# Decomposing work

> Large tasks fail as single prompts. This topic teaches breaking work into pieces an agent can complete and you can check, iterating on the pieces as the results reveal what you actually needed, and recognizing the point where another round of delegation costs more than doing the step yourself.

Page: https://schubergphilis.github.io/ai-training/topics/using-agents/decomposition/
License: CC BY-SA 4.0, https://creativecommons.org/licenses/by-sa/4.0/

*Using agents* · topic `using-agents/decomposition`

Large tasks fail as single prompts. This topic teaches breaking work into pieces an agent can complete and you can check, iterating on the pieces as the results reveal what you actually needed, and recognizing the point where another round of delegation costs more than doing the step yourself.

## Concepts

- **Task decomposition**: Splitting a large piece of work into steps small enough that each has a clear input, a clear output and a way to check it. Good pieces can be handed to an agent one at a time, verified independently and redone without losing the others. Decomposition also surfaces the decisions that are yours to make before the agent starts filling gaps. [glossary](https://schubergphilis.github.io/ai-training/glossary/#task-decomposition)
- **Iteration**: Working in rounds: delegate a piece, check it, adjust the brief with what you learned, delegate the next. The first result usually reveals a missing constraint or a wrong assumption about the goal. Treat each round as feedback on the brief rather than as the agent failing, and keep rounds short so mistakes stay cheap. [glossary](https://schubergphilis.github.io/ai-training/glossary/#task-iteration)
- **When to stop and do it yourself**: Recognizing the point where explaining, correcting and re-checking an agent costs more than doing the step directly. Signs include a third round on the same piece, a task that depends on knowledge only you hold, or a check that takes longer than the work. Taking the step back is a judgment call, not a failure of the tool or of you. [glossary](https://schubergphilis.github.io/ai-training/glossary/#when-to-stop-and-do-it-yourself)

## Links

- **Builds on:** [Delegating to an agent](https://schubergphilis.github.io/ai-training/topics/using-agents/delegating/)
- **Leads to:** [Deciding and specifying](https://schubergphilis.github.io/ai-training/topics/coding-with-agents/specification/)
- **Competencies drawing on it:** [Specifies work well enough for an agent to implement and for anyone to verify](https://schubergphilis.github.io/ai-training/competencies/coding-with-agents/specifies-work/), [Delegates a task to an agent and checks the result](https://schubergphilis.github.io/ai-training/competencies/using-agents/delegates-and-checks/)

## Lessons

- [Breaking a task into pieces an agent can finish](https://schubergphilis.github.io/ai-training/using-agents/breaking-work-into-pieces/) (tutorial)
- [Delegating in rounds](https://schubergphilis.github.io/ai-training/using-agents/delegating-in-rounds/) (tutorial)
- [When to stop delegating and do it yourself](https://schubergphilis.github.io/ai-training/using-agents/when-to-stop/) (explanation)

## Sources

- `DLAI-11` [Agentic AI: M1 workflows and autonomy, M2 reflection, M4 evals and error analysis, M5 autonomous agents](https://www.deeplearning.ai/courses/agentic-ai), DeepLearning.AI (course)
- `Academy ai-fluency-framework-foundations` [AI Fluency: Framework and foundations](https://academy.claude.com/courses/ai-fluency-framework-foundations), Claude Academy (course)
- `OpenAI Academy applied-ai-foundations-szsmv` [Applied AI Foundations](https://academy.openai.com/public/courses/applied-ai-foundations-szsmv), OpenAI Academy (course)