AI Knowledge & LogicAI Analytics & Insights

Data Collection

How to use AI-powered data collection to automatically extract structured insights from every conversation — product issues, cancellation reasons, customer behavior, bot performance, and more.

Every conversation contains valuable information — why a customer is unhappy, what product they're interested in, whether the bot handled the issue well, how long the team took to respond. Data Collection lets you automatically extract this information and turn it into structured, reportable data.

You define the questions. The AI reads every conversation and answers them for you.

This isn't a simple tagging system. The prompt field accepts natural language instructions — the same frontier AI models that power your bot will interpret them. This means you can extract almost anything: product defects, cancellation reasons, customer sentiment, SLA compliance, purchasing power, language, retention outcomes, security concerns, and patterns you haven't thought of yet.


How to think about data collection

The core idea is simple: each data collection field is an AI prompt that runs against the full conversation after it closes. You tell the AI what to look for, give it the possible values, and it classifies every conversation automatically.

This makes data collection extremely flexible. It's not limited to what the customer said — the AI can analyze the entire interaction, including how the bot or agent responded. Some examples of what this enables:

  • What happened — What product issue did the customer report? What was the cancellation reason?
  • What the customer wanted — Were they looking for a refund? A specific product category? A payment link?
  • How it was resolved — Was the subscription saved? Did the agent respond within SLA? Did the bot offer the right solution?
  • Who the customer is — What language do they speak? What's their budget range? Are they a first-time buyer?
  • How the bot performed — Did the bot offer partial refunds when it shouldn't have? Did it leak another customer's data?

Think of each field as a question you'd want answered about every conversation — then let the AI answer it at scale.


Setting up data collection fields

Create and manage data fields in Settings → AI & Automation → Data Collection.

Each field has three settings:

SettingWhat it does
NameHow the field appears in analytics. Choose something clear and descriptive.
PromptNatural language instructions that tell the AI what to look for and how to classify it. This is where the power is — see writing good prompts below.
Possible valuesThe specific values the AI can assign. Can be detailed categories, simple Yes/No, or anything in between.
Optional fieldWhen enabled, the AI only assigns a value if it finds relevant information. (Recommended for most fields — many won't apply to every conversation.)


How it works

After a conversation is closed, resolved, or handed off, the AI:

  1. Reviews the full conversation — every message from the customer, bot, and agents
  2. Evaluates each data collection field against the conversation
    • Required fields are always classified
    • Optional fields are only classified when the conversation contains relevant information
  3. Assigns the most appropriate value for each field
  4. Saves the results for reporting, filtering, and analysis

Writing good prompts

The prompt is the most important part of a data collection field. It tells the AI what to look for and how to decide between values. The AI is capable of following nuanced, multi-step logic — don't be afraid to write detailed instructions.

Be specific about when to classify

The most common mistake is not telling the AI when to skip classification. If a field only applies to certain conversations, say so explicitly:

"This categorization should only be performed if the customer has requested a subscription cancellation. If no subscription cancellation was requested, output null."

"If the customer is not reporting a technical issue, don't output a value."

Without this guidance, the AI may force-fit a value to conversations where the field doesn't apply.

Tell the AI how to handle edge cases

Good prompts anticipate ambiguity:

"If no reason was provided, output 'No reason provided'. If none of the cancellation reasons match, output 'Other'."

"If the concern does not match any known values, classify as 'Others'. If the conversation is not product-related, leave blank."

You can analyze bot and agent behavior, not just customer messages

The AI reads the full conversation — including bot responses and agent replies. This means you can use data collection to monitor your own team's performance and the bot's behavior:

"Return 'Yes' if the bot offered partial refunds, otherwise output 'No'."

"Calculate the time between the handoff and the first agent response. Within 4 hours = 'Within SLA'. Greater than 4 hours = 'SLA Violated'."

"If the bot provided information of the wrong person and the customer complained about it, output 'Yes'. Otherwise, output 'No'."

Complex logic works

The AI can follow multi-step reasoning. You can combine multiple conditions into a single field:

"Q1: Did the customer ask for money back? Q2: Did the customer ask to cancel their subscription? Q3: What was the outcome? Classify as 'SS Saved' if subscription was retained, 'Refund Saved' if refund was avoided, or the appropriate combination. IMPORTANT: A subscription being cancelled is NOT a 'refund not saved'."


