Prerequisite Actions — called Tasks in the underlying agent editor — define the distinct journeys the Enterprise Search agent can run, each with its own objective, steps, and tools. This screen mirrors the AI Agent editor's Tasks settings exactly.
Overview
Tasks define different journeys, letting you structure the different flows your agent can execute. Each task bundles an objective, a set of step-by-step instructions, the tools it's allowed to use, optional conditions for when it runs, and, optionally, its own execution model. At runtime the agent detects which task fits the user's request and runs it. Structuring the agent into clear tasks makes its behavior predictable — instead of one giant instruction set, each journey is scoped and tooled on its own.
Creating a task
Use Add Task to open the full-page task editor and fill it in:
Objective (required) — what the task should accomplish, described clearly.
Instructions — the ordered, step-by-step actions the agent must follow in sequence, added one at a time.
Tools — the actions the agent can take; it picks the right tool based on context.
Conditions (optional) — the task only runs when these conditions are met.
Execution model for this task — by default the task inherits the agent's model; override it here when one journey reads better in a different model's voice or needs more reasoning depth.
Give the task a name in the header and click Save. Save stays disabled until the task has a name and you've made a change.
Tool selection strategy: Routed vs. Direct
Tool selection controls how all of an agent's tasks are exposed to the model. Open it from the task list header and pick one of two strategies:
| Strategy | How it works | Tag |
| Routed | Tasks are grouped behind a single router tool that dispatches at runtime. | Recommended — scales past ~15 tasks |
| Direct | Every task becomes its own tool; the model picks directly via function calling. | Fastest — best under ~15 tasks |
Use Direct for a handful of tasks where speed matters; switch to Routed as the agent grows past roughly fifteen tasks so the model isn't overwhelmed with choices. With Direct selected, the Task Detection model isn't used — the main model picks tasks directly. The header shows the current strategy and a badge for any per-task overrides.
What happens at runtime
Both strategies expose your tasks to the model as tools — the difference is how many. With Routed, the model sees one router tool whose input is simply the task name, chosen from your enabled tasks; one tool in the catalog no matter how many tasks you have, which is why it scales. With Direct, each task becomes its own tool named after the task, and the model picks the task by calling its tool directly — faster, but every task adds an entry to the tool catalog the model must reason over.
In both cases, tasks whose governance rules don't pass for the current user are filtered out before the model ever sees them. When the model selects a task, the task's step-by-step instructions are injected into the conversation as the tool's result, so the next reasoning step runs under that task's rules, tools, and, if set, its own execution model. Every selection is logged as a "Topic Selection" entry in traces.
Task state and dynamic instructions
Each task runs as its own thread inside the conversation. The runtime keeps a per-task state record holding which agent triggered it, its current topic, and its own loop counter, separate from the conversation-level state — so a task only sees the conversation history that belongs to it, its loop-limit budget is counted separately, and its instructions don't leak into other tasks. When the task needs a final answer in a specific shape, the expected output format is appended to the model's instructions at the end of the run.
Besides the static instructions you write in the task editor, a task can carry a dynamic-instructions automation. When the task is selected at runtime, that automation runs and its output is appended to the task's written instructions before they're handed to the model — useful when part of a journey's guidance depends on live data, such as current promotions or a per-customer policy.
Managing tasks in the list
The task list shows each task's Topic Name, Description, Owner, and Last Updated. Each row has an enabled toggle so you can turn a task on or off without deleting it — tasks are on by default. Row actions let you Edit, Share, and Delete a task; deleting asks you to confirm because it can't be undone. Search by name to find one quickly. Created On and Last Updated By columns are also available, hidden by default — turn them on from the column-visibility control, or hover the Last Updated date for the same detail as a tooltip.