Skip to content

Recipes ​

A recipe is a worked example, not a new feature. Each one names the actors, the prompts that start the work, the signals to watch in the Work pane, the output to expect, and the mistakes that waste a command.

Recipes ​

GoalRecipe
Run two independent research tracks and combine the resultsRun parallel research
Review one change through separate correctness, security, and test lensesRun a multi-agent code review
Turn an issue into a scoped implementation ticketTurn an issue into a ticket
Give one agent a skill without exposing it to the teamUse an agent-scoped skill

Before you start ​

  • Complete the quickstart and first team. You need a workspace, a leader, and at least two members.
  • Give every agent a main model. A recipe that names an agent without a model cannot produce a result.
  • Read Conversations and routing for $Name and @path, and Dispatch budgets for the ceilings a recipe can hit.
  • Open the workspace group chat for multi-agent work. A direct chat stays one-to-one and never routes a mention to another agent.

How to use a recipe ​

  1. Read Actors and Before you start and adjust the synthetic names to your own roster.
  2. Copy an Example prompt into the group composer with i, then press Enter. Replace <placeholders> before you send it.
  3. Follow What to watch in Work while the work runs. Open a native session with o when a result needs inspection.
  4. Compare the result with Expected result. If it differs, read Pitfalls before you retry.
  5. Use Next to continue to the neighboring task or the exact reference page.

Expected result ​

Each recipe produces visible work items, a durable answer in the group chat, and a finished history you can inspect. You can name the actor behind each result and the Work state it passed through.

Next ​

Released under the MIT License.