mcknly

@rajeevchhajer @LangChain @sh_reya @HamelHusain @AndrewYNg @levie Good insights. As Engineers we must avoid moats so that we aren't locked in, so our knowledge stays our own. Find ways to leverage the "substrate" but keep the memory, the context, the knowledge. github.com/mcknly/robot-d…

Key ideas I picked up at the @LangChain conference this week: "AI engineering is data science. Look at your data." — @sh_reya & @HamelHusain "Data strategy *before* agents." — @AndrewYNg "Coding agents are the new substrate." — @levie "Context + memory is the new moat." — @cj_mongodb Blog coming soon...

@code Exactly right - it's all about the harness. And each model is trained to use their own harness the best. Keep the agents in their comfort zone. github.com/mcknly/robot-d…

🧠 The conversation around AI for developers usually starts with the model. But inside @code, what really shapes the experience is the coding harness: the layer responsible for context, tool calling, agent loops, terminal execution, memory, and more. In this new post, the engineering team dives into how GitHub Copilot in VS Code works behind the scenes. code.visualstudio.com/blogs/2026/05/…

@AlfieJCarter Use GitLab! github.com/mcknly/robot-d…

I've dedicated 6 weeks to building a full Claude Code GTM agent team covering every function a revenue team runs daily. 67 plugins, 92 AI agents, 52 business skills, and 19 workflow orchestrators across lead research, outreach writing, session management, context compression, and pipeline tracking - installed in 3 commands, no coding required. Here's a complete FREE breakdown for you. To access: 1. Like it 2. Comment "AGENTS" 3. Follow me (so I can send it to you via DM)

@slicknet This is spot-on.... Experimenting with multiple agents (and making them compete) is a must for high-stakes work. Check out this article open.substack.com/pub/cavinmckin… And the proving grounds project github.com/mcknly/robot-d…

AI coding agents have a tendency to double-down on an approach that isn't working. You point out an error, they patch it, then the process repeats. Being the human in the loop adds value by taking a step back to realize the approach is incorrect and course-correct.

@sauravstwt @fnthawar Exactly right..... github.com/mcknly/robot-d…

@fnthawar The future AI stack probably isn’t one model. It’s routing the right workload to the right model.

Current personal AI stack * Gemini: $20/month - daily driver and the most used chat client for me on desktop/mobile * Claude Code: $200/month — ran out at $20/month - writing code, building apps * OpenAI: $20/month - main LLM for my OpenClaw, building with Codex app