In an automated, low-touch sales funnel, the "book a call" step is where prospects stall. Could a real-time AI video agent hold that conversation instead — qualifying the prospect naturally, working out which segment they belong to, and routing them to the right next step, without a human in the loop?
- Designed the complete agent persona: identity and role, personality and voice, behavioural rules, and a structured knowledge base
- Built a multi-objective conversation flow that classifies prospects into three segments mid-conversation and drives each toward a different goal — personalised demo, human sales call, or a graceful exit
- Engineered layered guardrails: disclosure rules, topic boundaries, escalation criteria, and hard behavioural limits for an unsupervised, customer-facing agent
- Wired conversation outcomes into CRM logging for attribution and follow-up
A fully autonomous, customer-facing conversational agent trusted to run without supervision — the guardrail and objective design is the deliverable, and it is what makes deployment possible at all.
- Tavus — real-time conversational video
- Persona · guardrail · objective-flow design
- CRM integration & attribution schema
Conversation design as engineering
A customer-facing agent with no human in the loop concentrates all the risk into the design phase. Every behaviour has to be specified before the first real conversation: what the agent may claim, when it must disclose it is an AI, how it detects it is out of its depth, and what a graceful failure looks like. The objective flow is effectively a state machine expressed in natural language — with the guardrails as its invariants.
Segmentation in the flow of talk
The hardest requirement was segmenting without interrogating. The flow gathers qualifying signals through natural conversation and commits to a track only when confidence is sufficient — mirroring what a skilled human qualifier does, but specified explicitly enough for an AI to execute reliably.