Skip to content
Conversational Analytics

Clicks whisper.
Prompts yell.

Clickstream tells you where users went. It can't tell you what they were trying to do. Every prompt is signal. Unresolved intents write your roadmap.

Works on top of the Product Agent.

Analytics Success Launched on June 1st, 2026 + Add Widget
Conversations 1
Last 30 days 671 ↑ +44.3%
User Messages 1
Last 30 days 1,037 ↑ +45%
Action Calls 1
Last 30 days 1,981 ↑ +111%
User Intent 1
Last 30 days↑ +44.7% signals
Action Request52981.3%
Information Request8813.5%
Reported Issue345.2%
User Sentiment 1
Last 30 days · 669 conversations±0.0pp
95.2% Good or better · 637 of 669
Negative 32Good 621Great 16
Resolution Rate 1
76.5% Resolved · 512 of 669 ↑ +4.2pp
Resolved 512Unresolved 119Escalated 38

The dashboard: intent, resolution, and sentiment from every agent conversation.

The why behind the what.

01

Know what users want

Every prompt is stated intent — demand in your users' own words, classified and ranked. Not inferred from clicks.

02

Know if you delivered

Resolution, sentiment, and gaps for every conversation. See where the product wins today, and what to build next.

03

Know what it costs

Token spend by model, by action, down to the user. Control the economics of every answer.

No black box: every metric drills down to the actual conversations behind it.

"Tapping into intent data changed how we prioritize. We know exactly what users want in every conversation — and instantly close the loop with agentic experiences."
Jakub Tutaj, Product Growth & Monetization, Mixmax

Understand agentic experience usage.

Usage, tokens, and cost for every action the agent takes — the same analytics you run on features, now on agentic workflows.

Analytics Agentic usage & cost Add description... Close Save As Update
Events or Metrics +
AUnique Conversations of Action CalledConversation Sum of Action Called
Conversation ⌄Unique ⌄Sum of Estimated cost ⌄
+ Filter on this Metric
BTotal Tokens of Action Called
CCost of Action Called
Report Filter applies to every metric
+ Add report-level filter
Breakdown +
Action key
Apply
Last 30 days Daily ⌄ Line ⌄
Asearch_knowledgeAask_questionAcreate_projectAconsult_navigation_agentAnavigateAadd_sketch_labelingAadd_project_estimateAget_project_id
Jun 30Jul 4Jul 8Jul 12Jul 16Jul 20Jul 24Jul 28
Average Total Tokens Cost Sun, Jun 28 Mon, Jun 29 Tue, Jun 30
Asearch_knowledge 25.1$1.02 754$30.60 1.2M $30.60 31$1.73 36$1.91 23$1.20
Aask_question 7.8$0.26 233$6.90 410K $6.90 19$1.03 20$0.99 9$0.44
Acreate_project 7.3$0.08 220$1.44 388K $1.44 4$0.09 7$0.13 2$0.01
Aconsult_navigation_age… 6.9$0.35 206$5.20 352K $5.20 9$0.69 8$0.94 6$0.45
Anavigate 3.2$0.08 97$1.96 92K $1.96 0$0 1$0.08 1$0.08
Aadd_sketch_labeling 3.1$0.08 94$1.35 88K $1.35 3$0.08 3$0.11 0$0

Read the demand. Build what's next.

“How do I share this dashboard?”How-to
“Create the Q3 pipeline report”Create report
“Why did my sync fail?”Troubleshoot

Analyze conversations

Read what users actually ask the Agent, classified by User Intent and broken down by segment or use case.

User sentiment
3 conversations turned negative

Catch frustration early

User Sentiment flags the conversations that turned negative, so you see where users struggle before they give up.

Agent adoption by segment
Enterprise78%
Pro54%
Free22%

Grow agent adoption

Know exactly who's using the agent and who isn't, with Audiences and Segments by plan, account, or activity.

Weekly active users ↑ 12%

See if it sticks

Active-user and retention trends show whether the agent keeps users coming back, or catch the early signs it doesn't.

Agent Gap
Bulk edit tags 214 asksBuild
SSO setup guide 96 asksDocument
Export to PDF 61 asksBuild

Find your next feature

Agent Gap turns every request the product couldn't serve yet into ranked demand for net-new capability — split into what to build and what to document.

86%resolved
Session replay

Increase user success

See which conversations resolved, replay the ones that didn't with Session Replay, and fix what's breaking.

Usage by account
Acme Corp82%
Initech64%
GlobexAt risk

Track account adoption

Segment agent usage by account to spot adoption gaps before they widen.

Time to outcome
“Create the Q3 pipeline report”
Agent path
Ask Done
Navigation path
Find the screen Configure Filter Export Done

Prove the faster path

Same job, two ways to do it. Compare time-to-outcome when users ask the agent against the traditional UI path, measured end to end on your own product. It's the modernization case, made with your own data.

#2841 · Export failedUnresolved
#2847 · Billing questionEscalated
#2852 · Sync timeoutUnresolved

Catch and report issues

Unresolved and Escalated conversations get flagged automatically, and Session Replay shows what went wrong.

The Economics

Every token, accounted for.

Every answer your agent gives has a price. Conversational Analytics shows you exactly where the spend goes — and gives you the levers to control it.

Spend by model
claude-sonnet-5$12.40
1.8M tokens · $0.021 per conversation
claude-opus-5$4.20
0.3M tokens · $0.045 per conversation
claude-haiku-4-5$1.90
2.6M tokens · $0.004 per conversation

Cost by model

See token consumption and spend per model across every conversation. Route simple work to cheaper models in Studio, and watch the same job cost less.

Calls vs. cost
ActionCallsCost
search_knowledge754$3.10
generate_report212$18.60
navigate97$0.40

Called most vs. costs most

Two rankings of your actions and tools: the ones users trigger constantly, and the ones that burn the budget. They're rarely the same list — and that's where the optimization lives.

Cost by account
AccountConvResCost
Acme Corp21488%$41
Initech12682%$28
Globex3861%$96

Down to the user

Cost per user and per account, next to the value they got. Spot the outliers before the invoice does, and know exactly which accounts your agent spend is serving.

Ready to see Conversational Analytics in action?

Book a live walkthrough and see real conversations turned into intent, resolution, and gap signals.

Get a demo

What teams do with intent data.

Ranked by demand
1Bulk edit tags 214 asks→ Roadmap
2API export 156 asks
3Custom roles 98 asks
Build what users ask for

Decide what to build next

Action Gaps and Feature Requests rank real demand for capabilities that don't exist yet — new value users are literally asking for, so the roadmap follows evidence, not opinion.

Reported issues
Rising — act this week
Catch problems early

Spot friction before it spreads

A rising Reported Issue line or falling Resolution Rate is an early warning you can act on this week.

High-value use cases
Pipeline reports High intentExpansion
Forecast exports High intentUpsell
Deal alerts GrowingMonitor
Grow the account

Increase revenue

Find the high-intent use cases users succeed at and double down — new experiences, new workflows, new value that drives adoption and expansion.

Conversational Analytics provides the signal. Your team decides what to do with it.

Stop guessing. Start reading intent.

Your users are telling you exactly what to build next and where to win. This is how you hear it.