Refine and Test Prompts

​

Audience

• Operators iterating on call behavior and tone
• Admins maintaining quality across multiple agents

​

Prerequisites

• Access to prompt tools in workspace
• Existing agent prompt draft
• Test scenario for validation

​

Plan and role requirements

• Prompt tooling availability may depend on plan.
• Editing production prompts should be limited to trusted roles.

​

Working without AI access

The AI parts of Prompt Studio — optional Review with AI suggestions, the Test simulation, and Convert to Intent Flows — need an active subscription and available AI credits. If your workspace has no active plan, or you’ve used all your AI credits, those surfaces are shown locked with a short note explaining why; you won’t see an error. You can still use Prompt Studio in this state. Write your agent’s instructions in plain language as usual and choose Save Instructions — your wording is saved into the agent’s standard prompt so it still automatically follows all the standard call-handling rules. You only need to describe the call flows; the core structure is added around your instructions. To switch the AI features back on, open Settings → Billing to start a plan or top up your credits, then reopen Prompt Studio.

​

Steps

​

1) Draft or import prompt

1. Open prompt tools.
2. Paste or draft your prompt content.
3. Define desired behavior outcomes.

​

2) Refine with prompt assistant

1. Choose Review with AI when you want refinement suggestions. Prompt Studio does not run AI review automatically while you type.
2. Apply improvements for clarity and constraints.
3. Save refined output for test.

​

3) Test in writing

1. Open the Test tab. Your agent opens the conversation with its greeting first — just like a real call, where it speaks before the caller does. Type a caller message to continue.
2. Compare output to expected behaviour.
3. Iterate until response quality is stable.

The test applies the same date and time context and response-style rules your agent receives on a live call, so its answers about dates, scheduling, and tone match production. The greeting is shown as the agent’s first turn for realism, but — exactly as on a real call — it is spoken at the start and is not part of the prompt the agent reasons over. If your agent uses a personalised greeting, the test shows your base opening line as a representative example; the live greeting is tailored to each caller. Caller details and callback context only apply to real return calls and are not simulated here.

​

4) Save or convert

1. Choose Save to keep a custom prompt verbatim.
2. If you want Voqo’s structured format instead, choose Convert to Intent Flows and review the lossy-conversion warning before confirming.
3. Run a controlled call test and verify key workflows before wider deployment.

​

When to use prompts vs skills

• Use prompts for language, behavior, and instruction quality.
• Use skills for reusable structured capabilities and tool-like functions.

​

Troubleshooting

​

Prompt quality regresses after update

• Roll back to known stable prompt version.
• Re-test with same scenario set.
• Apply smaller incremental changes.

​

Tool output differs from call behavior

• Confirm deployed prompt matches tested prompt.
• Check skills/functions attached to agent that may alter behavior.

​

AI review, Test, and Advanced are locked

• This means your workspace has no active plan, or you’ve run out of AI credits — not a fault.
• You can still write and Save Instructions; your instructions are saved into the agent’s standard prompt so it follows all standard call-handling rules automatically.
• Open Settings → Billing to start a plan or top up credits, then reopen Prompt Studio to unlock the AI features.

If unresolved, contact support@voqo.ai with workspace ID, agent ID, prompt version context, and failing scenario.

​

Related docs

• Create and Bind Skills
• Conversation Prompts
• Manage Agent Lifecycle