Ruben Casas
AI Engineer, Postman
9 Apr 2026Live at AI Engineer
Ruben Kassas (Postman): Generative UI & Beyond Chat
Ruben Kassas argues models are already good at writing UI but true generative UI hasn't arrived — today's chat is like the 1970s terminal and the industry is still waiting for its 'Mac OS moment'. He points to visual collaboration, like the Excalidraw MCP app and ChatGPT canvas, as the likely next step, and weighs personalized super-apps against monopoly concerns. His advice to companies: stop over-investing in UI that agents will bypass and focus on collaboration and human-friendly visualization. The segment ends with the hosts juggling last-minute changes to the guest lineup.
Matty Carey (Cloudflare): Code Mode, Demo Days & Agents Week
Matty Carey covers AI Demo Days' expansion from London across Europe, why the London AI scene is getting 'more vibey', and his Cloudflare work on MCP, Code Mode and programmatic tool calling ahead of next week's Agents Week. He recounts Lockheed Martin happily executing LLM-generated code as evidence that even regulated enterprises are adapting, and argues security will decide who wins. On Mythos he guesses it's a GPT-4.5-scale model that may now be economical to serve, and predicts more companies will 'slop fork' legacy software to make it their own.
Jacob Lauritzen (Legora): Velocity, Lawyers & Gooseneck Mics
Legora's CTO explains growing the company from ~10 to nearly 100 people with velocity as its core DNA, and how 'AI-pilled' lawyers now co-create skills and templates that spread through their firms. He covers bi-weekly demos as the productivity bar, Claude being the top author of commits, his gooseneck-mic experiments for talking to agents, and the new London engineering hub he's hiring for. On Mythos he backs Anthropic's restricted release as 'a sign of the times'. Afterward the hosts kick themselves for missing the gooseneck-mic business idea and plan to vibe-code a store.
Stephen Batifol (Black Forest Labs): World Models & Video Gen
Stephen Batifol outlines BFL's research-first approach: recent small models for near real-time image editing, a paper from a month ago on training from images, video, actions and audio, and world models for robot training as the long-term goal beyond video generation. He describes developer advocacy as inspiring developers and creatives, correcting misconceptions about how models are trained, and converting attention into API and open-weights usage. He also defends the deliberate Freiburg-rooted, research-first branding — build cool things and people come — and argues Europe has the talent to build frontier models while keeping an SF office.
Marlene Mhangami (Microsoft & GitHub): Copilot & Open Source
Marlene Mhangami describes her role spanning Microsoft and GitHub, the cultural contrast between the enterprise-focused parent and the more playful GitHub, and her developer-advocacy work on Python, open source and Azure APIs. She reports growing Copilot usage — including beginners using it to contribute to open source — and notes Copilot supports models from both Anthropic and OpenAI. The conversation turns to her take on the Mythos announcement right as this part ends.
Marlene Mhangami: Harnesses Matter More Than Models
Marlene Mhangami closes out her segment, saying she loves the Claude models and uses Opus through Copilot, which supports all models. She argues LLMs are generalists trained on the mean, so harnesses like Copilot matter more than raw model choice for specialized domains, and doubts current models are at AGI level. Asked what excites her, she highlights multi-model workflows and GitHub's new Critique release, where one model critiques another's output, before pointing listeners to GitHub Copilot and Copilot CLI.
Swyx: AI Engineer London, 10 Downing Street & EU/acc
Final guest Swyx joins live to discuss AI Engineer London. He explains the push to publish talk clips immediately after sessions and describes the morning visit to 10 Downing Street, praising the UK government's AI fellowship and noting the UK Chief AI Officer will give a closing keynote. He highlights the ElevenLabs booth with its Michael Caine voice, calls Luke Harries one of the world's top AI growth people, and cites Gradium's speech-to-speech work as evidence Europe can build its own AI champions. He also explains the EU/acc logo in the conference branding, saying builders must push capabilities alongside regulators.