Recent content in Ryan McCue on Ryan McCue - AI Delivery Systems & Engineering Leadership
The engineer says they need to get better at AI. Two weeks later, they have six branches open. One is a half-finished refactor. One is a test-generation pass nobody has reviewed. One is a migration that works locally. Two are small product changes waiting on clarification. The last one is a surprisingly clean PR that the author cannot quite explain without reopening the agent transcript. This…
The PR lands at 3:42. The author is done. Or at least they feel done. The diff is tidy. The tests are plausible. The summary sounds calm. Nobody is being lazy, and nothing obviously terrible happened. An AI-assisted first pass turned a small implementation into a short afternoon instead of a full day. Then the reviewer opens it. Now the real question starts. When an AI coding rollout reports ten…
Generated code is not the hard part anymore. That does not mean delivery got easy. A team can now produce a clean-looking implementation faster than its release system can safely absorb it. The PR compiles. The tests pass. The demo looks fine. Then the change waits, ships nervously, or turns into cleanup work after the fact. That is where the real AI adoption test lives. Not in the editor. Not in…
AI dashboards are getting better. That does not mean they prove delivery impact. This distinction matters because a lot of engineering organizations are starting to confuse visibility with evidence. They finally have charts for AI usage, tokens, active users, review comments, agent activity, and compliance logs. The dashboards look serious. The numbers move. Someone puts the trend line in a…
Every serious AI coding workflow eventually teaches you two things about the little approve button. First, the button is useful. If an agent is about to run a shell command, edit a file, install a package, or call a tool, I would rather see the question than not see it. Second, the button is nowhere near enough. Approval prompts fail in both directions. They are too weak to be the whole safety…
AI does not make software delivery simple. It makes one part of it smaller. That is the distinction most AI team-design arguments miss. They look at a small group of strong developers using agents and conclude the whole delivery system can collapse into a tiny autonomous pod. Maybe for a demo. Maybe for a greenfield internal tool. Not for the messy production work most engineering teams actually…
Most companies are still treating AI adoption like a tooling rollout. Pick the IDE assistant. Approve the chat tool. Let a few teams try agents. Write a policy that mostly says “be careful.” That was probably fine when AI sat beside the work. It is less fine when AI is starting to sit inside the work. AI now affects how engineering work gets defined, built, reviewed, shipped, secured, and…
AI did not just change how code gets written. It changed the economics of your delivery system. When implementation gets cheaper, the constraint moves. More code shows up upstream, but CI does not magically get faster, QA does not become less overloaded, release confidence does not appear out of nowhere, and production does not become more forgiving because the diff was generated by a model. The…
A pull request used to carry its own credibility. Not perfectly, obviously. Bad code still got merged. Sloppy reviews still happened. But the basic trust model was stable enough that most teams could function: a developer wrote the code, a reviewer read the diff, maybe glanced at the tests, and made a judgment call. That model is breaking. AI-assisted teams can now generate more code than…
If you ask for weekly proof that your AI transformation is working, you are setting your team up to manufacture theater. Most weekly AI ROI numbers are not finance. They are tool activity multiplied by an hourly rate, with the messy parts stripped out: seats activated, prompts sent, self-reported minutes saved, maybe a heroic spreadsheet that turns that into dollars before the code is even…
I used to write terrible tickets. Not maliciously terrible. Just the kind of lazy that everyone recognized and nobody questioned. “Add retry logic to the payment service.” “Handle the error case for expired tokens.” Tickets that assumed the implementer already knew what I meant, because the implementer was usually me, or someone sitting three desks away who’d been in…
I wrote recently about the 5 stages of AI tooling adoption that engineering teams go through, from curiosity to orchestrated autonomy. That framework is about organizations. This one is about you, the individual developer, and the thing nobody warns you about when you start getting good with AI tools: the bottleneck keeps moving. You spend weeks learning to prompt effectively, finally start…
When vendors start inventing new engineering management frameworks, it’s usually because the old assumptions stopped fitting reality. This week LinearB launched APEX , a framework organized around AI leverage, predictability, flow efficiency, and developer experience. I don’t think most teams need to adopt APEX as a branded thing. I do think the launch is a useful market signal. When a…
