Skip to content

Commit fe0c3a2

Browse files
authored
fix test suite doc (#218)
* fix voice testing oc * fix voice testing oc
1 parent 23e07b7 commit fe0c3a2

File tree

1 file changed

+35
-57
lines changed

1 file changed

+35
-57
lines changed

fern/test/voice-testing.mdx

Lines changed: 35 additions & 57 deletions
Original file line numberDiff line numberDiff line change
@@ -6,38 +6,36 @@ slug: /test/voice-testing
66

77
## Overview
88

9-
Voice Testing is an end-to-end feature that automates testing of your AI voice agents. Our platform simulates a call from an AI tester that interacts with your voice agent by following a pre-defined call script. After the call, the transcript is sent to a language model (LLM) along with your success criteria. The LLM then determines if the call met the defined objectives.
9+
Voice Testing is an end-to-end feature that automates testing of your AI voice agents. Our platform simulates a call from an AI tester that interacts with your voice agent by following a pre-defined call script. After the call, the transcript is sent to a language model (LLM) along with your evaluation rubric. The LLM then determines if the call met the defined objectives.
1010

1111
## Creating a Test Suite
1212

1313
Begin by creating a Test Suite that organizes and executes multiple test cases.
1414

1515
<Steps>
1616
### Step 1: Create a New Test Suite
17-
- Navigate to the **Test** tab in your dashboard and select **Voice Testing**.
17+
- Navigate to the **Test** tab in your dashboard and select **Test Suites**.
1818
- Click the **Create Test Suite** button.
1919

2020
### Step 2: Define Test Suite Details
2121
- Enter a title for your Test Suite.
2222
- Select a phone number from your organization using the dropdown.
23+
- Make sure the phone number has an assistant assigned to it (if not, navigate to Phone Numbers tab to complete that action).
2324

2425
### Step 3: Add Test Cases
2526
- Once your Test Suite is created, you will see a table where you can add test cases.
26-
- Click **Add Test Case** to add a new test case (up to 50 can be added).
27+
- Click **Add Test** to add a new test case (up to 50 can be added).
2728

2829
### Step 4: Configure Each Test Case
29-
- **Caller Behavior:** Define how the testing agent should behave, including a detailed multi-step prompt that outlines the customer's intent, emotions, and interaction style.
30-
- **Success Criteria:** List one or more questions that an LLM will use to evaluate if the call was successful.
30+
- **Script:** Define how the testing agent should behave, including a detailed multi-step prompt to simulate how the customer should behave on the call.
31+
- **Rubric** List one or more questions that an LLM will use to evaluate if the call was successful.
3132
- **Attempts:** Choose the number of times (up to 5) the test case should be executed each time the Test Suite is run.
3233

3334
### Step 5: Run and Review Tests
3435
- Click **Run Tests** to execute all test cases one by one.
3536
- While tests are running, you will see a loading state.
3637
- Upon completion, a table displays the outcomes with check marks (success) or x-marks (failure).
37-
- Click on a test row to view detailed results: a dropdown shows each attempt, the LLM's reasoning, the transcript of the call, the defined caller behavior, and the success criteria.
38-
39-
### Step 6: Export Results
40-
- You can export the test results as a CSV file for further analysis.
38+
- Click on a test row to view detailed results: a dropdown shows each attempt, the LLM's reasoning, the transcript of the call, the defined script, and the success rubric.
4139
</Steps>
4240

4341
## Test Execution and Evaluation
@@ -51,74 +49,54 @@ When you run a Test Suite, the following steps occur:
5149
- The number of attempts made.
5250
- The LLM's reasoning for each attempt.
5351
- The complete call transcript.
54-
- The configured caller behavior and success criteria.
55-
- **CSV Export:** Results can be exported for additional review or compliance purposes.
52+
- The configured script and rubric.
5653

5754
## Example Test Cases
5855

59-
Below are three example test cases to illustrate how you can configure detailed caller behavior and success criteria.
56+
Below are three example test cases to illustrate how you can configure detailed simulation scripts and evaluation rubrics.
6057

61-
### Example 1: Account Inquiry
58+
### Example 1: Billing Support
6259

63-
**Caller Behavior:**
64-
Simulate a customer inquiring about their account status with growing concern as unexplained charges appear in their statement.
60+
**Script:**
61+
```md title="Script" wordWrap
62+
1. Express anger over an unexpected charge and the current bill appearing unusually high.
63+
2. Try to get a detailed explanation, confirming whether an overcharge occurred, and understanding the steps for resolution.
64+
3. End the call.
65+
```
6566

