Ben Woodmansee — Designing Frontier AI Products

View Case Study

Hey, I’m Ben. I turn frontier AI research into products people can actually use. Currently Design Lead for AI Incubation, shipping at startup speed inside IBM. Before this, I led design across hundreds of generative AI projects at IBM Client Engineering (the ones I'm proudest of: NatWest's Cora+ and a £400M UK Government programme), and before that I was Founding Product Designer at Grandeo Labs, a ML startup later acquired. Erna Plachte Scholar at University of Oxford. Fellow at the Oxford AI Safety Initiative (OAISI). Studied AGI Strategy at BlueDot Impact.

I’m a Design Lead with 8+ years experience building frontier AI products, from computer-using agents and agentic systems to vibe coding platforms and generative tools used by millions.

RECENT PROJECTS

(02)

Selected

↓

Work

Projects from years
©2017 — 2026

A few recently shipped projects exploring how new AI capabilities reshape the interfaces we build.

Flint - Natural‑Language‑to‑Application Vibe Coding Platform, 2025 - 26

Led the 0 → 1 design of an internal natural-language-to-application builder. Shipped MVP in 4 weeks and scaled to 500+ users in 12 weeks by redesigning the interaction model around iterative building.

Design Lead

0 → 1

Vibe Coding

Relay - Designing Supervision Interfaces for AI Agents, 2026

Architected the supervision model and prototype for long-running enterprise AI agents.

Agents

0 → 1

Prototyping

AI-Assisted Email Triage, UK Government, 2024

Designed an AI system for a £400M government transformation programme that automates large-scale correspondence workflows while maintaining auditability and policy compliance.

AI Governance

Generative AI

Government Scale

NatWest's Cora+ with Generative AI, 2023

Led design of NatWest’s Cora+ generative AI assistant used by 11M+ customers. Built guardrails and interaction patterns to ensure the system could never hallucinate financial advice.

Generative AI

Assistants

Consumer Facing

Dynamic Quantum Optimisation - IBM Quantum, 2024

Designed a quantum optimisation interface translating complex quantum simulations into decision workflows usable by financial analysts.

Whitelabel

Prototyping

Quantum Computing UI

Project Webglide - Computer-Using Agent, 2025

Designed the interaction layer for a computer-using agent built on IBM’s CUGA framework (#1 AppWorld, #2 WebArena). Focused on supervision patterns for agents operating across real interfaces.

Computer Using Agents

Interaction Patterns

IBM CUGA

See interactive versions of my work: AI-assisted conversation design for a FTSE 100 client, UCL's first unified design system (BIMA Award Winner), and a patented blockchain file-sharing platform acquired by Binarii Labs.

View all projects

(03)

What I Work on

I work across the full stack of AI product design and development: from prototyping in code and designing agent supervision systems to shipping generative tools at enterprise scale. These are the problems I find most exciting, and the projects that shaped how I think about them.

→
0-to-1 Frontier AI Products
The products I find most interesting are the ones nobody has shipped before. At IBM AI Incubation, that meant working at startup speed inside one of the world’s largest technology companies. Small team, short cycles, constant iteration and finding opportunities to optimise your delivery speed. Flint went from a brief to 500 users in twelve weeks. Relay was architected and prototyped while the agent framework it depended on was still being built. The constraint wasn't resources, it’s that there’s no prior art or roadmap.
→
AI-Native Design and Prototyping
The design-to-engineering handoff is one of the slowest parts of most product teams. I’ve removed it from my own workflow. I use Cursor, Claude Code, Figma MCP and other agentic coding tools to move from Figma to working frontend in the same session, testing interaction patterns against real model behaviour rather than static mockups. On Flint, that meant shipping continuously and collecting real usage data weekly.
→
AI Safety & Governance
Some of the most interesting design problems in AI come from constraints and governance. On NatWest’s Cora+, the system could never hallucinate financial advice to different personas. On the UK Government programme, generated output carried institutional and legal weight. On Flint, trust was dependent on Carbon alignment, reliability, and visible failure states. That changed how I think about AI design. The challenge is often not making the system more capable, it's defining where autonomy is dependable, where review is needed, and how those boundaries become legible.
→
New Interaction Paradigms
I design interfaces for systems that can generate, reason, and act. Most of my work sits between product design, research, and hands-on building. I’m passionate about the moments when a new model capability appears, and the old interface stops making sense, and invention has to take place. We're moving to a homegenised but custom product world, where interfaces are adaptable, steering but importantly are used to steer, supervise, and build with AI, not just prompt it.
→
Agentic Systems & Agents
I designed the interaction layer for a computer-using agent built on IBM’s CUGA framework (#1 on AppWorld, #2 on WebArena). The core design question was simple. If an agent can operate any interface, what does the human need to see? Supervision interfaces change what people feel comfortable delegating. Is a webpage that useful for a user to see? How do you present users with what they actually value?
→
Systems at Scale
I like early-stage work, but I also care about what happens when systems meet real complexity. Cora+ served 11 million customers and was one of the largest genAI deployments in UK at the time. The UK Government work sat inside a £400M transformation programme. Flint scaled through continuous internal releases and was often used in client-facing contexts. At that point, you are not designing for ideal users in clean flows. You are designing for legacy systems, compliance, uneven trust, and real organisational mess. That is where the problem space gets interesting.
→
Tools for Developers & AI Infrastructure
Neurolab started from a specific frustration: developers building multi-agent systems had almost no visibility into why things failed. We designed a tracing and observability tool that made tool calls, recovery loops, and agent handoffs legible to the people building them. The design problem was translating internal system state into something a human could act on. That’s a version of the same question I keep returning to across most of my work. I’ve also built internal tooling used at scale, including a Figma AI Classification asset used by 400+ IBM designers.

CREATIVE RESEARCH & TOOLS

(04)

Creative Research & Tools

Outside product work, I stay close to the research layer. Not to publish, but because the design problems I care about require understanding how these systems actually work, not just what they produce.
‍
On weekends I’m as likely to be rebuilding Gemmascope as patching a Moog Modular.

Neurolab, 2025

A tracing and observability tool for LLM applications designed for enterprise developers. Helps debug complex agent workflows including multi-agent systems, tool calls, and recovery loops.

Classification with Generative AI - Figma

Created an AI classification asset used by 400+ IBM designers, helping standardise taxonomy and accelerate design system adoption across the organisation.

Oxford AI Safety Initiative — Core Fellowship

Most AI safety research is written for ML researchers. The OAISI core fellowship changed how I think about the design layer. Studying alignment principles, scaling paradigms, and macro-economic collaboration on AI made clear that the hardest problems aren’t purely technical. They’re about what systems are designed to do, for whom, and under what constraints.

(05)

Awards

2016

Erna Plachte Scholarship

University of Oxford

→

2018

Next-to-Nothing - iD Magazine

Topsafe

→

2021

The Drum Awards - 4 Nominations

Awarded UK Government Technology Grant

Grandeo Labs

→

2023

Sustainability Partnership of Year

IBM

→

2024

IBM Technology Excellence

Oxford AI Safety Initiative

Follow Me On Substack
for weekly essays on Frontier AI and Design Futures

Explore Page

→