Example 2: One Choice

A learning example with one fork: the agent does the task, then answers one yes-or-no question — does the result fully match the request? Yes leads to a report; no leads to an honest note about what is missing. No loops and no variables. For real work, describe the task to your agent and let it choose a ready flow or create one.

The steps

• Do the task the user asked for.
• Check the result against the request. Answer yes if it fully matches, or no if something is missing.
  • yes — it matches →
    • Tell the user in a few sentences what you did.
  • no — something is missing →
    • Tell the user what is missing and why, and suggest what to do next. Do not start the task again in this flow.

Start it

The easiest way is to ask your agent in plain words, for example:

“Run Example 2: One Choice from Moira for this task: …”

An agent that calls the tools directly starts it like this:

mcp__moira__start({ action: "prepare", workflowId: "moira/example-one-choice", parentExecutionId: "none" })
mcp__moira__start({ action: "execute", startAttemptId: "<Start attempt ID from prepare>" })

It is a learning example. For real work you do not need to pick or build a flow: describe the task to your agent, and it chooses a ready flow or creates one for you.

The same process with every text in Russian is Пример 2: Одна развилка.