66-
**Example Prompt:**
67-
```md title="Example Prompt" wordWrap
68-
[Identity]
69-
You are a long-time bank customer with a keen eye for your financial details.
67+
**Rubric:**
68+
```md title="Rubric" wordWrap
69+
The voice agent acknowledges the billing discrepancy respectfully without dismissing the concern.
70+
```
7071

71-
[Personality]
72-
Normally calm and polite, you become increasingly anxious when you notice discrepancies on your account statement. Your tone shifts from supportive to urgent as the conversation progresses.
72+
### Example 2: Account Inquiry
73+
74+
Unlike in the previous example, this time we will provide a more free-form script for the test agent to follow.
75+
76+
**Script:**
77+
```md title="Script" wordWrap
78+
Simulate a customer inquiring about their account status with growing concern as unexplained charges appear in their statement.
7379

74-
[Goals]
7580
Your primary objective is to clarify several unexplained charges by requesting a detailed breakdown of your recent transactions and ensuring your account balance is accurate.
7681

77-
[Interaction Style]
7882
Begin the call by stating your name and expressing concern over unexpected charges. Ask straightforward questions and press for more details if the explanation is not satisfactory.
7983
```
8084

81-
**Success Criteria:**
82-
```md title="Success Criteria" wordWrap
85+
**Rubric:**
86+
```md title="Rubric" wordWrap
8387
1. The voice agent clearly presents the current account balance.
8488
2. The voice agent provides a detailed breakdown of recent transactions.
8589
3. The response addresses the customer's concerns in a calm and informative manner.
8690
```
8791

88-
### Example 2: Billing Support
89-
90-
**Caller Behavior:**
91-
Simulate a customer who is frustrated and calling about a billing discrepancy.
92-
93-
**Example Prompt:**
94-
```txt title="Example Prompt" wordWrap
95-
[Identity]
96-
You are a loyal customer who has always trusted the billing process, but the current bill appears unusually high.
97-
98-
[Personality]
99-
Frustrated and assertive, you express anger over an unexpected charge while remaining focused on obtaining clarification.
100-
101-
[Goals]
102-
Your goal is to understand the discrepancy in your bill by obtaining a detailed explanation, confirming whether an overcharge occurred, and understanding the steps for resolution.
103-
104-
[Interaction Style]
105-
Start the call by clearly stating your billing concern, describing the specific overcharge, and requesting a comprehensive explanation with resolution options.
106-
```
107-
108-
**Success Criteria:**
109-
```md title="Success Criteria" wordWrap
110-
1. The voice agent acknowledges the billing discrepancy respectfully without dismissing the concern.
111-
2. The agent provides a clear explanation of the charges, detailing possible reasons for the discrepancy.
112-
3. The conversation concludes with a proposed solution or a clear escalation plan to address the overcharge.
113-
```
114-
11592
### Example 3: Appointment Scheduling
11693

117-
**Caller Behavior:**
94+
This time, we will spin up an even more detailed personality for the test agent. By showing these varied styles of scripts, we hope to show the flexibility of the Voice Testing feature and how you can use it to meet your testing needs.
95+
96+
**Script:**
97+
```md title="Script" wordWrap
11898
Simulate a customer trying to schedule an appointment with a hint of urgency due to previous delays.
11999

120-
**Example Prompt:**
121-
```md title="Example Prompt" wordWrap
122100
[Identity]
123101
You are an organized customer who values efficiency and punctuality.
124102

@@ -132,8 +110,8 @@ Your goal is to secure an appointment at your preferred time, while remaining fl
132110
Begin the call by stating your need for an appointment, specifying a preferred date and time (e.g., next Monday at 3 PM). Request clear confirmation of your slot, and if unavailable, ask for suitable alternatives.
133111
```
134112

135-
**Success Criteria:**
136-
```md title="Success Criteria" wordWrap
113+
**Rubric:**
114+
```md title="Rubric" wordWrap
137115
1. The voice agent confirms the requested appointment time clearly and accurately.
138116
2. The agent reiterates the appointment details to ensure clarity.
139117
3. The scheduling process ends with a definitive confirmation message of the booked appointment.

0 commit comments

Comments
 (0)