Dashboard modules
Your dashboard is organized as eight focused modules. Each one answers a single operational question. This page describes what you see and the typical workflow.
Tip
Insights & reliability
The pulse of your support on a single page: conversation volume, first response time (median and p90), average quality score, share of negative sentiment, top demanding customers, SLA compliance and agent load distribution.
The reliability tile shows the correlation between the AI score we assign and the actual CSAT ratings your customers leave. Above 0.7 means our score is a trustworthy proxy when CSAT is missing.
Quality scoring
Every reply, human or Fin Agent, is scored from 0 to 100 on four criteria:
- Relevance — does the reply address what the customer actually asked?
- Accuracy — is the information correct against your docs and product?
- Tone— does it match your brand voice and the customer's emotion?
- Completeness — does it fully resolve the question or leave gaps?
The module surfaces the worst-scoring replies with the reasons. Your team can validate or correct the score, which calibrates the AI over time.
Documentation gaps
A gap is a topic that drives meaningful support volume but has no dedicated article in your Help Center. ResponZ ranks gaps by impact (volume × negative sentiment × deflection potential) and suggests which articles to write first.
Top questions
Conversations grouped by theme using automatic clustering. For each cluster you see volume, dominant sentiment, sample conversations and evolution over the last 90 days. You can exclude off-topic clusters to keep the view sharp.
Trends & releases
Support volume and quality plotted over time, with vertical markers for your GitHub releases (merges to main / prod). Click a release marker to get the before/after delta on volume, score and sentiment.
Engagement
Performance of your outbound Intercom campaigns (surveys, emails, series). Full funnel: received → opened → clicked → converted, with unsubscribe and reply rates per campaign.
Targets & churn risk
Set targets per KPI (CSAT, average quality score, FRT, containment, reopen rate) and track the gap. The churn risk table ranks accounts by a composite score combining negative sentiment, reopens and trend. Hand it to your Account Management team weekly.
Sprint board
A lightweight kanban (To Do, In Progress, In Review, Done) to turn insights into action: write an article from a detected gap, brief an agent on a low-scoring reply pattern, fix a Fin Agent workflow. Filterable by swimlane and priority.