Jason's proposed multi-model escalation system for the Forge "Jarvis" assistant:
Lee discovered Agent Teams (experimental, JSON settings toggle). Compared to GSD orchestrator — both coordinate multi-agent work, but Agent Teams is first-party with inter-agent communication. Key insight: orchestrator/lead agent uses lots of tokens, so Agent Teams best for complex projects, sub-agents for simpler tasks.
Lee's team using Copilot's coding agent at Best Buy. One team cut a 4-month project to 1.5 months. Lee uses Copilot code reviews — reviews that took 1 hour now take 5 minutes. Training offshore devs to self-review with AI before submitting.
Jason demoed NowPage publisher and explained the HC Standard concept:
Jason's "two-hat" recursive approach predates Agent Teams' devil's advocate pattern. Instead of destroying bad ideas, the steelman forces the solution to be stronger. Links to emerging Recursive Language Models (RLMs) research.
Jason arguing traditional programming is "dead" — built entire NowPage infrastructure without coding knowledge. But skilled devs still add value by directing AI more specifically (CSS cleanup, architecture choices). Proposed race: same task, manual dev team vs Claude Code.