Your next step

Reliable actions over several steps

Retries, idempotency, permissions, sandboxes, handoffs, checkpoints.

What you’ll learn

A retry can repeat a side effect
Identify an operation that needs outcome checking before retry.
About 4 minutes · Open activity
Idempotency makes repeats safer
Explain a stable operation identifier in a toy retry.
About 4 minutes · Open activity
Read and write permissions differ
Select only the access needed for a task.
About 4 minutes · Open activity
A sandbox limits execution reach
Identify an enforced boundary in a supplied setup.
About 4 minutes · Open activity
Subagents need narrow handoffs
Specify one independent task and return format.
About 4 minutes · Open activity
Parallel work can conflict
Recognize overlapping writes before delegation.
About 4 minutes · Open activity
Humans need usable checkpoints
Choose a review point with concrete artifacts.
About 4 minutes · Open activity
Recover a partial run
Inspect a timed-out write, overlapping edits and a missing result, and choose one recovery for each without assuming the final state.
About 5 minutes · Open activity
Trace one agent task
Inspect a toy file-search agent that reads a workspace, calls a tool, sees an error and changes its next step, and read its proposed change before accepting it.
About 5 minutes · Open activity