Where to Write Your Prompt
Your agent’s prompt lives in Basic Details → System Prompt inside your agent configuration. If you used a template, a prompt was auto-generated for you. You can edit it directly from that screen. See Agents for the full System Prompt section breakdown.The Golden Rules of Voice Prompts
Voice prompts are different from chatbot prompts. Callers hear responses spoken aloud - so everything about how you write the prompt affects how natural the conversation sounds.Be Specific
Vague instructions produce vague behavior. Tell the agent exactly what to do, not just what kind of agent it is.
Keep Responses Short
Long AI responses sound unnatural over the phone. Instruct your agent to keep answers to 2-3 sentences.
Define Every Scenario
Write instructions for greetings, common questions, edge cases, and what to do when the agent can’t help.
Always Set a Fallback
Tell the agent exactly what to do when it doesn’t know the answer - never leave this undefined.
Prompt Structure
Every effective agent prompt has the same core sections. Valuez AI templates auto-generate these - but understanding them helps you customize effectively.1. Role and Identity
Tell the agent who it is and what it represents.2. Primary Responsibilities
List the specific tasks this agent is responsible for. Be explicit - the agent will only do what you tell it to do.3. Communication Rules
Define exactly how the agent should speak. This is especially important for voice - responses need to sound natural when read aloud.4. Knowledge Base Instructions
Tell the agent how to use its training data.5. Escalation Logic
Define exactly when and how to transfer to a human.6. Boundaries and Safety
Tell the agent what it must never do.Complete Prompt Examples
Customer Support Agent
Appointment Scheduling Agent
Outbound Sales Agent
Common Prompt Mistakes
Writing a prompt that's too long
Writing a prompt that's too long
Prompts over 1500 words slow down response time and confuse the agent. Keep your prompt focused. Use the knowledge base for detailed information instead of putting everything in the prompt.
Not defining fallback behavior
Not defining fallback behavior
If you don’t tell the agent what to do when it can’t answer, it will either make something up or give a robotic error response. Always define a fallback - transfer number, message, or both.
Using bullet points in response instructions
Using bullet points in response instructions
Bullet points are a written format. When your agent speaks them aloud they sound like: “One. Answer questions. Two. Book appointments.” - extremely unnatural. Write all response instructions as prose.
Being vague about responsibilities
Being vague about responsibilities
“Help customers with their questions” is too vague. “Answer questions about pricing, book appointments, and transfer for billing issues” is specific enough for the agent to follow reliably.
Forgetting to test after changes
Forgetting to test after changes
Every prompt change should be followed by a test call. Small wording changes can have large effects on how the agent behaves in real conversations.
Prompt Improvement Workflow
Use this cycle to continuously improve your agent over time:1
Run test calls
Use the Test Your AI tab after every prompt change. Test at least 3 scenarios - a common question, an edge case, and a fallback trigger.
2
Review conversation logs
After going live, read real call transcripts periodically. Look for questions the agent answered incorrectly or awkwardly.
3
Identify gaps
For each problem you find, identify whether it’s a prompt issue (behavior) or a knowledge base issue (missing information).
4
Update the prompt or knowledge base
Add specific instructions to the prompt for behavior gaps. Add content to the knowledge base for information gaps.
5
Test again
After every change, run the same scenarios again to verify the fix worked and didn’t break anything else.
Related Pages
Agents
Open the System Prompt section in your agent’s Basic Details to apply what you’ve learned here.
Train Your AI
Upload knowledge base content so your agent has accurate information to draw from.
Test Your AI
Test your prompt changes using Text to Text or Speech to Speech before going live.
Platform Analytics
Use call data and transcripts to identify where your prompt needs improvement.