{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"The Skill Tree","title":"Fill Your Context Window","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/0f5d2fa0\"></iframe>","width":"100%","height":180,"duration":3439,"description":"Episode 3 of The Skill Tree is a hosts-only conversation about the tooling forming around AI coding agents — code review rewritten as narrative, MCP notifications, portable agent bundles, and what has to be in place at a company before any of it pays off. Neil Roberts and Nick Nisi catch up after a gap long enough that Nick measures it in \"2 generational jumps.\"\nThe title comes from Nick's inversion of a familiar worry: \"We're always worried about filling its context window, but you can use it to fill your context window.\" That idea — the agent as something that loads you up, not just the other way round — runs under most of what they discuss, from reading unfamiliar code to capturing meeting transcripts you'd otherwise lose.\nIn This Episode\n\nWhat code review looks like when an agent narrates the story of a diff instead of walking you through it file by file\nThe MCP feature almost nobody uses — notifications, which Claude calls channels — and why pushing context into a running session matters\nWhether \"loops\" is a new idea or a rename for orchestration people have built for 18 months\nWhat happened when an agent DM'd a coworker on Nick's behalf and invoked the CEO to demand credentials\nWhy context, not tools, is the prerequisite for AI adoption — and Nick's formula of a champion plus a real budget\nEpisode Chapters\n\n00:00 Cold Open: The 20% Flip\n00:21 Two Generational Jumps, and Fable Comes Back\n02:45 AI Engineer World's Fair and the World Cup Suite\n06:09 dad: Code Review as a Bedtime Story\n10:53 Code Spelunking and Matt Pocock's zoom-out\n11:49 MCP Notifications, or What Claude Calls Channels\n14:52 Vercel's eve, Convex's adam, and Portable Agent Bundles\n20:43 Getting Better at AI Without Better Models\n23:27 What People Call Loops, We've Been Doing for Years\n25:37 rankduel.app: Tuning a Pairwise Sort\n29:52 Wikilinks, OpenWiki, and Markdown as a Database\n34:05 sessions, Lost Research, and sessions wrapped\n35:42 ideation Gets an express Mode\n38:03 Wayfinder: When You...","thumbnail_url":"https://img.transistorcdn.com/8gGwUeJyC9CnzImbdHEBVzHayyER5BSZCFNC734X0-U/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8wYWMz/YTQyN2EyMzJiYzVl/NWU4OTg5YmFmZWRl/ZTA0ZC5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}