


7 episodes
by Demetrios · English
Relaxed conversations and technical deep dives around AI Agents. This Show is brought to you by the Agentic AI Foundation where the leading agentic open-source projects like MCP, Agents.md, and Goose live. See more at aaif.io





Building and scaling coding agents and “harnesses,” plus practical demos (Playdate client, Evener), and how to manage cost, quality, and long-horizon “AI colleagues.”
19 Nov 2026 · 41m · 19 chapters
How AI gateways and multi-cloud LLM routing power context-aware coding agents, plus how agent “experience” is evaluated and used for automated PR review and security/compliance checks.
16 Nov 2026 · 29m · 12 chapters
How AI agents change what “good documentation” means, why Stripe reduced internal docs from 500,000 to 5,000, and how to make docs legible, trustworthy, and accountable for both agents and humans.
13 Nov 2026 · 33m · 13 chapters
The episode explains how an AI agent system called Hermes can automate “life admin” tasks and how RL (reinforcement learning) and continual learning could let agents improve by learning from their…
9 Nov 2026 · 35m · 17 chapters
Total cost of ownership for AI agents, why “just call the API” doesn’t scale, and how to cut costs 10x while adding features.
5 Nov 2026 · 42m · 16 chapters
A conversation about how Stanford’s “Modern Software Developer” course is adapting to rapid AI coding-agent advances, plus broader lessons on building reliable agentic coding workflows and agent…
2 Nov 2026 · 44m · 23 chapters
Two hosts ride a tandem bike through Amsterdam while discussing “software factories,” why current AI coding models still produce “slop” that breaks at scale, and how agent tooling (computer use,…
29 Oct 2026 · 47m · 20 chapters