New podcast shows real agent workflows: evals for charting tools, local Qwen for earnings analysis
hugobowne · x · 2026-10-19
Episode two of "Show Us Your Agent Skills" by hugobowne and twiecki is out as a podcast, featuring practitioners demoing how they actually work with agents:
- BEBischof's warning: "If someone tells you, I know what agents want, you should be immediately suspicious."
- Hilary Mason calls default creative output "aspirationally very mid," demos how she tests creative variations, and shares three agent "gremlins."
- Eric Ma steers a protein engineering analysis one plot at a time with an agent in marimo.
- ttunguz runs Qwen locally on his Mac to analyze company earnings with pi.
- Bryan shows bbplot and the evals he built for his charting tools: "The goal is not to score high on a benchmark. The goal is to generate information about gaps."
The series gets developers to open their editors and explain the decisions, frustrations, and experiments behind their agent workflows.
More from coding & agent
- State machines for agent logic are extremely slept-on: LEGO bricks agents can rearrange — DavidKPiano · 2026-10-19
- Data preparation is architecture: a six-step pipeline shared by fine-tuning and RAG — Puzzleheaded_Box2842 · 2026-10-19
- Inspired by Booking.com's MCP playbook, author launches a Query Agent MCP server — CShorten30 · 2026-10-19
- Booking.com's platform team distributes MCP servers so internal teams can build tool-calling agents — CShorten30 · 2026-10-19
- Hunting for an agent that auto-tops up LLM API balances across providers — huangyun_122 · 2026-10-19
- LangChain CTO to join fireside chat on turning production agent traces into better models — hwchase17 · 2026-10-19