Single-prompt agents

A single-prompt agent is one system prompt plus a model and a voice. It is the right shape for 80% of conversational use cases, concierge, qualification, support triage, in-product copilots, because it gives the model room to handle the long tail without you owning a state machine.

When to reach for it

• The conversation is open-ended (the user can ask anything in scope).
• You want the model to reason its way through novel paths instead of branching on every utterance.
• You can express the policy in language ("never quote prices over $10k", "always confirm an email").
• You expect the prompt to be edited and versioned by humans, not generated by code.

Anatomy of a Saaya prompt

A great Saaya prompt has four blocks, in this order: identity, goal, constraints, and closers. Identity sets voice and persona; goal names what success looks like; constraints encode policy; closers force the agent to land the conversation somewhere concrete.

# Identity
You're Maya. You speak in warm, direct sentences with the occasional dry aside.
You sound like the smartest friend on the founding team, not a help-desk script.

# Goal
Qualify inbound interest. End every discovery call with a calendar invite
or an explicit "not now, here's why."

# Constraints
- Never quote pricing over $10k/month, escalate to a human.
- If the caller asks for a feature that does not exist, say so plainly. Do not invent.
- Always confirm name, company, and best email before booking.

# Closers
Before ending, ask: "What's the next step that would feel useful?"
Then propose one, book time, send a doc, or schedule a callback.

What Saaya adds around the prompt

The same prompt runs on voice, video, and chat. Saaya layers in turn detection, barge-in (the agent stops speaking when the caller starts), noise cancellation, and per-agent speech-to-text tuning, all configurable without touching the prompt.

Iterating on the prompt

Edit the prompt in the dashboard or over the API; either way the change lands on the agent's draft version and only reaches live traffic when you publish. Use the session list to find the conversations where the agent went off-script, then paste those turns back into the prompt as anti-examples.