Clippy

Don't just slap on a chatbot: building AI that works before you ask

Feb 22, 2025 · 5:46

Arthur Objartel of Evil Martians argues that slapping chatbots on products is misguided, advocating instead for proactive AI that assists users before they ask. Drawing from his work on Tegon, an AI-powered issue tracker, he demonstrates three interaction modes—suggestion, action, and question+action—that operate within the natural workflow without chat interfaces. The AI triggers contextually relevant questions and actions, such as splitting issues or suggesting subtasks, all reversible with one click. He proposes three rules: AI supplements user agency, offers recommendations not force, and integrates without breaking flow. Examples extend to code editors catching pitfalls and design tools promoting accessibility. The talk challenges the status quo, urging experimentation beyond reactive chat interfaces.

Personality Driven Development: Exploring the Frontier of Agents with Attitude

Feb 17, 2025 · 18:00

Ben, from Perpetual, argues that anthropomorphizing AI agents—giving them personalities, forms, and preferences—transforms user adoption and engagement, despite significant challenges. He presents examples like Tech Lead, an artichoke recruiter, and hamster teams, showing how form factors create instant understanding and enable price anchoring (e.g., 1/20th the cost of a junior employee). Benefits include easy problem decomposition (specialized agents outperform generalized), branding, and fun. However, downsides include reinforcing stereotypes (100% of generated software engineers appear male), raised performance expectations, difficulty rebranding, distraction from core value, and stark reminders of job replacement—illustrated by a CEO introducing an IC as the one who 'knows what they're doing.' Ben highlights personality-driven development where every instance is bespoke, with prompt-driven preferences (e.g., 'I like Ivy League schools'), making debugging uniquely challenging.