Conversation Listeners
Opt-in listeners that capture conversations from every channel an organization uses — support, email, team chat, customer messaging, webchat, sales tools, voice — and route them into the signal-extraction pipeline with consent and retention rules attached.
Production AI is not a prompt. It is a system of context, tools, permissions, traces, evals, and feedback loops.
How they are built
Each listener runs with the minimum scope required: read access to specified channels, no message-write capability unless a workflow explicitly needs it, no DMs unless a user has opted in. Captured messages are written to a dedicated table governed by Data Foundations with a configured retention window. PII handling is declared per source.
- Minimum-scope tokens per channel
- Explicit retention window per source
- PII redaction rules declared per listener
- User-visible off-switch and audit log
Channels we typically support
Support platforms via webhook or API (Zendesk, Front, Intercom, Help Scout, Salesforce Service Cloud); email inboxes via Gmail API, Microsoft Graph, or IMAP; team chat via platform APIs (Slack, Microsoft Teams, Discord); customer messaging via the WhatsApp Business Platform, Telegram Bot API, SMS providers (Twilio, MessageBird), Messenger, and Apple Messages for Business; webchat and in-app widgets via SDK hooks; sales tools via CRM activity logs (HubSpot, Salesforce, Pipedrive); voice transcripts from call platforms (Twilio, Aircall, Five9, Genesys, Dialpad). New channels are added as MCP-compatible listeners; the same governance, retention, and consent rules apply regardless of source.
Consent and the off-switch
Channel onboarding is permissioned and reversible. Users are told the listener exists, what it captures, how long it keeps data, and how to opt out — and the consent flow is tailored per channel (a Slack workspace announcement, a customer-facing notice in webchat, an opt-in keyword on SMS or WhatsApp, an email footer disclosure). The off-switch is a real switch — disabling the listener stops capture immediately and the retention clock starts on what was already collected.
Related resources
Turning every approved conversation — support, email, team chat, customer messaging, voice, sales — into structured signal you can act on, instead of anecdotes that evaporate when a ticket closes.
Turning raw conversation transcripts into structured fields — intent, subject, sentiment, CSAT, tool performance, product mentions — that downstream systems can query, dashboard, and act on.
The policy layer for what an AI system is allowed to read, call, decide, and ship — encoded as configuration the runtime enforces, not as a document on a shared drive.