Who this comparison is for
Chat Core highlights
- Omnichannel session manager + auditable handoff contracts
- Pipeline: detect → enrich → decide → act → learn with plug-in nodes
- Event bus (webhooks, SSE, EventBridge/Kafka) and InsightLake metrics
Google Dialogflow CX highlights
- Graph-based dialog builder with NLU intents and flows
- Native telephony/voicebot tooling in GCP
Capability matrix
Capability | Chat Core | Google Dialogflow CX | Notes |
---|---|---|---|
Durable session orchestration (multi-channel) | Native | Partial | CX sessions per agent/bot; cross-system stitching via custom work |
Deterministic bot→human handoff (SLAs/queues) | Native | Partial | Requires external contact center or custom glue |
Multi-bot routing (LLM/CX/Rasa/flows) | Native | Partial | Router/skills vs intent handoff patterns |
Guardrails (moderation, DLP, prompt firewall) | Native | Partial | GCP moderation available; orchestration-wide policies in Chat Core |
Event streaming (SSE/Kafka/Webhooks) | Native | Partial | Pub/Sub oriented; externalization needed for UI/workflows |
Agent desk integration (queues/macros/SLA) | Native | Add-on | Chat Core → LiveConnect/Agent Desk vs adapters to CCaaS |
A/B routing & cost controls | Native | Partial | Experiments across models/routes vs flow comparisons |
- Matrix tokens: full/partial/none/native/addon/self_hosted/config-dependent.
- Dialogflow CX excels at bot design; Chat Core focuses on cross-bot orchestration, governance, and handoff.
Total cost of ownership
Teams keep CX for dialog design while lowering glue-code by letting Chat Core own sessions, routing, safety, and handoff. This reduces custom middleware and speeds rollout across channels.
Assumptions
- 3 bots (CX/LLM mix), 5 channels, 50k sessions/mo
- Existing GCP footprint; need human handoff + governance
Migration plan
From Dialogflow CX · Keep CX bots; place Chat Core in front for orchestration & handoff
-
1
Register CX as an Actor in the Chat Core pipeline (tool/function call)
-
2
Configure routing rules and confidence bands; define handoff queues
-
3
Enable webhooks/SSE for inbox UIs; turn on guardrails & cost limits
Security
- Region-pinned storage, RBAC, audit trails, DLP redaction
- HMAC webhooks and idempotent intake
Evidence & sources
Claim | Value | Source |
---|---|---|
Handoff contracts | Reason, macros, do/don’t, tool blocklist |
product_docs
Auditable and reversible
|
Event bus options | Webhooks, SSE, EventBridge/Kafka |
product_docs
CloudEvents JSON
|
About Chat Core
Chat Core decides what happens next in any live conversation. It stitches identity across channels, maintains durable sessions, detects intent and sentiment, calls tools and knowledge bases, and chooses between automated replies or human handoff with clear SLAs. Operators get routing/skills rules, cost & safety guardrails, experiments, and an orchestration trace for explainability.
Tightly integrated with PulseGate for transport, LiveConnect for real-time inbox, Agent Desk for tickets, FlowForge for automation, Chronicle for audit-ready timelines, and InsightLake for analytics—so you can ship omnichannel support that scales safely.