# Phil Johnston

> Developer Relations professional, photographer, and builder

## Pages

- [An Audience of Two: What a Weekend App Taught Me About Software Economics](https://philjohnstonii.com/blog/an-audience-of-two-what-a-weekend-app-taught-me-about-software-economics)
- [The Best Software I Use Has One User](https://philjohnstonii.com/blog/the-best-software-i-use-has-one-user)
- [I Built a Throwaway Tool to Cram Python in Two Days. The Lesson Wasn't About Python.](https://philjohnstonii.com/blog/i-built-a-throwaway-tool-to-cram-python-in-two-days-the-lesson-wasnt-about-python): I've programmed in Python before. I've also programmed in plenty of other languages since, and the syntax had drifted. The logic was still there. The idiomatic shortcuts that make Python feel like Python were not. I needed to close that gap fast, and I have memory challenges that make traditional cram sessions a slog. Generic Python courses were the wrong shape. They assumed I was new. They wanted weeks. I had 48 hours.
- [/insights report](https://philjohnstonii.com/blog/insights-report): 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.
- [Stop Letting Your AI Agents Be Generalists](https://philjohnstonii.com/blog/stop-letting-your-ai-agents-be-generalists): 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…
- [Fresh Eyes: How I Got Past My Agent's Quality Ceiling](https://philjohnstonii.com/blog/fresh-eyes-how-i-got-past-my-agents-quality-ceiling): 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.
- [My Agentic Coding Stack: How I Ship Software With AI Agents](https://philjohnstonii.com/blog/my-agentic-coding-stack-how-i-ship-software-with-ai-agents): 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…
- [Code Is Commodity. Art Direction Is the Moat.](https://philjohnstonii.com/blog/hb3sdhgq74qbq63nhp90s6h4gf5cpa): 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.
- [The 80/20 Rule for AI Code Review](https://philjohnstonii.com/blog/wc9s23btpmv673x8k9ihp15w2b668e): 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 Got You the Prototype. Now What?](https://philjohnstonii.com/blog/pua6p9xgs4r03fjb8570vkp17cabzm): 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.
- [Building GoPro’s Developer Program from Zero to 330 Partners](https://philjohnstonii.com/blog/building-gopros-developer-program-from-zero-to-330-partners): How Phil Johnston built GoPro's developer program from zero to 330+ partners including NASA, Google, and BMW. Lessons on building developer ecosystems at hardware companies.
- [Standards Are the New Moats](https://philjohnstonii.com/blog/standards-are-the-new-moats): 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.
- [The Last SaaS You’ll Ever Subscribe To](https://philjohnstonii.com/blog/the-last-saas-youll-ever-subscribe-to): 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.
- [What Running DevRel at 1Password Taught Me About Open Source and Developer Trust](https://philjohnstonii.com/blog/what-running-devrel-at-1password-taught-me-about-open-source-and-developer-trust): Lessons from building DevRel at 1Password: managing 900+ open source projects, scaling technical content, and why trust is the product for security-focused developer tools.
- [Your Developer Tool Is Invisible to AI. That’s a Problem.](https://philjohnstonii.com/blog/your-developer-tool-is-invisible-to-ai-thats-a-problem): AI tools are reshaping how developers discover and evaluate APIs and SDKs. Learn what makes a developer tool visible to LLMs, why most companies are behind, and tactical steps to fix it including llms.txt, JSON-LD, MCP servers, and content strategy.
- [15,000 Developers During a Pandemic: What I Learned at HERE Technologies](https://philjohnstonii.com/blog/iuqdpdkpo11dzgygsoz7j7cbiwq9zx): How Phil Johnston onboarded 15,000 developers at HERE Technologies during the pandemic using digital-first DevRel, then expanded the cloud marketplace by 2,250x as product manager.
- [How I Help API-First Companies Build Developer Programs That Actually Work](https://philjohnstonii.com/blog/how-i-help-api-first-companies-build-developer-programs-that-actually-work): Phil Johnston is a fractional Head of Developer Relations helping API-first companies build developer programs, partnerships, and AI discoverability. 15 years of experience at GoPro, BMW, HERE Technologies, and 1Password.
- [“Phil Johnston LinkedIn” (Leaving LinkedIn and Choosing Independence)](https://philjohnstonii.com/blog/phil-johnston-linkedin-leaving-linkedin-and-choosing-independence): 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.
- [The Future of Micro-Niche AI Tools](https://philjohnstonii.com/blog/future-of-micro-niche-ai-tools): As someone who’s soon to be less relevant when it comes to technology, I am personally augmenting my workflows to include self-developed tools to help me get my work done.  One recent example is a quick script that will test server
- [Encouraging Developers to Share Their Stories in Their Own Words](https://philjohnstonii.com/blog/encouraging-developers-to-share-their-stories): 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.
- [Micro-niche vibe coding?](https://philjohnstonii.com/blog/micro-niche-vibe-coding): I've been building small terminal UI apps tuned to very specific personal workflows. It's vibe coding at its most practical: making the tools to be more productive, one micro-niche problem at a time.
- [Phil Johnston, II](https://philjohnstonii.com/resume): Resume of Phil Johnston, II. 15 years in Developer Relations at BMW, GoPro, HERE Technologies, and 1Password. Built the GoPro Developer Program to 330+ partners including NASA and Google. Onboarded 15,000+ developers. Based in Portland, OR.
- [AI agents are creating a new distribution channel for dev tools.](https://philjohnstonii.com/consulting): Fractional DevRel consulting for API-first companies. Services include Fractional Head of DevRel ($5,000/mo), DevRel Program Audit ($2,500), and AI DevRel Accelerator ($3,500-4,000). Track record with GoPro, HERE Technologies, and 1Password.
- [Johnston Software & Services, LLC](https://philjohnstonii.com/apps)
- [SkyWave - Know When to Get On the Air](https://philjohnstonii.com/skywave)
- [Terms of Service](https://philjohnstonii.com/terms-skywave)
- [Privacy Policy](https://philjohnstonii.com/privacy-skywave)
- [Photography — Phil Johnston, II](https://philjohnstonii.com/photography)

## About

Source: https://philjohnstonii.com
Last updated: 2026-09-15