/ Selected work

AI that talks to customers — and takes action

Operational services Founder-operator — product build

Context

Most conversational AI deflects. The valuable version completes: it can look up the caller, answer from their real record, and execute the follow-up in the operational system.

The problem

Conversations span channels — a request starts on a call and finishes over SMS — while state has to stay coherent.

Answering from account data means live integration with systems of record, with the access-control questions that follow.

Voice adds hard latency budgets: retrieval, reasoning, and synthesis must fit inside a natural pause.

The system

Channels voice · SMS · email Orchestration state + routing Context caller record cache Action catalog typed · authorized Systems of record Human escalation with context
Architecture — ai that talks to customers — and takes action

Critical decisions

Agent actions are typed operations, not free-form tool calls

The agent chooses from an explicit, auditable action catalog with per-action authorization — capability boundaries are architecture, not prompt text.

Escalation is a feature, not a failure

Confidence thresholds route to humans with full conversation context. The metric is resolved work, not deflection rate.

Latency budget drives the retrieval design

Pre-fetched caller context and cached account summaries keep voice interactions inside conversational timing.

Execution

Channel by channel: SMS first (forgiving latency), then voice. Every production conversation reviewed in early weeks to build the evaluation and escalation tuning set.

Outcome

  • Customer conversations that end in completed work inside operational systems.
  • Human agents concentrated on the interactions that genuinely need them.
  • [Quantified outcomes to confirm before publication]

Lessons

  1. The integration layer, not the conversation layer, is where the value lives.
  2. Typed actions with authorization beat open-ended agency in production.
  3. Latency is a product constraint that shapes architecture.

Have a similar problem?

Discuss an AI initiative