James Shore

New blog:

I’ll get straight to the point: your AI coding agent, the one you use to write code, needs to reduce your maintenance costs. Not by a little bit, either. You write code twice as quick now? Better hope you’ve halved your maintenance costs. Three times as productive? One third the maintenance costs. Otherwise, you’re screwed. You’re trading a temporary speed boost for permanent indenture.

Oh, you want to know *why?* Sure. Let’s go for a drive.

https://www.jamesshore.com/v2/blog/2026/you-need-ai-that-reduces-your-maintenance-costs

One CIO I talked to recently, with 170 people in his organization, measured a 2.1x increase in productivity from AI.

That productivity came at a cost. His top users of AI each spent $21,000 on tokens per month. Another engineering leader spends six to eight thousand dollars per engineer per month.

If you’re going to make these tradeoffs—and *somebody* is going to—they need to be good ones. Which raises the question: how do you know what you’re getting?

https://www.jamesshore.com/v2/blog/2026/are-you-getting-your-moneys-worth-from-ai

Hey, did you know I wrote an open source testing framework for JavaScript? It's simple, boring, and very, very detail-oriented.

Its raison d'etre is to provide a better test automation API. I built it after test tool magic bit me in the butt one too many times. I've been using it on my production code for years, but never made a big deal about it.

Anyway, I just released a new version. Check it out if you like simple, well-documented tools that are pleasant to use.

https://github.com/jamesshore/ergotest

I gave a keynote at Agile Cambridge a few weeks ago on "The Accountability Problem." How do we define software department accountability so our business partners don’t do it for us? The transcript of that presentation is now available on my site:

https://www.jamesshore.com/v2/blog/2025/the-accountability-problem

You can learn more about the position and apply here:

• Canadian applicants: https://www.opensesame.com/about/careers/job-openings/#senior-software-engineer-canada

• Latin American applicants: https://www.opensesame.com/about/careers/job-openings/#senior-software-engineer-latin-america

If you 1) have strong XP experience (TDD, pairing, refactoring); 2) have worked with legacy codebases and improved them incrementally; and 3) can mentor other engineers through collaboration, please email me directly after applying so I can hotlist your application. My email address is jim.shore at the domain above.

Thanks for reading!

2/2

Apologies, folks, the link I posted was incorrect. Here’s the correct link: https://job-boards.greenhouse.io/opensesame/jobs/7927745?gh_jid=7927745

If AI is doing the maintenance, do we care how easily a human can understand the code?

Among the people I've talked to, there's widespread agreement that heavy use of AI produces code that humans have trouble understanding. But there's disagreement about how much that matters. This is what we need to measure. Is there an impact? If there is, is it enough to matter?

Ultimately, we want to know if AI usage is sustainable. Part 3 of my series on quantifying AI's impact: https://www.jamesshore.com/v2/blog/2026/measuring-ais-unintended-consequences?source=mastodon

As I talk to engineering leaders, I’m seeing *order-of-magnitude* differences in spending on AI. Should you spend thousands per person per month on hands-off agentic coding? Or hundreds on analysis and fancy auto-complete?

It depends on the outcomes.

You can’t pick the right approach to AI without knowing what you’re getting, and you can’t afford to half-ass this. So how do you measure it?

Measure and compare approaches in part 2 of my series on quantifying AI impact: https://www.jamesshore.com/v2/blog/2026/measuring-ais-impact-on-delivery-speed?source=mastodon