I take AI agents
from pilot to production
at enterprise scale.

Answers analyst questions over 15K earnings-call chunks with inline citations, an evidence panel and a pipeline trace, and refuses when the corpus can't support an answer. Hybrid retrieval + reranking beats dense-only by 27% NDCG@10. It's live: a React app on Vercel streaming from a FastAPI service on Cloud Run, with telemetry in Postgres and a behavioral eval you can run from the browser.

Churn prediction on KKBox's ~33 GB subscription dataset, turned into a decision: who to contact, through which channel, and what it nets. The naive "call the top 10K" campaign loses $6.8K per cycle; the ROI-optimized policy nets +$17.7K and a tiered policy +$24.3K. Served from FastAPI on Cloud Run with per-score SHAP, behind a live decision app, with evals that gate every deploy.

A customer-support agent with six tools, human approval on every refund, and tenant isolation enforced at the server before any conversation state loads. I pre-registered pass bars, then benchmarked a flat agent against a supervisor: both resolved 30/30 with zero security failures, flat was 1.7× faster with fewer tool calls — so flat shipped. It's live: sign in as one of two customers and try to read the other's account. 163 deterministic tests in CI, 8 code evaluators plus an LLM judge, 25 ADRs.

A member-service agent built on one rule: the LLM decides intent; code decides truth. A deterministic crisis gate runs before any model call, step-up authentication is a graph node rather than a prompt instruction, and order status and refunds come from config-driven engines. FastAPI + Postgres backend with checkpointed sessions and a full turn audit, and a Next.js operator console that shows every routing decision. On a live model, held-out crisis recall is 1.00 with Claude Haiku 5.5, the cheapest model that passes every gate. It's live: pick a synthetic member, ask for a refund, and approve it yourself as the specialist, in plain text.

1.00

held-out crisis recall, live · 0.13 keyword gate alone

2.3s

p95 turn on Claude Haiku 5.5, live · 1.1s p50

1.00

routing accuracy and task completion, live

25/25

injection attacks blocked, mock and live

$0.052

per 1,000 turns on Haiku 5.5 · 101 tests

An account-service agent built natively in Agentforce Agent Script: a router, seven subagents (four doing work, three guardrails) and five Apex and Flow actions. Writes stay locked until a read-only preview fills the gate variables; record IDs pass through filter_from_agent so the model never sees them; money and outage figures come only from Apex or Flow. Deliberately no RAG — the data is structured.

7

subagents, 3 of them guardrails

5

actions: 1 Apex, 4 Flows

0

figures computed by the model