Ai Playbooks Best Practices
- 24 Jun 2024
- 2 Minutes to read
- Print
- DarkLight
- PDF
Ai Playbooks Best Practices
- Updated on 24 Jun 2024
- 2 Minutes to read
- Print
- DarkLight
- PDF
Article summary
Did you find this summary helpful?
Thank you for your feedback
Crafting the right goals and topics for your Ai Playbooks ensures effective evaluation and accurate analytics.
Let's go over some tips and tricks on how to create effective topics.
Name-goal relationship
The topic name and goal must be related. The topic name should summarize the goal, and the goal must explain the topic name.
Good name-goal relationship | Bad name-goal relationship |
|---|---|
Name: Customer Budget Goal: The budget the customer has allocated for this project. | Name: Step 1 Goal: The budget the customer has allocated for this project. |
Single topic pairing
A name-goal pair should focus on a single subject.
If the topic description contains more than one topic, we recommend separating them into multiple topics.
Good topic pairing | Bad topic pairing |
|---|---|
Name: Main Pain Points Goal: The most significant challenges or obstacles currently being faced. Name: Customer Budget Goal: The budget the customer has allocated for this project | Name: Main Pain Points and Budget Goal: the most significant challenges or obstacles currently being faced and customer budget |
Clear and concise
The topic name and goal should be clear, concise, and objectively measurable.
Avoid subjective or immeasurable assessments like “friendliness” or “politeness”.
If a topic name or goal is too vague, Dialpad AI will not have enough detail to detect the topic accurately in real-time, which can cause missed topics (incomplete analytics) or even Ai hallucinations.
Long topics or goals can also result in missed detections and inaccurate evaluations because the focus is too narrow. Topics should be detailed for accuracy, yet broad enough to cover various instances.
Recommended | Too vague or long |
|---|---|
Name: General Customer Satisfaction Goal: How happy the customer is with Aerolabs’ service after interacting with the company representative. Name: Expected Outcomes After Choosing Aerolabs Goal: Customer expectations and desired outcomes after migrating their shipping services to Aerolabs. Understanding these expectations can help providers smoothly facilitate the transition and ensure customer satisfaction whether the focus is enhanced packing, simpler user experience, faster shipping times, or cost efficiency. | Title: Additional Solutions Goal: Additional service options or solutions to resolve customer concerns. Name: Post-Migration Expectations Goal: Customer expectations and desired outcomes after migrating to |
Tips
An ideal topic name is 4-40 characters.
The ideal topic goal is 25-150 characters.
Avoid biases
If a topic includes gender, racial, or other group stereotypes, misinformation, or societal biases, it can cause biased or false detections by focusing on specific language patterns, leading to inaccurate and unfair results. Remember, the “questions” should assist the agent by giving them practical hints or instances.
Bias examples
“How old is the candidate?”
Using age as a topic or description can lead to biased data collection, potentially discriminating against various populations.
“What is the candidate's nationality?”
Using nationality as a topic or description can lead to data collection based on harmful stereotypes.
“What was the overall tone of the conversation?”
Tracking conversation tone through "friendliness" or "politeness" topics results in biased evaluations due to the narrow set of available linguistic patterns.
Avoid personally identifiable information
Topic titles and descriptions should not contain personally identifiable information (PII) or cause the collection of sensitive information like credit card details, social security numbers, passwords, or email and home addresses.
PII examples
“What is the candidate's complete birthday?”
“What is the candidate's address?”
“What is their CVV”
Titles shouldn't directly address agents
To keep topics consistent throughout your playbooks, avoid addressing agents directly.
Choose straightforward topic titles like "Customer's ideal price point" over phrases like "You should discuss the ideal price point".
Use the "Questions" field for agent guidance or hints.
Was this article helpful?
