# Delegating to an agent

> Delegating to an agent is like delegating to a capable new colleague who will fill every gap with a guess. This topic covers writing a brief with a goal, limits and done-criteria, supplying the context the task needs, choosing how far the agent may go before checking in, and reviewing the result against the brief.

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

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

Delegating to an agent is like delegating to a capable new colleague who will fill every gap with a guess. This topic covers writing a brief with a goal, limits and done-criteria, supplying the context the task needs, choosing how far the agent may go before checking in, and reviewing the result against the brief.

## Concepts

- **Task brief**: The short written statement you hand an agent: the goal, the context it needs, the limits it must stay inside and the criteria that make the work done. Whatever a brief leaves out, the agent fills in with a plausible default, so what it must not touch matters as much as what it must do. Writing done-criteria first turns review into a check. [glossary](https://schubergphilis.github.io/ai-training/glossary/#task-brief)
- **Giving context**: Supplying the agent with the information and materials the task depends on: the relevant files, the approved source of numbers, the constraint you know and it cannot, the example of what good looks like. An agent that has to guess sources takes the most available one, not the right one. Point at things by name and location rather than by description. [glossary](https://schubergphilis.github.io/ai-training/glossary/#giving-context)
- **Choosing a degree of autonomy**: Deciding, per task, how much the agent may do before you look: draft only, act but ask before anything irreversible, or run to completion. The choice follows from how costly a mistake is and how easily it is undone, not from how capable the agent seems. Start with less autonomy on a new kind of task and widen it as the results earn trust. [glossary](https://schubergphilis.github.io/ai-training/glossary/#choosing-a-degree-of-autonomy)
- **Checking results**: Reviewing what the agent delivered against the brief's done-criteria rather than against a general impression. Read the changes, not the agent's summary of them; run what can be run; look for work outside the limits you set. A plausible result is easy to accept and often subtly wrong, so the brief is the yardstick, and any gap goes back into the next brief. [glossary](https://schubergphilis.github.io/ai-training/glossary/#checking-results)

## Links

- **Builds on:** [What an agent is](https://schubergphilis.github.io/ai-training/topics/concepts/what-is-an-agent/), [Verifying outputs](https://schubergphilis.github.io/ai-training/topics/safety/verification/)
- **Leads to:** [Running a coding agent](https://schubergphilis.github.io/ai-training/topics/coding-with-agents/first-session/), [Choosing models and tools](https://schubergphilis.github.io/ai-training/topics/using-agents/choosing-tools/), [Decomposing work](https://schubergphilis.github.io/ai-training/topics/using-agents/decomposition/)
- **Competencies drawing on it:** [Chooses the right tool and autonomy level for a job](https://schubergphilis.github.io/ai-training/competencies/using-agents/chooses-tool-and-autonomy/), [Delegates a task to an agent and checks the result](https://schubergphilis.github.io/ai-training/competencies/using-agents/delegates-and-checks/)

## Lessons

- [Changing the brief while the agent works](https://schubergphilis.github.io/ai-training/using-agents/adjusting-the-brief/) (tutorial)
- [How much the agent may do before it asks](https://schubergphilis.github.io/ai-training/using-agents/choosing-autonomy/) (explanation)
- [Delegating a task to an agent](https://schubergphilis.github.io/ai-training/using-agents/delegating/) (tutorial)

## 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)
- `Ng` AI engineering skills map: build and deploy AI applications, software engineering fundamentals, use coding agents, shape the build, The Batch (newsletter) (reference)
- `Academy ai-fluency-framework-foundations` [AI Fluency: Framework and foundations](https://academy.claude.com/courses/ai-fluency-framework-foundations), Claude Academy (course)
- `Academy introduction-to-claude-cowork` [Introduction to Claude Cowork](https://academy.claude.com/courses/introduction-to-claude-cowork), Claude Academy (course)
- `OpenAI Academy agents-and-workflows-y0qoc` [Agents and Workflows](https://academy.openai.com/public/courses/agents-and-workflows-y0qoc), OpenAI Academy (course)