Ryan McCue on Ryan McCue — Engineering Leader & AI Infrastructure Builder

Coding with Agentic GenAI Tools: A Senior Software Developer's Workflow

Wed, 30 Jul 2025 00:00:00 +0000

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 slides and theory, the audience watched an end-to-end feature go from planning to shipped code using AI-assisted development.

Hivemind

Wed, 15 Jan 2025 00:00:00 +0000

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 coding task runs inside an isolated Docker container with the right repo, branch, and dependencies pre-loaded.
Agent Management: Supports multiple AI backends — Claude Code, Codex CLI, and others — with a unified interface for spawning, monitoring, and collecting results.
Pipeline Automation: Multi-phase workflows (plan → implement → review → fix → PR) run automatically, with human checkpoints where they matter.
Fleet Operations: Run dozens of coding agents in parallel across different repos, branches, and tasks.

Architecture

┌─────────────┐ ┌──────────────┐ ┌────────────────┐
│ Hivemind │────▶│ Agent │────▶│ Docker │
│ API Server │ │ Orchestrator│ │ Containers │
└─────────────┘ └──────────────┘ └────────────────┘
 │ │ │
 ▼ ▼ ▼
┌─────────────┐ ┌──────────────┐ ┌────────────────┐
│ Web UI │ │ Git Manager │ │ AI Agents │
│ (Fable) │ │ (Gitea) │ │ (Claude/Codex)│
└─────────────┘ └──────────────┘ └────────────────┘

Key Decisions

F# / SAFE Stack: Strong typing catches orchestration bugs at compile time. The functional-first approach makes complex state machines manageable.
Docker isolation: Every agent runs in its own container. No cross-contamination between tasks. Clean environments every time.
Git-native: Everything flows through git. Plans are committed to specs/, implementations happen on feature branches, reviews happen on diffs.

Impact

Hivemind has become the backbone of my development workflow. What used to take hours of manual context-switching — spinning up environments, feeding context to AI tools, reviewing output — now happens automatically while I focus on architecture and code review.

Clair Flow

Sun, 01 Jun 2025 00:00:00 +0000

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 three codebases — native clients for macOS and Linux, backed by a hosted cloud service that handles the heavy lifting.

AI Development Workflow

Sat, 01 Jun 2024 00:00:00 +0000

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 handoff protocols.
Chat-native interface: All interactions happen through a familiar chat interface. No context switching to separate dashboards.
Skill-based routing: Tasks are automatically routed based on type — coding tasks to drones, research to search agents, ops to infrastructure tools.
Memory and continuity: Persistent memory across sessions. The system remembers what was discussed, what’s in progress, and what’s blocked.

Why Build It

Off-the-shelf AI tools are general-purpose. This system is opinionated about my workflow — the repos I work on, the tools I use, the way I think about task decomposition. That specificity makes it dramatically more effective than any generic assistant.

Your PR Needs a Burden of Proof Now

Mon, 20 Apr 2026 08:00:00 -0600

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 reviewers can safely trust from the diff alone. The problem is not that the code is always bad. The problem is that the reviewer can no longer assume the diff itself is the whole story. As code gets cheaper to produce, proof gets more expensive to skip.

Engineering Productivity Is Not AI ROI

Sat, 18 Apr 2026 09:00:00 -0600

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 reviewed.

That is not ROI. That is instrumentation wearing a finance costume.

The Spec Is the Product Now

Wed, 15 Apr 2026 09:00:00 -0600

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 the same standup that morning.

This worked fine for twenty years. It was, in hindsight, a system held together entirely by the fact that humans are excellent at reading between the lines. AI is not.

The Bottleneck Keeps Moving: What Actually Limits You at Each Stage of AI-Assisted Development

Mon, 13 Apr 2026 07:00:00 -0600

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 getting useful output, and then discover that generating code was never really the problem. Now you’re drowning in code you can’t verify fast enough. So you build better review habits, develop a sense for when to trust the output and when to double-check, and then realize the new constraint is that you can’t break complex problems into pieces the AI can actually execute on. Every time you solve one bottleneck, the next one is already waiting behind it.

Why Faster Coding Made Engineering Management Harder

Fri, 10 Apr 2026 07:45:00 -0600

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 company that has spent years selling engineering metrics decides it needs a new management model, it’s usually because the management job changed under everyone’s feet.

What Kind of Developer Are You Without the Keyboard?

Wed, 08 Apr 2026 08:00:00 -0600

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 I’d been successfully ignoring it: if the code I write is no longer the thing that makes me valuable, what exactly is my value?

Why Most Teams Are Expert Beginners With AI Dev Tools

Mon, 06 Apr 2026 09:00:00 -0600

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 concept comes from the Dreyfus model of skill acquisition, which maps five stages from novice to expert. The key insight is that most people don’t progress linearly through all five. They hit “advanced beginner,” start getting decent results, and stop improving because the current approach feels good enough.

Stop Treating AI Tools Like Junior Developers

Fri, 03 Apr 2026 09:00:00 -0600

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 direction now. Which, if anything, proves it was never the right framing to begin with.

How Far Do You Trust It? The 5 Levels of Developer-AI Delegation

Wed, 01 Apr 2026 09:00:00 -0600

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. That line is your delegation boundary, and where it sits tells you more about your relationship with AI tooling than which editor you use or how many prompting guides you’ve bookmarked.

The 5 Stages of AI Tooling Adoption Every Engineering Team Goes Through

Mon, 30 Mar 2026 09:17:00 -0600

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. Eighty-five percent of developers now regularly use AI coding tools, according to JetBrains’ 2025 survey of 24,000 developers. The tools are everywhere. What’s missing is a vocabulary for what comes after “we have the tools.” Teams don’t have a way to talk about the gap between where they are and where they could be, so they don’t talk about it at all.

I Built an AI Coding Orchestration System. Here's What I Learned.

Sun, 29 Mar 2026 17:50:00 -0600

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 speed up code generation. But that just moves the constraint downstream into code review, QA, merge conflicts, and deployment queues. None of those got faster. They got worse, because they’re processing more volume at lower average quality.

About

Mon, 01 Jan 0001 00:00:00 +0000

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 build tools that make developers radically more productive.

Outside of work, I’ve been building Hivemind, a full-stack platform in F# that orchestrates AI coding agents inside Docker containers. It’s the system I use to ship software faster than any workflow I’ve tried in a decade of professional development.

Contact

Mon, 01 Jan 0001 00:00:00 +0000

Get in Touch

I’m always interested in conversations about AI-powered development, engineering leadership, and building tools that ship. Whether you want to collaborate on a project or just exchange ideas, I’d love to hear from you.

Email

The best way to reach me: ryan@ryanmccue.ca

Elsewhere

GitHub: github.com/rymccue
LinkedIn: linkedin.com/in/rymccue

What I Like Talking About

AI Development Infrastructure — Building pipelines that deploy AI coding agents at scale. Container orchestration, quality gates, review workflows.
Engineering Productivity — Practical strategies for integrating AI tools into real development workflows. Not demos — production pipelines.
Technical Leadership — Engineering management, team scaling, development process design.

Based in Calgary, Alberta, Canada 🇨🇦