Mark Headd

SpecOps: Specification-Driven Legacy Modernization Specifications over code. Preserve institutional knowledge, verify behavior, and generate modern systems with AI.

You can learn more about the SpecOps Method and obtain a copy of the book I wrote about it here: spec-ops.ai

I wrote a book about exactly this challenge. The SpecOps method proposes creating that verification artifact for legacy modernization efforts by leveraging AI to generate specifications that domain experts can read and confirm. The trends called out in the Anthropic report verify this approach.

This is why the role of humans doesn't disappear or diminish as AI coding tools gets more capable. AI can handle legacy code base analysis and new code generation. Humans are best suited to handle judgment and verification. Each actor in the process is focused on what it does best.

Domain experts know whether business rules are correct. But they often can't read COBOL, Java or other legacy languages. The verification problem in legacy modernization isn't about technical capability. It's about creating an artifact that human judgment can engage with.

The report makes a prediction of significant relevance to governments: AI will handle COBOL fluently soon. But reading old code isn't the hardest part of legacy modernization. Verification is. AI can describe what code does. It can't verify that system behavior matches policy intent. Only humans can

Anthropic's new report on #AI coding trends shows that engineers use AI in 60% of their work but fully delegate less than 20% of tasks. They call this "the collaboration paradox." The report also predicts AI will handle COBOL fluently soon. Let's dig in. 🧵 resources.anthropic.com/hubfs/2026%2...

Why your coding agent keeps undoing your architecture Think of your codebase as a state machine. The code is the current state. The architectural decisions are the transitions.

"Your coding agent is not malicious. It's amnesiac."

mahdiyusuf.com/why-your-cod...

True story

Thanks, Randy!

Government Software at the Crossroads Government tech leaders are signing longterm software contracts during the biggest shift in how software works since cloud computing. The assumptions behind those decisions may already be obsolete.

Lots of chatter online about what people are seeing with the rapid evolution of #AI coding tools, but I don't see as much conversation about what these changes mean. Here's what I think it means for a sector that I have worked in on and off for my entire life: government. civic.io/2026/02/11/g...

🤖 The SaaSpocalypse - The week AI killed software How Opus 4.6, Plugins Codex 5.3 wiped $285bn from SaaS valuations

I been saying this: "The SaaSpocalypse - The week AI killed software" www.fintechbrainfood.com/p/the-saaspo...

How government platforms make AI coding assistants more effective | Ad Hoc AI coding assistants are transforming how developers work, generating everything from boilerplate code to complex business logic in seconds. But these tools are only as effective as the context they h...

How government platforms make #AI coding assistants more effective.

adhoc.team/2026/02/05/h...

Cool new feature to add agentic workflows to your GitHub repos. Another banger coming from the group at @githubnext.com and further validation that the future of software development is opening up for people that have developed the ability to communicate clearly. Words > Code github.github.io/gh-aw/

Watch Mob War: Philadelphia vs. The Mafia | Netflix Official Site A brutal mob war between John Stanfa and Joey Merlino plunges '90s Philadelphia into chaos and bloodshed in this captivating true-crime series.

There's a good series on Netflix about the Philly Mob Wars, which features Skinny Joey in his youth. www.netflix.com/title/81763602

Astute watchers of the ESPN 30 for 30 "The Philly Special" will notice a special cameo by a quintessentially Philadelphia character: Joseph Salvatore Merlino. I think he has a steak shop now in Philly or something. Wild seeing him in this. en.wikipedia.org/wiki/Joey_Me...

If there was a snow shoveling event in the Winter Olympics, I'd crush that shit.

YouTube video by ESPN 30 For 30: The Philly Special [FULL EXCERPT] | NFL on ESPN

ESPN 30 for 30 episode on the iconic Philly Special play from Super Bowl 52 drops tonight at 9:30 PM EST.

INJECT THIS DIRECTLY INTO MY VEINS!!! #GoBirds #30for30

www.youtube.com/watch?v=nVYa...

Good advice here: "Fully trusting the answer an LLM gives you is foolishness, but it’s wise to use an LLM to help navigate the way to the answer."

Sometimes you just have to "git checkout main && git branch -D your-old-idea" and start again...

Code is cheap. Show me the talk. Linus Torvalds once said, 'Talk is cheap. Show me the code'. That is no longer the case.

Software development is changing, dramatically. "For the first time ever, good talk is exponentially more valuable than good code. The ramifications of this are significant and disruptive."

nadh.in/blog/code-is...

#AI #ChatGPT #Claude #LLMs #Coding

Personally I think it's too early to settle on any one tactic as "the right one" just yet. These techniques will continue to evolve, and models will improve. The best approach for organizations adopting AI coding for now is to codify your best practices and institutional approaches. Write. it. down.

AGENTS.md outperforms skills in our agent evals - Vercel A compressed 8KB docs index in AGENTS.md achieved 100% on Next.js 16 API evals. Skills maxed at 79%. Here's what we learned and how to set it up.

Super interesting study on the efficacy of different AI-coding assistant instruction methods. Big takeaway from this work - simpler is better. vercel.com/blog/agents-...

YouTube video by ESPN 30 for 30 | The Philly Special | Official Trailer

Hell yeah! #GoBirds #PhillyPhilly www.youtube.com/watch?v=K1SA...

We're experimenting with ways to keep AI agents in sync with the exact framework versions in your projects. Skills, 𝙲𝙻𝙰𝚄𝙳𝙴.𝚖𝚍, and more.

But one approach scored 100% on our Next.js evals:
vercel.com/blog/agents...

The Collapsing Cost of Software Development The cost of generating software code is collapsing. AI coding tools have matured faster than most realize. For governments, this changes everything.

The cost of generating software code is collapsing, and governments aren’t ready yet for what that means. civic.io/2026/01/29/t...

#AI #ChatGPT #Claude #CivicTech #SoftwareDevelopment

"The tools have changed, the craft hasn't" - good post on using AI-assisted coding tools.

This would address one of the chief bottlenecks in delivery in the public sector: compliance documentation.

If government software teams are going to use #AI coding-assistants for their work, and increasingly they are doing just that, then why not direct those AI tools to generate code and configuration files that are compliant from the start?

mheadd.github.io/atlas-ato-ac...

Disposable Software and the Future of Government Technology AI is driving a toward “disposable software” and this could have significant implications for the public sector. The SpecOps method offers one way for governments to adapt to this poten…

The rapid evolution of #AI coding tools and increasingly sophisticated generative AI models has resurfaced the idea of “disposable software,” or designing for obsolescence. What does this mean for government software projects and how can spec-driven development help?

civic.io/2026/01/26/d...

Codeless: From idea to software - Anil Dash A blog about making culture. Since 1999.

It's still early days, but the coding world is changing really, really fast. It just might turn out that the future of software development is... writing things down in clear, simple, documents that #AI tools can use to generate software. www.anildash.com/2026/01/22/c...