Paul Stack

Infra Coder with a militant interest in DevOps and Systems Thinking. Speaks with a funny accent. **Evangelist of Life**. DAF

[Paul Stack @stack72]

So @currys is a perfect example of how AI can be integrated incredibly poorly into your system. An automated response to my tweet meant that I messaged them back and now I have another AI but trying to interact with me via DM.

[Paul Stack @stack72]

@daveremy Yeah same thing for me - 4.7 was a token killer and 4.8 feels poor

Has opus peaked at 4.6….

[Paul Stack @stack72]

@currys one of your customer support staff hung up on my after I insisted on speaking to a supervisor. I’m incredibly annoyed at this considering it was a curry’s systems issue that caused the problem with the order

[Paul Stack @stack72]

Every production environment has someone who can't go on holiday without their phone buzzing. Not because the team is bad. Because everything that person learned from incidents over the years never made it anywhere except their head.

That's not a people problem. It's an encoding problem. New post on why this is the first thing to solve before AI agents go anywhere near your infrastructure.

https://t.co/Zv3q5frHFz

[Paul Stack @stack72]

@mlvnd :) Thanks for reminding me to update my bio!!

[Paul Stack @stack72]

The sovereign cloud movement has an $80B budget but the the cost to switch is the real blocker to make it happen. Your automation is coupled to your provider. Moving means rewriting everything for zero new functionality.

We started replacing our GitHub usage with Forgejo and in a couple of days it was working (including actions replacement). Two years ago that's a quarter-long project. The implementation was straightforward. Being precise about what we actually needed was the real work.

https://t.co/Rvi1MhG3e0

[Paul Stack @stack72]

Getting agents to generate IaC code faster isn't the answer. It's still probabilistic output driving your infrastructure. The agent doesn't know your conventions or your breaking changes. You won't know how well it guessed until apply time — or until you have to review and debug it.

What if agents worked against typed schemas instead? No code generation. Deterministic execution. Same inputs, same result, every run.

https://t.co/wKw7fptgfX

[Paul Stack @stack72]

A lot of the stories about AI agents failing come down to two things:
* no trust (gates everywhere, agents wait for permission)
* chaos (everyone ships, nobody coordinates).

The fix isn't better tools. It's building the systems that make trust safe.

https://t.co/iEcDbt7LSF

[Paul Stack @stack72]

@sudomateo yeah Forgejo is really nice! I am writing a blog post about how I ran it end to end with swamp on DigitalOcean

[Paul Stack @stack72]

I'm not sure why but @claudeai has starting asking me for permission to use a skill... that seems new the past couple of days - anyone seen that? I am going to try adding to settings.json to bypass it but it feels a UX step backward

[Paul Stack @stack72]

Bug reports that looked like noise turned out to be three compounding architectural problems. In a traditional team, you patch and move on.

We had agents, so we rearchitected the whole thing. Six parallel workstreams, eight days, landing to main the whole time.

If it hadn't worked? Eight days lost, not six months.

https://t.co/qiZepXT9Re

[Paul Stack @stack72]

Every team gets told to ship faster. When agents make that trivially easy, speed stops being the problem and direction does.

Planning as we know it is meaningless. Your PM is about to have an existential crisis.

The hardest skill now is taste. And that's not something an agent can help you with.

https://t.co/f8FomPH0NF

[Paul Stack @stack72]

I've been writing about how AI agents changed my work. Stopped typing code, started making better decisions, how we are building swamp with agents doing all the implementation.

The fear is real. The shift is real. The difference is structure.
https://t.co/lwlLjpZbaI

[Paul Stack @stack72]

I haven't written code in months (probably for the best). Five of us build swamp, none of us write code manually.

The job got bigger, not smaller. The code was never the job — the understanding was.

New post up: https://t.co/RBIajkW5fU

[Paul Stack @stack72]

An agent can open a PR in thirty seconds that takes an hour to review.

Multiply that by every repo with an issue tracker and you have the current state of open source.

We banned external code contributions and here's why.

https://t.co/SLitOEVaEP

[Paul Stack @stack72]

@ccollicutt Delighted to hear that it’s given you some ideas :) thanks for the kind words

[Paul Stack @stack72]

4,236 unit tests passed yet the binary was broken.

A separate UAT suite running against the real compiled artifact caught it in four minutes. Three recent bugs, same pattern: all unit tests green, bug at an integration seam, no user ever saw it.

https://t.co/FcR7i37Iq2

[Paul Stack @stack72]

@fiunchinho great question! I found that by having bash and then gh pr * in the ask, I wanted to be specific that gh pr checks was allowed - it's just about trying to be very specific over what's in the ask

[Paul Stack @stack72]

I sorted every agent tool into two buckets: can git checkout undo it, or does it touch something external?

Eliminated 90% of permission prompts. Kept the ones that matter like gh pr create.

https://t.co/UbxtIRbNti