Hey, Luca here! Welcome to a new edition of the 💡 Monday Ideas 💡 — ideas and readings to start the week on the right foot.
🔀 Open-source workflow orchestration
This newsletter is brought to you by our friends at Kestra!
Last week I published this primer about workflow orchestration, together with the team at Kestra, which builds a great open source platform to scale AI agents into more deterministic and observable workflows.
I have been playing with it to replace some of my OpenClaw chaos cron jobs, and I am pretty happy with the result so far! Will probably write more about it in the future.
You can learn more about Kestra below 👇
💡 ADRs are the reviewable artifacts of AI coding
Last month I wrote that the most recent and most valuable addition to my AI coding workflow have been ADRs.
Since then, I realized they are especially valuable because they help turn design judgment into reviewable artifacts. What does it mean?!
I don’t want to inspect every line of code an agent writes, but I can definitely review a short decision record that explains the chosen approach, alternatives, consequences, and what would trigger reconsideration. This gives me a way better control point than reviewing code details in isolation.
ADRs also improve future agent work. Before making a structural choice, the agent can read past decisions, reuse the system’s current principles, and avoid debates that were already settled.
I especially like that ADRs are immutable. When a decision changes, the agent creates a new record that supersedes the old one, instead of rewriting history.
As of today, Tolaria has 120+ ADRs. Are they perfect? Not at all — but they don’t have to be. They are good enough to 1) make me understand key design choices, and 2) steer agent behavior to make it compliant with what exists.
You can find the full article below:
🎙️ Use AI by default to learn its failure modes
Speaking of AI coding, last month I interviewed Stuart Caborn, Distinguished Engineer at loveholidays, and one of the few tech leaders I know that is really doing it at scale, documenting the process.
One of the things he told me is that teams do not learn how AI works by waiting for perfect use cases.
They learn by using it by default, even in moments where typing the code directly would be faster. This sounds inefficient locally, but the point is building the feedback loop, rather than optimizing the single task.
Stuart explains that every failed AI attempt teaches the team something: which instructions are missing, which docs are unclear, which conventions are invisible, where the agent needs guardrails, and so on.
Stuart cares about making failures public, instead of private, and for this, he creates pressure for the failures to surface. The team runs showcases, shares patterns, and even forces engineers to go through AI before asking for human support 👇
“At one of the platform showcases, the core engineering team said: we’re not going to support you if you have a problem with your Terraform, if you haven’t asked Claude to do it first. That was bold — but the reasoning was: we need the feedback now.”
You can find the full interview here:
📚 Weekly Readings
Finally, here are the best articles I have read this week:
🥇 Sensors for Coding Agents
15 min • by Birgitta Böckeler
Great primer on using sensors — like ESLint rules and static analysis — as feedback loops for coding agents. The idea is that agents need guardrails to maintain code quality, and these automated checks act as their “senses” on the path to production.
🥈 Apple Silicon Costs more than OpenRouter
5 min • by William Angel
Yet another reminder that, for 99% of us, running LLMs locally makes absolutely zero sense. This time backed by numbers.
🥉 Not So Locked In
2 min • by Simon Willison
Programming languages used to be lock-in — they’re increasingly not. LLMs are making it feasible to port entire codebases across languages and frameworks, which changes how you think about tech choices, risks you can take, and more.
And that’s it for today! If you are finding this newsletter valuable, subscribe to the full version!
1700+ engineers and managers have joined already, and they receive our flagship weekly long-form articles about how to ship faster and work better together! Learn more about the benefits of the paid plan here.
See you next week!
Luca
The supersede-rather-than-rewrite property is the part of ADRs that maps best to agent ergonomics. An immutable record of design intent gives the next agent a stable retrieval target, while a line-level diff history forces it to reconstruct intent from edits and dates. Tolaria at 120+ ADRs is a useful ceiling test for whether the review surface scales without becoming the new bottleneck. The Caborn point about forcing AI by default to surface failure modes is the human-process complement: without that pressure, the decision records never get written in the first place.
I think this is where AI changes career value too. The people who win are not just the ones who can produce more output. It’s the ones who can make judgment explicit enough that other humans and agents can reuse it.
That applies way beyond engineering. Product specs, GTM decisions, strategy docs, customer segmentation, pricing logic, ops playbooks. Same pattern: if the reasoning is not inspectable, AI mostly accelerates confusion.