I combine hands-on development with coaching to help organizations move from AI experiments to real business results. As a CTA certified coach, I guide technical leaders through practical adoption and help teams avoid the pitfalls that derail most AI initiatives.
In my exploration of AI coding tools, I've discovered that while they promise productivity gains, they can also introduce challenges in the software delivery lifecycle. By measuring code quality, batch size, and delivery, rather than just adoption rates, we can gain valuable insights. I share five key metrics derived from GitHub's API that can help teams identify problematic development patterns early on.
In my recent experience, I faced the challenge of creating a clear interface guideline for a third-party platform while dealing with legacy code. By leveraging AI assistance, I was able to streamline the process and produce comprehensive documents for four SDKs in just one day. This approach not only clarified our requirements for potential vendors but also enhanced our project's efficiency.
Structured planning mode for code generation mirrors what I’ve been doing with my sequenced Plan-Do-Check-Act prompt cycle (https://lnkd.in/effgt9zm ). I’m adjusting my prompts to work within the plan/build modes. Seems like it’ll be smooth as butter.
You can’t tack production requirements onto rapidly produced code. The age of AI hasn’t changed this fact.
Agentic code agents can rapidly prototype applications in hours. This is amazing. These prototypes can quickly help people test the viability and value of a feature or implementation approach.
Production code is a complex mix of such details that require scalability, safety, security, deployability, test coverage, quality evaluation and stakeholder sign off, and optimization for performance, troubleshooting and maintainability. Production code takes orders of magnitude longer to create than prototypes.
The disposable prototypes agents generate usually can’t even be incorporated into such systems without a rewrite. Production software requires a more human centric and expert led approach from the start.
Finally, the speed of delivering software to users is not directly driven by the speed at which the code itself is produced. Code authoring is the middle of a value stream and is not the sole bottleneck in building effective software. AI can also speed up investigation and learning. It can facilitate communication and documentation. In the hands of qualified, experienced teams, AI tools can speed up actual delivery of quality production software by 10-30%.
This gain is worth shooting for but it is an iterative, evolutionary practice improvement. Not something you get out of the box as part of a software license.
Advice? My daughter is moving to the Irish Republic on a visa that allows her to work.
She’s a recent graduate of Worcester Polytech in Robotics Engineering. If anyone out there has ideas on where she might look for engineering related work, technical design and drafting, please DM me!
My learning mindset is driven by humility about my depth of understanding, which extends borderlessly into self-reproach. They are an inseparable essence. One gift.
I believe it's crucial to understand that current AI systems lack true accountability. While they can simulate decision-making, they do not possess moral agency or the ability to comprehend ethical judgments. This creates a dangerous void where responsibility is blurred. We must remember that AI informs our decisions, but we, as humans, remain accountable for its deployment and impact.
I am a failure who has achieved more than I imagined.
I am an ethical human who questions whether I’ve made a positive impact.
I am a happy man who struggles with sadness.
I am a discontent who is at peace with his choices.
I am at any moment any of these. Each wrapped in context without which it disperses.
Each fact eternal. Yet ephemeral and subjective.
Real and nothing.
A practical PDCA framework for accountable AI code generation. Structure sessions in phases: agent-led analysis and planning (compatible with plan mode), test-first code changes, validation against goals, and targeted retrospectives to refine prompts. Apply these agile disciplines to maintain quality and control over the code you ship.
The race to adopt AI code generation is a sustainability crisis that Agile practitioners are uniquely positioned to solve. Here is a disciplined Plan-Do-Check-Act (PDCA) cycle. Each step has a distinct purpose and builds upon the prior ones.
Use AI tools to retrieve the conceptual design of legacy software and reduce the toil of lengthy up-front design.
Selected posts from my earlier blog, where I wrote about agile transformation, leadership, and building software teams.
I’m doing most of my writing these days as @kenjudy on LinkedIn. It’s where people can find it, right now. More personal things I put on @kenjudy at mastadon.social. Related posts: HICSS-42 Six questi...
Read on judykat.com →This is what I said to open an all day creative exercise with our leadership team, and founder (Debbie) focused on our long term future… The most important thing I have to say is Debbie and I have tal...
Read on judykat.com →It’s not about grand gestures. It’s about really doing the work. Knowing how to use our talents, how to find joy in ‘enough’, being generous with help, and knowing who we want to be in the world. Cont...
Read on judykat.com →This post is published on the Stride Consulting Blog. Gerald Weinberg said in his Secrets of Consulting, “Never forget they’re paying you by the hour, not by the solution.” In other words, a consultan...
Read on judykat.com →I've started asking these six questions to foster equity, participation, and buy in before enacting any important leadership decision Continue reading → Six questions for equity, participation, and bu...
Read on judykat.com →I am filled with joy and inspired by a sense of duty as Stride’s new CEO. It’s hard to express how beautiful and rare Stride is. It is a sustainable business with an inspiring community and culture fu...
Read on judykat.com →