Chapter 1 of 6 · 4 practices · 3 min · 4-question quiz
Choosing between a workflow and an agent
Agents trade cost and predictability for flexibility. These practices help you pick the simplest design that solves the problem.
Start: Start with the simplest design and add autonomy only when it pays off4 practices in this chapter
- 1Start with the simplest design and add autonomy only when it pays offAnthropic's article on building effective agents draws a clear line: The article's advice is to start with the simplest solution and add complexity only when needed. Agents often trade latency and…
- 2Know the standard workflow patterns before reaching for full autonomyThe same article names five workflow patterns that cover many problems without a free-running agent: Many production "agents" are really one of these with a tool or two. That is a good thing: each…
- 3Build one agent before splitting work across severalMulti-agent systems add handoffs, shared state and more places to fail. OpenAI's evaluation guide advises adopting multi-agent designs only when evals justify the added complexity, and adds handoff…
- 4If you use a framework, understand the prompts and calls underneath itAgent frameworks save boilerplate, but Anthropic's article warns that they can add abstraction layers that obscure the underlying prompts and responses, which makes debugging harder.
Check yourself on this chapter
4 questions, right here once you are signed in. Your progress is saved as you read.