Use case ideas

Data collection is underutilized by most businesses. Here are concrete ways to extract value from conversations you're already having.

Product and service issues

The most common use case — classify what went wrong so you can spot trends and fix root causes.

Field nameWhat to trackExample values
Product issuesThe specific defect or complaint the customer reportsDamaged, Defect, Missing Items, Not as Advertised, Wrong Size, Adverse Reaction, Others
Packaging issuesWhether the product arrived in poor conditionBroken seal, Damaged container, Missing parts, Leaks
Delivery problemsWhat went wrong with shippingDelay, Lost shipment, Damaged on arrival

Tailor the possible values to your specific products. A knife brand tracks "Bent Blade, Blunt Blade, Broken Tip, Chipped Blade, Rust, Loose Handle." A pillow brand tracks "Flat Pillow, Odor/Smell, Cover Size, Damaged Zipper." The more specific your values, the more actionable your data.

Cancellation and retention

Understand why customers leave — and whether your retention efforts work.

Field nameWhat to trackExample values
Cancellation reasonWhy the customer wants to cancel their subscriptionToo expensive, Not using the service, Didn't meet expectations, Technical issues, Personal reasons, No reason provided
Cancellation outcomeWhether the customer was retainedCancelled, Paused, Customer changed their mind
Retention outcomeWhether a refund or subscription cancellation was preventedSubscription Saved, Subscription Not Saved, Refund Saved, Refund Not Saved
Return reasonWhy the customer is returning a productAllergic reaction, Bad quality, Better alternative, Damaged, Financial reasons, No results, Too much product

Customer insights

Learn about who your customers are and what they want.

Field nameWhat to trackExample values
LanguageWhat language the customer communicates inEnglish, Spanish, French, German, Portuguese, Italian
Purchasing powerThe customer's stated budget rangeUnder $10k, $10k-$20k, $20k-$40k, $40k+
Product interestWhat type of product the customer is looking forComputers, Individual components, Protein powder, Multivitamin
Customer satisfactionHow the customer felt after receiving adviceVery satisfied, Neutral, Not satisfied

Operational quality

Monitor how your team and bot perform — without manual QA.

Field nameWhat to trackExample values
First response SLATime between handoff and first agent responseWithin SLA, SLA Violated
Next response SLATime between conversation reopen and next agent replyWithin SLA, SLA Violated
Bot behavior auditWhether the bot did something it shouldn't haveOffered partial refund, Leaked customer data, Behaved correctly
Troubleshooting outcomeWhich step resolved the customer's technical issueRestart device, Factory reset, APN change, Not resolved
Technical issue solutionWhat solution the agent proposedNo data left, Device is defective, Restore network settings, Other

Payment and order status

Track operational patterns in how customers interact with orders.

Field nameWhat to trackExample values
Payment issuesWhether the customer had trouble payingPayment problem, No problem
Order statusCurrent state of the customer's orderIn preparation, In transit, Delivered, Returned, Cancelled
Package opened on returnWhether the customer opened the package before returningYes, No
Payment method providedWhether the customer shared bank detailsYes, No

Security and compliance

Catch concerning behavior automatically.

Field nameWhat to trackExample values
Bad intent detectionWhether the customer is trying to exploit the botAttempting to steal information, Trying to break security
Data leak detectionWhether the bot accidentally shared another customer's dataYes, No
Refund threat trackingWhat leverage the customer used to demand a refundDispute/Chargeback, Scam accusation, Report to authorities, Bad review

Analytics

Insights are available in Metrics → Data Collection.

You can:

  • See how often each value appears across all conversations
  • Compare trends by channel, product, or time period
  • Spot rising issues early (e.g., "packaging leaks" spiking this month)
  • Filter conversations by any collected field for deeper analysis
  • Combine multiple fields to find patterns (e.g., cancellation reason and retention outcome)

This turns raw conversations into clear, structured data you can use to improve products, operations, and customer experience.


Examples

On this page