Part IV - Multi-step processes and tool use
Multi-step work introduces saved state, retries, permissions, partial failure, and effects outside the program. Some software follows fixed steps and routing rules. In other cases, the model selects its next action from available tools using the current state and observations. Both designs need controls on execution and stopping.
Each step needs defined inputs, checks on its result, and a way to record progress. Retrying an operation must not accidentally repeat its effects. Permissions, approval checks, and time and cost limits control what may run. These safeguards also apply when the system plans work, runs code in a restricted environment, uses a shared protocol to connect tools run by separately managed services, passes work between task-running components, or saves information for later use.
Chapter 8 builds predefined chains, routes, parallel branches, feedback loops, and approval checks. Chapter 9 adds model-selected actions, code execution, tool connections, retrieval recovery, and repeated trials. Chapter 10 examines explicit planning, dependency scheduling, feedback between attempts, and agent coordination. Chapter 11 follows information selected for reuse across sessions, including correction and deletion. These are design choices for different requirements, not required upgrades.
