AI agents that navigate real digital workflows
Prototype to Salesforce acquisition in ~a year. I owned the frontend and the agentic UX for an AI that perceives, reasons, and acts across dynamic interfaces.
Context
Convergence built advanced AI agents that perform complex, human-like tasks in digital environments — navigating dynamic UIs and multi-step web workflows. I joined as the founding design engineer and frontend lead.
Problem
Agentic behavior is powerful but opaque. The hard part wasn't the model — it was making an agent that perceives, reasons, and adapts legible and controllable, so people could trust it with real work.
Approach
Built the frontend architecture and design system 0→enterprise (Next.js, TypeScript, Redux Toolkit, Tailwind, Shadcn) and set the team's engineering standards. Designed the agentic UX for real-time reasoning, tool invocation, and multi-agent orchestration — visualizing backend behavior through explainable flows. Architected an Electron desktop client with local LLM inference, Whisper voice input, and native OS interactions, and defined the human–AI collaboration paradigm that shaped the roadmap.
Outcome
Convergence was acquired by Salesforce in June 2025 — becoming the nucleus of Salesforce's London AI R&D lab and feeding Agentforce.
- Prototype → Salesforce acquisition in ~1 year
- Owned FE architecture + design system, set team engineering standards
- Shipped explainable agent UX across web and an Electron desktop client
- Helped hire and grow the founding engineering team