← Back
Agents Case Study · 02 Published March 2026

Centralized Qualitative Insights Agent, @voc-agent

A Notion AI agent that synthesizes customer signal across Zendesk, Canny, Outreach Kaia, Slack, and Notion in one place, with citations back to the original quote, available in Notion and via a dedicated Slack channel.

TL;DR

Built the VoC Agent, a Notion AI agent that synthesises qualitative customer signal across Zendesk, Canny, Outreach Kaia transcripts, Slack, and public Notion pages in one place. Product, Operations, and Research teams can ask on-demand questions about feature requests, support trends, churn risks, and customer sentiment, and the agent connects the dots across sources to surface patterns, with citations back to the original quote. Available directly in Notion and via the dedicated #voc-agent Slack channel.


The Problem

Customer signal at Phorest is rich but scattered. Product talks to Zendesk for support trends, Canny for feature requests, Outreach Kaia for sales-call objections, and Slack for the daily drumbeat, and each team ends up rebuilding the same ingest, filter, and summarise pipeline by hand.


The Solution: One Agent, Five Sources

A single Notion AI agent with two modes, discovery (natural-language Q&A) and reporting (scheduled monthly synthesis), backed by five governed data sources.

Connected sources

SourceWhat it coversHow it's connected
ZendeskSupport tickets, escalations, recurring issuesNotion connector
CannyPublic feature requests, vote counts, comment threadsNotion connector
Outreach Kaia~2,099 calls / 18 monthsCustom MCP server (in-house) wrapping the Kaia recording API
SlackProduct, churn-risk, beta-feedback, competitive channelsNotion ↔ Slack integration (incl. private channels)
NotionAll public-facing Phorest pages, research, discovery, releasesNative

Two modes of use

  1. Discovery mode, instructions tuned for back-and-forth Q&A. Used by Product, Research, and CS leadership to interrogate themes, pull quotes, stress-test hypotheses.
  2. Reporting mode, instructions tuned to generate a fixed monthly report template covering top feature requests, support trends, churn signals, production issues, broken down by team / region / vertical.

Distribution


Key Challenges

Getting access to Kaia

Outreach's commercial model made direct Kaia access expensive and slow. We bypassed it by building our own MCP server against the public Kaia recording API, exporting 18 months of transcripts directly. Same end result, no per-user licence cost.

Splitting one agent into two modes

The original VoC agent was instructed as a report generator. When PMs started asking it ad-hoc questions in Slack, the answers came back stiff and report-shaped. Solution: refactor instructions so the same agent supports both report generation and discovery Q&A, picking up the right behaviour from the prompt.

Volume vs. context window

The agent can't load 2,099 transcripts into a single context. For deep 18-month analysis we ran a one-off batch export offline; for ongoing use the agent queries shorter periods or specific accounts on demand.

Trust and provenance

Every claim the agent makes is auditable back to the original Zendesk ticket, Canny post, Slack message, or transcript timestamp. The agent always cites, no synthesis without a source.


What the Agent Can Do

CapabilityExample question
Cross-source theme synthesis"What are clients saying about Phorest Pay this month?"
Feature-request trend tracking"Top feature requests not on our roadmap in the last 30 days"
Quote retrieval"Pull a client quote for each support theme this week"
Churn signal surfacing"Which accounts have shown churn risk language in the last 60 days?"
Beta feedback rollup"What is beta feedback saying about WhatsApp and AI features?"
Monthly report generationScheduled VoC report, themes, asks, churn signals, production issues
Region / vertical filtering"Top medspa requests in UK & Ireland over the last quarter"

What We Learned


Tech Stack