Maggie Appleton: Agentic Coding Has Outgrown the Text Box

Agentic coding has outgrown the text box. Maggie Appleton, staff research engineer at GitHub Next, argues that walls of CLI output and AGENTS.md files serve coding agents far better than the humans steering them. She walks through Chopin, the GitHub Next prototype where background agents turn a team's planning chat into a structured plan, and makes the case for agents that prompt you instead of waiting to be prompted. What we cover: – Why text-heavy agentic coding tools favor agents over humans – Boundary objects: what AGENTS.md, skill files and MCP servers get right and wrong – Multiplayer planning with coding agents in GitHub Next's Chopin – Human-to-agent handoffs, formal verification and spec-driven development – Why software quality is rising, not falling, with coding agents – Which roles still matter: PMs, designers and engineers Chapters: 00:00:00 - Introduction 00:02:14 - Inside GitHub Next and the Chopin project 00:05:57 - Why solo agents break team alignment 00:07:52 - Why coding agents struggle with design 00:12:16 - Boundary objects: AGENTS.md, skills and MCP 00:18:27 - Planning with coding agents as collaborators 00:26:49 - Multiplayer planning with background agents 00:31:57 - Agent handoffs and spec-driven development 00:37:41 - Quality, craft and who decides what to build 00:44:29 - Starting a career in agentic coding Build your software factory, one workflow at a time, with Tessl: https://tessl.co/j3d 🔔 Subscribe for weekly episodes on AI-native development Should coding agents be prompting you more? Tell us in the comments how your team plans agentic coding work today.