The Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AI
The talk addresses the critical role of design and User Experience (UX) in making AI applications successful, arguing that polished aesthetics are a major competitive advantage. The speaker details methods to avoid generic 'AI slop' by codifying anti-patterns using tools like Hallmark, leveraging specific themes, and adopting structured development practices such as providing visual references, writing detailed prompts, and iterating with smaller open-source models.
Key takeaways
-
Use Visual References (Inspiration Vault)
Always provide AI models with a large collection of screenshots or inspiration images to guide the design output. This significantly improves the final product quality.
-
Structure Prompts and Features
Instead of sending one massive prompt for all features, break down development into smaller steps (one or two features per prompt) and use longer, more specific prompts (e.g., voice notes) to guide the agent.
-
Iterate with Smaller Models
10:53
Start base builds using larger models (like Codex/Claude Code), but use smaller, faster open-source models (such as GLM 5.2) for iterative refinement and polishing to achieve better results.