{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Building Out Loud","title":"Episode 10: Evals with Ed Biden","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/e9dce513\"></iframe>","width":"100%","height":180,"duration":1395,"description":"Building Out Loud: Debugging AI Agents, Evals, and When to Move Beyond Prototyping Tools (with Ed Biden of Hustle Badger)\nRandy Silver and Faith Forster are joined by Ed Biden, co-founder of Hustle Badger, to follow up on Faith’s progress building an AI-powered discovery product. \nFaith shares insights from roughly 20 interviews and survey feedback, noting strong resonance with the product’s commercial outcomes value proposition but a clear need to improve trust in the underlying data by getting her “army of agents” working reliably before polishing features. \nThey discuss the temptation to immediately implement feedback versus waiting to prioritise patterns, and Faith details practical debugging issues including missing notifications (e.g., running out of Perplexity credits), JSON parsing problems, and OpenAI producing no output. Ed explains four categories of AI building tools (LLMs, workflow builders, prototyping tools, IDEs) plus an emerging fifth category, then introduces evals and observability via traces, clustering failure modes, and automated tests. \nFaith plans to try Langfuse, improve dashboards, rethink agent orchestration with planning agents, and continue toward beta users while balancing automation with team control.\nCheck out Hustle Badgers Evals course: https://youtu.be/TA9LJJddlNE\nOr watch their introductory video on Evals: https://youtu.be/7OcrV7VSvW4\n00:00 Welcome and Guest Intro\n00:49 Discovery Progress Update\n01:33 Resisting Quick Fixes\n02:57 Agent Debugging Woes\n03:43 Moving Beyond Replit\n05:03 AI Tooling Landscape\n08:30 Swarms and Subagents\n09:16 Evals and Observability\n15:05 Building Better Evals\n18:21 Faith Next Steps and Roadmap\n21:29 Replit vs IDE Comfort\n23:05 Wrap Up and Teaser\nLearn more about Discoveree: https://discoveree.com/","thumbnail_url":"https://img.transistorcdn.com/zRtsvl0fP7pXHBBa0YY5Eq9tGJczgYrCbA80W7Cr0VY/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8yYTJm/MDM0NDYxN2QwMGZi/ODhlNGVkNGM0MmVl/MDQwMC5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}