Your AI agent skips steps. Give it a todo list.

Description and use

The TodoWrite tool prevents agents from skipping steps by recording the plan as a checklist and ensuring only one task is in progress at a time, leading to complete and visible task execution.

Problem

AI agents often skip steps in long tasks, leaving some tasks unfinished without errors.

Outcome

The TodoWrite tool prevents agents from skipping steps by maintaining a live checklist, ensuring only one task is in progress at a time, and updating the plan after each step. This leads to complete task execution and clear visibility of progress.

Workflow

• Give the agent a multi-step request with a clear plan.
• The agent calls TodoWrite to generate a todo list with tasks and statuses.
• The agent processes one task at a time, marking it in_progress.
• After completing a task, the agent calls TodoWrite again to update the list, marking the task completed.
• The agent repeats until all tasks are completed.
• The agent returns a final summary of the work done.

Evidence

Language models pay less attention to whatever sits in the middle of a long context. As an agent works, its context fills with tool calls and results, and the original plan drifts into that middle zone.

Source

One rule does most of the work: only one task can be in_progress at a time.

Source

If the agent skips the list on a big job, make the request more explicit about its steps or tighten the system prompt.

Source