Everything I've written on The Davenporter, newest first. Most posts start with a question someone asked me, then work through what I've tried, what broke, and what I'd do next. The WIBTM series covers what I'm building right now, and why.
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.
Why git and AST’s have some relationship, and what’s next when it comes to systems that are agent-first.
And how it can keep us in the high value areas of AI engineering.
AI is still a business transformation problem, and its out-kicking the product coverage.
A conceptual map of how to establish provenance for agent decisions using the existing tools we have today
Unpacking how we teach non-determinism in a 30 second attention span economy.
Telemetry and observability give you the means to start capturing data that make your agent systems long running, and improve their capabilities over time.
I gave this talk at AI4 on how to create a memory system for your agents to dream, sharing here in the long form.
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.
Vibe coding and pure prototypes are creating cognitive overload. Here is how enterprise engineering teams must restructure for long-term AI success.
Moving beyond clean git commits to knowledge systems for agentic development.
Failures, learnings, and hopefully good next steps to being realistic about developing AI models and methods
Why tracing is critical to improving your AI experiences
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
How AI has changed the question from how to learn quickly to if learning will be useful.
A little router I'm building and improving to use different Gemini (and soon other) models.
Explorations about successful learning patterns for AI and how I'm using it currently
This week: How agent skills are improving my session workflows
AI requires you to create another moat of advantage. Here are my thoughts about how to do it.
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.
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?
cosm locks functions instead of files so several agents can edit the same codebase at once.
| Theme | Essay | Code |
|---|---|---|
| Why your coding agent needs a blast-radius tool | WIBTM: What happens when you let an agent design a new git system? | davenportjw/cosm |
| How I built a self-improving coding system | Give an agent access to memories... | davenportjw/agentic-memory |
| The warehouse and hybrid model routing | WIBTD/M/L: Routing AI responses between local and cloud models | davenportjw/smartrouter & warehouse-dash |