A few months ago, I watched Claude Code implement a feature I’d been planning to build that afternoon. It took about four minutes. The code was clean. The tests passed. The approach was roughly what I would have done, minus one edge case I caught in review. I merged the PR and moved on to the next thing. And then I sat there for a second, because a question had been forming for months and…
Ninety-five percent of developers now use AI tools at least weekly, with seventy percent juggling two to four tools at once. Adoption isn’t the issue anymore. Most teams adopted the tools without adopting any shared practices around them, and that creates a predictable plateau. The Expert Beginner Plateau Erik Dietrich coined the term “expert beginner” over a decade ago. The…
Somewhere in the last two years, the industry settled on a mental model for AI coding tools: “It’s like having a junior developer. You still need to review everything carefully.” A year ago, this was wrong because it overstated the tool’s capabilities. The tools have gotten dramatically better since then, and the metaphor is still wrong, just in a completely different…
I wrote recently about the 5 stages of AI tooling adoption that engineering teams go through. That framework is about organizations. But there’s a parallel progression happening at the individual level that nobody talks about, and it matters more. Every developer has an invisible line. On one side: things they’ll hand off to AI. On the other: things they insist on writing themselves.…
Every engineering team I talk to tells me they’re “using AI.” When I dig into what that means, it’s almost always the same story: the company bought Copilot licenses, a few people use Claude or ChatGPT on the side, and everyone has a vague sense that they should be getting more out of it. Nobody knows what “more” looks like. This isn’t a tools problem.…
Over 91% of developers now use AI coding tools. PR volume is surging. And organizational productivity has barely moved. That gap keeps showing up in the data. Teams adopt AI coding tools, generate more PRs, but review time climbs even faster. More code going in, same bottleneck at review, same deployment queues, same or worse quality gates. The Bottleneck Shifted AI coding assistants genuinely…
Invited by the University of Victoria’s Digital Scholarship Commons, I presented a live, hands-on session exploring how senior developers actually use agentic AI coding tools in their day-to-day workflow. What I Covered The session centered on a live demonstration of Claude Code — Anthropic’s agentic coding CLI — adding real functionality to a web application in real-time. Rather than…
The Problem Voice dictation tools either produce garbage transcripts or lock you into a single platform. The good ones require cloud accounts with zero transparency about what happens to your audio. And none of them understand that “new paragraph” means a paragraph break, not the literal words “new paragraph.” The Solution Clair Flow is a voice dictation system built across…
The Problem AI coding assistants are powerful, but deploying them at scale is a mess. Every task needs a clean environment, the right context, and proper isolation. Running AI agents manually — one terminal at a time — doesn’t scale. The Solution Hivemind is a full-stack platform built in F# (SAFE stack) that manages the entire lifecycle of AI coding agents: Container Orchestration: Each…
Overview A personal AI operations platform that bridges conversational interfaces with development tooling. Chat-driven task delegation that routes work to the right execution environment — whether that’s a Hivemind drone, a local coding session, or a direct edit. What It Does Multi-agent orchestration: Specialized AI agents for different roles (product, development, operations) with clear…
The Short Version I’m an Engineering Manager with 10+ years of full-stack development experience, currently leading a cross-functional engineering pod at a real estate technology company. I work on the systems around software delivery: how teams define work, build it, verify it, ship it, and learn from it. Outside of work, I’ve been building Hivemind , a full-stack platform in F# that…
AI coding tools are already inside the engineering workflow. The harder question is whether the system around them can absorb more generated work without creating review bottlenecks, weak proof standards, delivery risk, or fake ROI stories. The AI Delivery System Audit is a compact advisory engagement for engineering leaders who want a practical second opinion before expanding AI usage or…
Get in Touch I’m always interested in conversations about AI-assisted delivery, engineering leadership, and the systems that make generated code shippable. If your team is already using AI coding tools and running into review pressure, vague specs, weak proof standards, messy ROI stories, or rollout friction, I’m happy to compare notes. Email The best way to reach me: ryan@ryanmccue.ca…