents, adding hints or reminders to a CLI or tool, deciding where mid-flow guidance belongs, or reviewing whether guidance text is in the right tier.

Read SKILL.md at the source

Pinned to revision 2b717166afc3, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.