Why patterns matter · AI Agent Design Patterns: I Tested All 35 So You Don't Have To

35 agentic design patterns grouped into families.
Without them you're flying blind.
The right pattern can dramatically improve results.

Family	Examples
Tools and actions	Tool use, ReAct
Reasoning	Reflection
Retrieval and memory	RAG, long-term memory
Multi-agent	Supervisors
Safety	Dry runs, hooks

Do this in your own tools, step by step. Ticks are saved on this device.

List the agents you run.
Name the pattern each uses.
Note one that may need a different pattern.

How many patterns are covered?

35.

Why know them?

The right pattern improves results a lot.

0:00 Just naming the pattern in a prompt to your coding agent can change its direction of travel. And here they are, all 35 spread across eight families. This is a live dashboard that I built where we can actually see each one of these in action. It's built on top of this free open repo from a developer called Fared Khan who has aggregated all of these from various sources. And before we get into it, it's worth noting that these patterns are just workflow shapes.

0:23 Each one is a small graph of nodes with a control flow running through it. So things can chain together, they can branch or fan out. And the arena, the dashboard draws that shape live for each run. And the special shape, the one that makes all of this agentic, is the loop. The model decides, it acts with a tool, it checks the result, and it goes again until the job is done. You'll see that loop inside most of these patterns.

0:47 And you don't need to memorize any of these. You just need to know what's the right shape for the job. These patterns can be broadly grouped into eight families. You've got tools and actions, reasoning and reflection, retrieval, there's memory, sampling and search, multi-agent, safety and routing, and then there's a couple of specialtity ones. And knowing these shapes is useful in a lot of scenarios. If you're driving coding agents like clawed code or codecs, you can replicate a lot of these using sub aents, agent teams, or dynamic workflows.

1:34 If you design workflows and automations, every one of them is secretly one of these shapes. If you're building custom AI systems or harnesses, these are your architecture menu. And importantly, if you run smaller local models, the weaker models need the shape