Before you begin
You need an Autopilot agent. See Build an Autopilot agent.Know who says what
Only the system prompt goes to the model. The other messages are fixed text that Fonoster speaks for the agent at set moments:
This changes how you write the prompt:
- Don’t greet in the prompt. The first message already did, and the model sees it in the history.
- Don’t say goodbye before hanging up. When the model calls
hangup, the goodbye message plays. If the model also says goodbye, the caller hears it twice. Tell the model to hang up, not to say goodbye. - Don’t announce a transfer. The transfer message covers it.
Structure the prompt
Use short sections with headings. The model follows them more reliably than one long paragraph, and you can find what to change later. This shape works for most agents:Write for the ear
1
Keep replies short
Ask for one or two sentences per reply, and one question at a time. A caller can’t hold a
three-part question in their head.
2
Put the important part first
Callers interrupt. When they do, the agent stops, and the model only remembers the part the
caller heard. Lead with the answer, then the detail.Instead of “Thanks for waiting, I looked into it, and it seems your order shipped Tuesday,” the
agent should say “Your order shipped Tuesday.”
3
Write the way people speak
The voice reads every character. Tell the model not to use formatting that only makes sense on
a screen:
4
Plan for mishearings
Speech recognition can get names, numbers and accents wrong. Tell the model to confirm what
matters and ask again when something doesn’t make sense:If callers often say a name or brand that’s misheard, add it to the agent’s
hints. See
Build an Autopilot agent.5
Stick to one language
Write the prompt in the language your callers speak, or say which language to answer in. The
agent’s voice and transcriber must match that language.
Tell the model when to use tools
The model picks a tool from its name, its description and your prompt. Be explicit about when to use each one, and what to do when it fails.requestStartMessage, such as “One moment while I check that,” so the caller doesn’t hear silence
while it runs. Smaller models need more explicit tool instructions than larger ones, so test your
tools with the model you deploy. See Give your agent tools.
Keep it honest
An agent that makes something up on a call is worse than one that says it doesn’t know.Tune the model settings
- Temperature. Keep it low, around the default
0.4, so the agent answers the same question the same way. - Max tokens. It caps the length of one reply. The default
400is plenty for short spoken answers. Don’t set it so low that replies stop mid-sentence.
A complete example
This prompt puts the advice together for a receptionist that looks up orders and transfers to a person:Test every change
A change that fixes one call can break another. Write test cases for the calls that matter, and run them after every prompt change. See Test your agent. The prompt and the fixed messages are listed in Autopilot configuration.Next steps
Test your agent
Check your prompt with scripted conversations.
Turn-taking and barge-in
How the agent knows when the caller has finished.