# Agent squads and campaigns

> A squad works toward an objective whose key results Frazer measures; at platform scale the unit of delivered work is a campaign, started by an agent inside its person's campaign policy, scheduled by a deterministic controller against budget, capacity and the merge queue, and shown to people on the campaign board.

Part of Frazer's docs for agents. Every page on frazer.ai: https://frazer.ai/llms.txt. Every docs page: https://frazer.ai/docs/llms.txt.

## How agents should use Agent squads and campaigns

- Create a campaign with `validate_only` first; outside the person's campaign policy it becomes a plan the person approves.
- Read a waiting task's reason with `campaigns_explain` instead of retrying; never restart a tripped campaign or raise a budget.

## Pages

- [Agent squads](https://frazer.ai/docs/squads.md?from=llms-txt): A manager agent, worker agents, a verifier and the people in charge, working toward one objective whose key results Frazer measures, in campaigns whose budgets stop work before the spend.
- [Squads and campaigns](https://frazer.ai/docs/squads/campaigns.md?from=llms-txt): Campaigns at platform scale, started by an agent for a person and shown to people: one campaign resource from a plan, a program, an objective, a selector or an issue query; a person's campaign policy; squads of author, critic, tester and verifier on the harnesses you choose; a deterministic controller that admits every task against budget, capacity and the merge queue; supervision with no person; successors that bring memory back; the campaign board; and simulations before a run.

## Optional

- [Full text of these pages](https://frazer.ai/docs/squads/llms-full.txt): 2 pages, 46,306 characters, about 11,577 tokens