Facebook organic/community layer.
Detects relevant commercial intent from engagement.
An agentic growth and revenue system.
Social engagement and inbound questions often contain sales intent, but manual qualification is inconsistent and difficult to scale.
Facebook engagement → Wira FB → sales-intent detection → Pemburu → qualification → scoring → Duta handoff
Detects relevant commercial intent from engagement.
Extracts structured context, qualifies, scores and recommends next action.
Receives qualified handoffs for relationship management.
Note: Agent roles are distinct from the underlying automation infrastructure.
HOT / WARM / COLD / SPAM
The system evaluates intent, fit, urgency, and authority signals. It uses BANT-style qualification where evidence exists in the conversation.
Unknown information remains UNKNOWN. The system must not invent budget or authority if it wasn't provided.
Validates HOT / WARM / COLD / SPAM classification.
The system reliably maps conversations to a structured lead schema, executing BANT-style qualification and product/service matching.
Produces qualified-lead handoff tickets, demonstrating zero-silent-drop recovery behavior via DLQ.
Validates the core routing layer that manages AI model execution.
Centralized model routing abstracts the LLM provider from the core logic.
Latency, model choices, and usage tracking are built into the pipeline.
A deterministic local engine steps in if external AI is unavailable.
Failed lead events are preserved for recovery in the DLQ. Automated retry, incident creation, and verification ensure resilience.
The Meta Page access token had expired during live integration testing.
The latest prototype cannot yet claim a continuously verified end-to-end production flow.
Next validation target: real Facebook comment → detection → qualification → scoring → Duta handoff → audit record.