Help

Onboarding Deep Dive Analytics And Ongoing Improvement

Airgentic Help

Deep-Dive: Analytics and Ongoing Improvement

This module covers how to use Airgentic's analytics to understand performance and continuously improve your service. Read this when you want to move beyond basic operation into data-driven optimisation.


Who this is for

  • Content owners who monitor service quality
  • Managers who report on performance
  • Platform administrators who drive improvement
  • Anyone responsible for service outcomes

What you'll learn

  • How to interpret Customer Service Insights
  • How to use Search Insights to identify gaps
  • Key metrics to track
  • How to turn data into action
  • Building a continuous improvement cycle

Customer Service Insights

Overview

Customer Service Insights shows how conversations are performing:

Section What it tells you
Summary Stats High-level counts: total outcomes, fully answered, partially answered, unanswered
Answer Completeness Proportion of conversations in each completeness category
Expert Agents How conversations are distributed across agents
User Feedback Positive vs negative ratings
Non-Neutral Sentiment Emotional tone of conversations
Products Mentioned Which products generate questions
Top Citation URLs Which content pages are used most

Key questions to ask

Are users getting answers?
- Check answer completeness — what percentage are fully answered?
- Unanswered and partially answered conversations indicate problems

Are users satisfied?
- Check user feedback — what's the positive/negative ratio?
- Check sentiment — are conversations trending positive or negative?

What's driving volume?
- Check products mentioned — which products generate the most questions?
- Check top citations — which content is working hardest?

Using filters

Filters let you drill into specific subsets:

Filter When to use it
Date range Compare periods, track trends
Answer Completeness Focus on problem conversations
Website Separate deployments or sections
User Rating Find dissatisfied users
Sentiment Identify emotional conversations
Needs Review Prioritise flagged items

Related: Customer Service Insights


Search Insights

Overview

Search Insights shows how users search and what they find:

Section What it tells you
All Searches Chronological log of every search
Top Search Queries Most frequently searched terms
Top Clicked Results Most frequently clicked pages
Timeline Search and click trends over time
Locations Geographic distribution of searchers

Key questions to ask

What do users want to find?
- Check top search queries — what are users looking for?
- Are these topics well-covered in your content?

Are users finding what they need?
- Check top clicked results — which content is working?
- Compare search volume to click volume — large gaps indicate problems

What's missing?
- Look for high-volume searches with low clicks
- Look for searches that don't match your content terminology

Related: Search Insights


Key metrics to track

Answer quality metrics

Metric Target What low scores indicate
Fully Answered % High (70%+) Content gaps, prompt issues, poor search
Unanswered % Low (<10%) Missing content, questions outside scope
Partial Answer % Monitor May be acceptable or need investigation

Satisfaction metrics

Metric Target What to look for
Positive ratings High Indicates users are satisfied
Negative ratings Low Each one is worth investigating
Negative sentiment Low May indicate frustrated users

Operational metrics

Metric What it indicates
Conversation volume Demand for the service
Questions by agent Which agents are working hardest
Needs attention count Workload for human review
Usage vs allowance Capacity and planning

Turning data into action

Diagnosing problems

High unanswered rate:
1. Review unanswered conversations — what topics come up?
2. Check if content exists for those topics
3. If yes → Check search configuration, prompts, categorisation
4. If no → Create content or add curated answers

High negative ratings:
1. Review conversations with negative ratings
2. Look for patterns — same topic, same agent, same type of error?
3. Address root cause (content, prompt, search, or legitimate limitation)

High escalation requests:
1. Review conversations where users asked for humans
2. Was the AI handling it poorly, or do users just prefer humans?
3. If AI issue → Fix the underlying problem
4. If preference → Consider whether AI-only is appropriate for this service

Improvement actions

Finding Action
Users ask about topics not in content Add content or curated answers
AI gives wrong answers for specific questions Add curated answers
Search returns irrelevant results Adjust search settings, synonyms, or boosts
Users phrase things differently than content Add synonym rules
AI tone is wrong for certain situations Refine prompts
Certain agent routing is broken Adjust agent role descriptions

Prioritisation

Not everything needs immediate action:

Priority Criteria
High High volume + negative outcome + fixable
Medium Moderate volume + clear fix
Low Low volume or unclear fix
Watch May not need action, just monitoring

Focus energy where it will have the most impact.


Building a continuous improvement cycle

Weekly review

Spend 30-60 minutes weekly:

  1. Check summary stats — Any significant changes from last week?
  2. Review flagged conversations — What caused the flags?
  3. Look at top issues — Are there patterns?
  4. Take action — Add curated answers, note content gaps, adjust settings
  5. Track what you changed — So you can measure impact

Monthly review

Spend 1-2 hours monthly:

  1. Review trends — Is answer quality improving?
  2. Check search performance — Any new gaps?
  3. Review usage — Are you within allowances?
  4. Report to stakeholders — Key metrics and improvements made
  5. Plan next month — What larger improvements should you tackle?

Quarterly review

Spend a few hours quarterly:

  1. Assess overall performance — Are you meeting goals?
  2. Review content strategy — Does your knowledge base need major updates?
  3. Consider new capabilities — Should you add agents, functions, voice?
  4. Plan significant changes — What requires coordination or Airgentic support?

Reporting to stakeholders

What managers typically want to know

  • How many conversations is the AI handling?
  • How well is it answering?
  • Are users satisfied?
  • What's the trend over time?
  • What are we doing to improve?

Suggested dashboard

Metric Time period
Total conversations Monthly
Fully answered % Monthly
Positive rating % Monthly
Top 5 topics Monthly
Key improvements made Monthly

Export data from Insights for analysis in spreadsheets or BI tools.


Common improvement patterns

Content-driven improvement

Problem: AI can't answer common questions
Solution: Add content to your website, then sync
Measure: Unanswered rate for those topics

Curated answer improvement

Problem: AI answers incorrectly or inconsistently
Solution: Add curated answers for specific intents
Measure: Negative ratings for those questions

Search improvement

Problem: Users search for terms not in your content
Solution: Add synonym rules
Measure: Search click-through rates

Prompt improvement

Problem: AI tone or behaviour is wrong
Solution: Refine prompts
Measure: Sentiment and ratings for affected conversations


Avoiding common mistakes

Chasing every negative

Not every negative rating is actionable. Some users are frustrated before they arrive. Focus on patterns, not isolated cases.

Changing too much at once

Make incremental changes so you can measure impact. If you change everything, you won't know what worked.

Ignoring the data

It's easy to assume things are fine. Regular review catches problems before they accumulate.

Fixing symptoms not causes

A curated answer is a quick fix, but if the underlying content is wrong, fix the content. Curated answers should be exceptions, not the primary solution.



Back to: Optional Deep-Dives

You have unsaved changes