Skip to main content

Bot-vs-Human Traffic Split (A/B)

Let a Chatbot Admin route only a configured percentage of incoming chats to the chatbot and auto-assign the remainder to human agents — so bot quality can be validated on real customer traffic before committing to full automation. Built by reusing the existing incoming-message routing decision (process_incoming_message_with_resolve) and the existing human auto-assignment path (SendMessageAutoAssignAgentWorker), adding a per-channel split percentage and per-conversation variant tagging for measurement.

QA Lane

Lane B — keeps a human QA gate. No Lane-B trigger is present (a bot-vs-human routing experiment), but no E2E test specs exist for this initiative yet, so the Lane-A entry bar (100% E2E, spec-mapped coverage) is unmet — Lane B by default. Classified 2026-06-29.

Phases

PhaseGoalStatusEpic
Phase 1 — Per-Conversation Split (Confluence)Per-conversation random split (X% bot / rest human) on a single channel, self-serve config, variant tagging + measurementDraftTBD
Phase 2 — Sticky Per-Customer SplitDeterministic per-unique-customer bucketing (a returning customer always gets the same arm)PlannedTBD

Contents

  • prds/ — Phase PRDs (each phase's PRD with its own ACs → Jira Epic) land here.
  • rfcs/ — Request for Comments (technical design proposals).
  • tests/ — E2E / acceptance test specs.
  • delivery/ — TPM program-management docs (timeline, status, decisions).