The Skills We Keep
A reflection on how AI changes the practice that builds technical judgment, and why the skills worth keeping need to be protected deliberately.
Thoughts on software, AI, and building things that matter
A reflection on how AI changes the practice that builds technical judgment, and why the skills worth keeping need to be protected deliberately.
In this podcast discussion, we explore how enterprise software must evolve to treat AI agents as first-class users, requiring structured interfaces, intentional design, and built-in governance alongside human workflows.
Enterprise software is entering a new era where it must support not just human users, but agents that can participate directly in work.
A reflection on AI literacy from the AI Agent & Copilot Summit, focusing on the shift from using generative AI tools to structuring work, defining accountability, and understanding where human judgment belongs.
A different lens on LLM reasoning. Intelligence may scale with internal computation depth, not just longer chains of thought.
Presented on the evolution of AI literacy at the Community Summit Roadshow: access is no longer the differentiator, structure is.
When tokens get cheap, competition shifts from production economics to systems thinking.
A practical mental model for leaders trying to understand how AI may show up in the broader economy over time.
For technology leaders: why AI coding agents demand a new engineering control model and how specification-driven development enables scale.
Great conversation at Microsoft’s Americas Enterprise Partner Accelerate on what it really takes to drive AI ROI. The organizations seeing results are focused less on technology choices and more on changing how people work with AI agents. Adoption, effectiveness, and trust matter more than demos.
Analyst-Agent Pair for modern teams: practical patterns for agentic workflows with evaluations, observability, and guardrails.
Memory Design for AI Agents: a practical guide to working, episodic, semantic, procedural, and preference memory—with patterns and evaluation tips.
Agentic AI is moving from prompts to outcomes. Learn how MCP, orchestration frameworks, and persistent memory enable enterprise-grade agents, plus four high-impact use cases and a practical next-step checklist.
Learn how content chunking transforms unstructured data into machine-readable segments, enhancing generative AI systems' effectiveness. Discover strategies like fixed-length, dynamic, hierarchical, and multi-modal chunking to improve embeddings, semantic retrieval, and AI accuracy. Explore the vital role of knowledge workers in refining, structuring, and validating content for optimal AI performance.
This episode focused on what it really takes to move AI from pilots into production, with an emphasis on AI literacy, data quality, and disciplined execution. We discussed why metrics, guardrails, and thoughtful workflow design matter as much as the models themselves when operationalizing AI at scale.
Most modern, business-focused software systems rely on high-quality data to function effectively. As artificial intelligence continues to shape these systems that support knowledge work, the demand for high-quality, diverse, and reliable data has never been greater.
Explore Retrieval Augmented Generation (RAG) and its transformative impact on knowledge work. Learn how RAG integrates retrieval and generation to deliver accurate, context-rich insights by leveraging embeddings, vector databases, and generative AI. Discover practical applications for productivity and decision-making.
I recently had the opportunity to join a GovExec webinar focused on how generative AI can help government agencies meet rising public expectations for service quality, responsiveness, and trust.
Discover how vector databases are revolutionizing knowledge management by efficiently storing and retrieving unstructured data. Learn about their core components, advantages, and real-world applications in this comprehensive guide.
Explore how AI uses embeddings to understand and retrieve knowledge across different media, enhancing the accuracy of semantic search and boosting productivity for knowledge workers.
Explore the evolution and impact of transformer-based AI models on knowledge work. Understand the basics of neural networks, the architecture of transformers, and the significance of inference in AI. Learn how these models enhance productivity and decision-making for knowledge workers.