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.
I reflect on Gödel's incompleteness theorems and their profound implications for our understanding of certainty. As I explore the beauty and elegance of these ideas, I challenge the notion of absolute knowledge within any system of thought. My journey into Gödel's proof deepens my skepticism about human certainty and highlights the limitations we face in our quest for understanding.
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.
A 38-slide talk applying Plan-Do-Check-Act with XP disciplines to close the accountability gap left open by unstructured AI coding adoption. Covers structured prompting, DORA AI Capabilities Model mapping, live demo, and measurement strategies for detecting AI code drift.
View Presentation →
I posted my presentation on how to build a skill or set of prompts to automate a business process using a human directed adaptive learning loop https://lnkd.in/gGEvsFYJ
Leadership is a tension between empathy and urgency.
The deeper a leaders thought process, the more they consider all the people who stand to gain or lose, the less obvious decisions become for them.
The leaders I most respect act from conviction but dwell in that uncertainty.
Being deliberate about how you present yourself in a critical conversation is generous. It’s being thoughtful about what you need to achieve, empathetic to what people need from you, and taking accountability for what you expect of yourself.
It’s only inauthentic if you don’t intend or are not capable of following through. Don’t be that person.
I vibe code unimportant things and test drive important ones. But I pushed the boundaries on some scripts to sync a client calendar where the calendar server is locked down to prevent our preferred and well tested sass solution.
Well. That backfired. It was consistently inconsistent on date ranges so a dedupe cycle of retrieve range with generic title from cal 1, delete, retrieve range from cal 2, add to cal 1 with generic title were two different ranges. Creating duplicates in the mismatched range.
Then in the attempt to fix that, I didn’t notice that it had removed the generic title part of the filter criteria and all my calendar events got deleted.
Not what I expected to occupy part of my day.
Welcome to the new era of going fast and breaking things.
I believe that successful AI adoption hinges on a realistic understanding of the time, focus, and investment needed to achieve returns. We must empower our teams to remove barriers and embrace change, rather than just speeding up code production. Without a strategic approach to our organizational systems, we risk creating isolated productivity that leads to chaos. Let's prioritize learning and humility in our AI initiatives.
I believe that software development is fundamentally a design process rather than a manufacturing one. When we misinterpret it as a manufacturing challenge, we risk focusing AI adoption on mere code generation. Instead, we should leverage AI to enhance our learning cycles, optimize solutions, and ultimately deliver greater value to our customers. Let's use AI to foster collaboration and improve the quality of our output.
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.