Skip to main content
The quickstarts end with an agent that takes calls. This is what to do on day two. Most people try to make an agent good by rewriting the prompt until it feels right. That does not converge, because you have no way of knowing whether a change helped or quietly broke something else. There is a loop that does converge. It is six steps and you will run it many times.
Before you start, build something with Your first inbound agent or Your first outbound agent. This page assumes an agent already exists.

​
The loop

1

Break it

Place a call and try to make it fail.
2

Capture it

Turn that call into a test case, before you fix anything.
3

Fix it

Give feedback on the exact thing it said and let it rewrite the prompt.
4

Prove it

Re-run the test. Now you know instead of hoping.
5

Extend it

Add skills, so calls end somewhere useful.
6

Measure it

Add insights, so real calls tell you what to fix next.

​
1. Break it

Open the agent and use Test Agent in the right hand panel. Start Browser Call talks to it through your microphone with no phone number involved. Start Phone Call asks for a number and rings you, which is the honest test because phone audio is harder than browser audio. Do not be polite. The useful calls are the awkward ones.
  • Interrupt it mid sentence.
  • Say something off topic.
  • Say no, then change your mind.
  • Ask a question the prompt never anticipated.
A call where everything went well teaches you nothing. You are looking for the moment it says something you would not want a customer to hear.

​
2. Capture it, before you fix it

Open the call in Calls. The Summary tab has both halves of this loop on it.
A call's Summary tab showing the transcript on the left and Create test from call, Improve agent and an Insights panel on the right
Click Create test from call. The conversation becomes a case on the agent’s Test tab. Do this first, while the agent is still broken. If you fix the prompt and then try to write a test, you are writing it from memory of a bug you no longer have, and you cannot prove the fix worked.
The Test tab only appears if the Early Access Program is enabled for your environment. See Early access. Improve agent is not gated and works either way.

​
3. Fix it by talking, not typing

Still on the call, click Improve agent. The transcript sits on the left and a feedback box on the right. You have two ways to say what went wrong, and they combine:
  • Describe it in plain language in the feedback box.
  • Click the specific agent message that was wrong and comment on that turn.
The second one is the reason this works. “It should not have offered the discount there” attached to the exact sentence is a far better instruction than any prompt edit you would have typed. Then click Get Recommendations.

​
Review before you accept

Recommendations never apply silently. They open in a Prompt changes window with green for added text and red for removed, numbered so you can step through them with Previous and Next.
The Prompt changes window showing a proposed addition to the agent prompt in green, with Reject All and Accept All in the footer
Reject any single change to keep your original wording. Accept All applies the rest, and the button counts what is left if you rejected some.
Accepting only updates the prompt in the editor. Click Save on the agent or the change never reaches a real call. This is the single most common way people conclude the feature does not work.

​
4. Prove it

Go to the agent’s Test tab. If you have never used it, Generate suite reads your prompt and writes cases for you, grouped by the five things that actually go wrong on calls.
A generated test suite with cases grouped under Flow, Policy, Boundaries, Recovery and Actions
Run executes the whole suite, and each case has its own run control for the one you are working on. Setup context supplies values like a name or an order number so cases behave like real calls. Regenerate tests replaces the suite, and Add test case writes one yourself. Your captured case is in there. Run it. If it passes, the fix is real. If it does not, go back to step 3 with better feedback.
Generated cases are a decent starting suite, but the ones worth keeping are the real calls that went wrong. Every time you hit a new failure, capture it. The suite becomes a record of every mistake this agent has made, and it stops making them twice.

​
5. Extend it with skills

Only now. A skill added to an agent that cannot hold a conversation just gives it a new way to fail. Skills are about how the call ends, not how it talks. Three earn their place first:
  • Appointment scheduling books the meeting on the call instead of sending a link and hoping.
  • Call back later agrees a time with the people who are not ready now, so the contact is not spent.
  • Call routing transfers to a person when the caller asks for one.
Ten are available in total, including in call SMS and email, IVR navigation, call screening and calling an external API.
Adding a skill changes behaviour. Re-run your test suite afterwards. This is exactly the situation the suite exists for.

​
6. Measure it, so real calls tell you what to fix

Steps 1 to 4 rely on you noticing a bad call. That does not scale past a few dozen. On the agent’s Post-Call tab, an insight is one thing you want to know about every call. Whether they agreed to a follow up. Which product they asked about. Whether the caller sounded confused.
Generated call insights listed with their type and description
Insights show on every call in Calls, can be filtered on, and can be charted over a date range in Reports. That is what closes the loop. Instead of listening to calls at random, you filter for the ones where an insight says it went wrong, and each one becomes step 1 again. See Post-call for insights, result conditions and follow up messaging.

​
What good looks like after a week

  • A test suite with more captured real failures in it than generated cases.
  • A prompt you have never edited by hand.
  • One or two insights you actually look at, rather than eight you do not.
If you take one habit from this page, take this one. When a call goes wrong, create the test before you fix the prompt. Everything else follows from it.

​
Where to go next