ChengYanSuo
D

Agent Design Patterns (21)

A distilled take on the 21 core patterns from Google's Agentic Design Patterns. A "which pattern for which problem" cookbook that fills the blind spots of the first three modules.

The first three modules cut along "capability dimensions," "engineering foundations," and "harness methodology." This module picks up a different knife — cutting along 21 reusable implementation patterns, a cookbook of "which pattern for which problem."

The source is Google's Agentic Design Patterns (Antonio Gulli); this is a distilled Chinese-to-English rendering, referencing xindoo's translation project. The 21 patterns group into 6 clusters: core execution / quality & safety / memory & knowledge / collaboration & interop / control & governance / reasoning & exploration.

Lecture order: Lecture 0 is the panorama — laying out all 21 patterns at once, grouping them, and marking "covered in the first three modules or not"; the later lectures dive only into the blind-spot patterns (reflection, learning & adaptation, knowledge retrieval / RAG, agent-to-agent communication / A2A, reasoning techniques, prioritization & exploration), without repeating tools/planning/memory/exception/safety/evaluation already covered.

For: anyone who wants a "move cheat-sheet" — knowing, for a given class of problem, which established patterns are on the menu.

Posts