I asked Claude Code to run a usage report on my Claude Code sessions from the last two weeks. Around 200 sessions, 235 hours, across game dev, mobile apps, multi-agent tooling, and infrastructure. I'm publishing the redacted version because it's a useful snapshot of how one person is actually working with AI coding agents in 2026, and because if you sell dev tools, your buyer might look more like this than you think.

I've been building two apps with AI agents doing most of the heavy lifting. One is a ham radio propagation tool for iOS. The other is a game for my daughter. Both started the same way: I gave the agent a prompt, it built something, and the result was fine. Just fine. Functional, forgettable, and looking like every other AI-generated app out there. Then I changed one thing, and the entire quality of the output shifted…

Most people iterating with AI agents hit the same wall eventually. The output quality plateaus. You tweak prompts, refine skills, adjust context. The results are fine. But they stop getting better. I hit that wall recently, and I think I found a technique worth sharing.

Most developers using AI for coding dump everything into one chat window and hope for the best. I think I may have found a better way. A workflow that treats different AI tools…

AI can generate code, but it can’t replace the human eye for design. Game artists, trained in composition, color theory, and spatial storytelling, are uniquely positioned to shape the next generation of software interfaces.

LLM-powered agents can simulate QA, security, and architecture expertise well enough to catch 80% of the issues a human reviewer would. The question is whether that last 20% still justifies the cost of a dedicated specialist.

Vibe coding is great for prototypes, but production software still needs guardrails. Here’s why AI-generated code demands the same SDLC discipline we’ve always applied, and how an 8-stage agent pipeline keeps things from falling apart.

How I built GoPro’s developer program from zero infrastructure to 330+ partners including NASA, Google, and BMW. Lessons learned about launching developer ecosystems from nothing.

If on-demand software is the future, interoperability is its foundation. JSON Schema, OpenAPI, MCP, and llms.txt are becoming the standards that determine whether AI-generated tools can actually talk to each other.

Most business software is a UI layer on top of well-documented rules. As LLMs get better at generating those interfaces on demand, the subscription model starts to look like a relic. This is what comes next.

1Password already had organic developer love and 900+ open source projects. The challenge was building a formal DevRel function around that affinity without breaking the trust that earned it.

Developers increasingly discover tools by asking AI assistants, not by Googling. If your product doesn't show up in those answers, you're losing evaluations you'll never know about. Here's how to fix that.

When COVID wiped out every developer conference on our calendar, we pivoted to a content-driven acquisition strategy at HERE Technologies. By year's end, we had onboarded 15,000 new developers without a single in-person event.

Most companies know they need a developer program but don't want to wait 18 months for a full-time hire to figure it out. I run a fractional DevRel practice that gets API-first companies from zero to a functioning program, fast.

After my LinkedIn account was compromised and permanently removed, I lost nearly two decades of professional connections. This is about what happens when a single platform becomes too central to your professional identity.

We're just scratching the surface of what AI can do when it comes to creating personalized, on-demand tools. The future isn't one-size-fits-all software. It's tools built specifically for how you work, generated in minutes.

One of the most effective DevRel tactics is personally inviting developers to write about their projects in their own words. Here are the strategies and lessons learned from building a developer storytelling program.