Dual-Surface Architecture: Serving Humans and Agents from the Same Tool Layer
Ethan (Jung Min) Cha
- When
- Tuesday, June 301:55 PM – 2:15 PM · 20 min
- Where
- Track 5San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
Every enterprise AI talk right now is about capability. Almost none are about containment. That's the gap this talk fills, because it's where regulated deployments actually die. The Deterministic Harness is the set of rigid rails around a model: schemas, data contracts, tool boundaries, and audit paths. These rails are what turn a probabilistic model into a deployable enterprise asset. The idea isn't new. Aviation wraps pilots in envelope protection. Nuclear wraps reactors in passive safety. Banking wraps algorithmic trading in transaction limits. Every regulated industry figured out the same thing eventually: high-variance systems only become deployable when wrapped in low-variance containment. Enterprise AI is catching up, not inventing. I'll walk through the single governed MCP and API server we built at Carlyle, and the architectural decisions behind it. You'll leave with four things: 1. A phased rollout model where each phase earns the next. Moving from locked-down reads to trusted writes isn't risk mitigation. It's trust compounding. Each phase generates the observability that underwrites the autonomy granted in the next one. Skip a phase and you don't save time. You destroy the evidence base that would have justified the next step. 2. One contract, two surfaces. A single data layer that serves both the human UI and the agent. The institution then has exactly one answer to any question either might ask. When the agent and the UI disagree, users lose trust in both. 3. An intent based feedback loop that captures what LLM providers structurally cannot. The gap between what users tried to accomplish and what the system actually delivered is invisible to Anthropic, OpenAI, and Google. Only the harness owner sees it. We close that loop back into the governed server, and it compounds into differentiation that model providers cannot replicate from where they sit. 4. The failure modes we hit and what we'd redesign. A pre mortem folks will inherit for free, from two regulated industries where a wrong answer has a named owner.
Speaker
AI Development Lead, The Carlyle Group
AI Development Lead at Carlyle partnering with investor relations teams to surface high-value AI opportunities and building the AI platform that ship them at scale. His work sits at the intersection of AI and relationship-driven corners of finance: how capital gets raised, how investors are understood, and how relationship scales. Across earlier roles at Cedar, a healthcare fintech company, and Novelis, a global manufacturing leader, he learned that curiosity about every edge of a complex problem, ruthless prioritization, and an obsessive focus on user outcomes are what separate AI demos from AI products that stick. But the real secret, he found, is understanding that successful product is about people, systems, and how solutions get sold and adopted.
More in Security
- Through the AI Fog: The architectural decision the next 24 months of agentic security depends on.Tuesday, June 30 · 10:45 AM – 11:05 AM · Track 5
- Your LLM Stack Is a 2008 Database With Better Marketing: Why ML Security Is Dominated by Misconfiguration, Not Missing FeaturesTuesday, June 30 · 11:10 AM – 11:30 AM · Track 5
- We Gave an Agent Production Code Access and Then Tried to Sleep at NightTuesday, June 30 · 11:40 AM – 12:00 PM · Track 5
- Agentic Development SecurityTuesday, June 30 · 12:05 PM – 12:25 PM · Track 5
- Using LLMs to Secure Source CodeTuesday, June 30 · 1:30 PM – 1:50 PM · Track 5
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.