https://davenporter.com Learnings about software, technology, agentic systems, and occasionally home renovation. en-us https://davenporter.com/writings/workflow-ownership-fix-the-machine https://davenporter.com/writings/workflow-ownership-fix-the-machine 2026-10-21T16:00:00Z Developers need to fix the machine, not the execution output. I was at a F500 sync in New York recently, and this idea came up: 100% of your developers should be building things to improve the workflow. So I asked the room how many of their team are actually doing the work. https://davenporter.substack.com/p/wibtm-what-happens-when-you-let-an https://davenporter.substack.com/p/wibtm-what-happens-when-you-let-an 2026-09-24T02:06:00Z Why git and AST’s have some relationship, and what’s next when it comes to systems that are agent-first. If you’ve run many agents together on a single repo, you quickly realize that the volume of agentic code can break git. https://davenporter.substack.com/p/the-value-of-being-bored-in-the-ai https://davenporter.substack.com/p/the-value-of-being-bored-in-the-ai 2026-09-16T02:08:06Z And how it can keep us in the high value areas of AI engineering. First, I hate being bored. I grew up in the era of the internet, and subsequently the attention economy, so I’m well accustomed to having something to distract myself. https://davenporter.substack.com/p/what-happens-ai-burns-down-the-backlog https://davenporter.substack.com/p/what-happens-ai-burns-down-the-backlog 2026-09-03T17:31:12Z AI is still a business transformation problem, and its out-kicking the product coverage. In a session a few weeks back someone presented me an interesting problem for developers and practitioners: What happens when developers using AI burn down the backlog? https://davenporter.substack.com/p/from-trajectories-to-lineage-building https://davenporter.substack.com/p/from-trajectories-to-lineage-building 2026-08-27T23:35:33Z A conceptual map of how to establish provenance for agent decisions using the existing tools we have today. In agent analysis and tracking, traces and trajectories are becoming well established for understanding a particular decision, or a session of decisions and events that an agent makes. https://davenporter.substack.com/p/is-the-future-of-learning-vibe-training https://davenporter.substack.com/p/is-the-future-of-learning-vibe-training 2026-08-25T15:33:06Z Unpacking how we teach non-determinism in a 30 second attention span economy. Have you stopped and asked yourself during a training or after the question: what did I actually get out of this? That question probably gets harder to answer the longer the training is. https://davenporter.substack.com/p/add-telemetry-and-observability https://davenporter.substack.com/p/add-telemetry-and-observability 2026-08-18T15:36:42Z Telemetry and observability give you the means to start capturing data that make your agent systems long running, and improve their capabilities over time. Most agent examples start with agent instructions, a model, and a few tools, and end there. https://davenporter.substack.com/p/give-an-agent-access-to-memories https://davenporter.substack.com/p/give-an-agent-access-to-memories 2026-08-12T23:52:48Z I gave this talk at AI4 on how to create a memory system for your agents to dream, sharing here in the long form. Philip Dick wrote a short story titled ‘Do robots dream of electric sheep?’. I slightly changed this title for a talk I gave titled ‘Do agents dream of binary sheep?’. https://davenporter.substack.com/p/ai-sdlc-scaling-framework https://davenporter.substack.com/p/ai-sdlc-scaling-framework 2026-07-01T22:27:12Z AI innovation is messy when you're trying to ship. Here are some practical things I've found to integrate AI into your software development lifecycle, from your first customer to your thousandth. A common question I hear these days is ‘how does someone else use AI?’. https://davenporter.substack.com/p/emos-over-memos-enterprise-ai https://davenporter.substack.com/p/emos-over-memos-enterprise-ai 2026-06-24T15:53:09Z Vibe coding and pure prototypes are creating cognitive overload. Here is how enterprise engineering teams must restructure for long-term AI success. I often use the analogy that AI is the equivalent in the workplace of taking the box of 96 crayons, representing the packaging of tasks by role, and throwing the box on the floor. https://davenporter.substack.com/p/how-to-track-ai-agent-lineage-and https://davenporter.substack.com/p/how-to-track-ai-agent-lineage-and 2026-06-16T16:14:04Z Moving beyond clean git commits to knowledge systems for agentic development. “Keep your git commits clean. It’s a goal for everyone, but we always struggle to actually do it. I don’t have enough fingers and toes to count in my individual commits when I’ve tried to fix something and the commit messages become fix and really fixed. https://davenporter.substack.com/p/wibtdwm-a-fools-folly-with-local https://davenporter.substack.com/p/wibtdwm-a-fools-folly-with-local 2026-06-11T19:18:55Z Failures, learnings, and hopefully good next steps to being realistic about developing AI models and methods. When I originally come up with the ‘What I built this ….’ concept, it was about sharing things I built that I thought might be useful with the community make AI and cloud computing things easier. https://davenporter.substack.com/p/with-ai-whats-old-is-new-in-telemetry https://davenporter.substack.com/p/with-ai-whats-old-is-new-in-telemetry 2026-06-09T16:45:40Z Why tracing is critical to improving your AI experiences. I remember a demo with an observability vendor back in 2019. We were setting up a big data app, and they showed us a cool topology map of a request, how it flowed through multiple API’s, and ultimately queried a database we were configuring. https://davenporter.substack.com/p/wibtdml-routing-ai-responses-between https://davenporter.substack.com/p/wibtdml-routing-ai-responses-between 2026-06-04T20:38:51Z Extending smartrouter to support calling local AI models that are a part of a pool of workers, learnings and tribulations, and things I'm planning to do next. I’ve been fascinated with local models more and more recently. These are the open models you can download and run on your laptop. https://davenporter.substack.com/p/whats-worth-learning-in-an-ai-era https://davenporter.substack.com/p/whats-worth-learning-in-an-ai-era 2026-06-02T17:12:31Z How AI has changed the question from how to learn quickly to if learning will be useful. I grew up when the internet in the US was just beginning its widespread adoption and I remember the first time we got high speed internet (we were the first on the block). https://davenporter.substack.com/p/what-im-building-this-week-route https://davenporter.substack.com/p/what-im-building-this-week-route 2026-05-28T16:02:33Z A little router I'm building and improving to use different Gemini (and soon other) models. A question I’ve received a few times recently is how companies can route Gemini API calls based on their own rules and specs. This usually includes a few things. https://davenporter.substack.com/p/can-you-learn-to-use-ai-without-being https://davenporter.substack.com/p/can-you-learn-to-use-ai-without-being 2026-05-26T16:02:26Z Explorations about successful learning patterns for AI and how I'm using it currently. A common pattern I’ve witnessed with developers and leaders over the past 3-6 months goes something like the following. Someone is told they should ‘try AI’ or has some mandate without a goal. https://davenporter.substack.com/p/what-im-building-this-weekmonthquarter https://davenporter.substack.com/p/what-im-building-this-weekmonthquarter 2026-05-21T17:30:15Z This week: How agent skills are improving my session workflows. I’m working on a demo that I’m hoping to share next week. This week’s ‘build’ focuses on where I’ve created a new agent skill in my workflow that helps manage my session information and make my life a little easier. https://davenporter.substack.com/p/ai-and-the-new-business-moat-defending https://davenporter.substack.com/p/ai-and-the-new-business-moat-defending 2026-05-19T16:01:24Z AI requires you to create another moat of advantage. Here are my thoughts about how to do it. I’m fortunate enough each year to lead a number of Google engineers as we build our keynotes. These activities take a lot of time. https://davenporter.substack.com/p/dark-data-is-your-new-most-valuable https://davenporter.substack.com/p/dark-data-is-your-new-most-valuable 2026-05-13T15:21:40Z And why big data is making a comeback to bring data out of the shadows that your agents need in order to be successfully created and trained. Someone asked me a question the other day related to generative AI (because why not AI), and it went something like ‘what do you think is going to be the next trend here in 6 to 12 months?’. https://davenporter.substack.com/p/maximizing-developer-value-using https://davenporter.substack.com/p/maximizing-developer-value-using 2025-07-10T16:00:00Z There’s now a wealth of information and tutorials floating around about how you can go from 0 to 1 with AI, or even vibe code personalized apps or prototypes? But what’s next, and how do we use AI effectively across all parts of our coding development?