James Hurburgh

💻🥩☕🎲✝️🇦🇺👫👦👧👦👦👧
Developer. Carnivorous caffeinated board game loving Australian Christian and very happily married father of five. Opinions are my own

[James Hurburgh @JamesHurburgh]

@mattpocockuk Wait till some tries to turn this observation into a skill. :(

[Steven Tey @steventey]

STOP ASKING YOUR WIFE "HOW WAS YOUR DAY"

she will say "fine" every single time

replace it with this instead:

“analyze your day and find the top 3 largest inefficiencies, then create proactive agentic workflows that will fix them. make no mistakes”

[James Hurburgh @JamesHurburgh]

@ledgerwhatuknow @elonmusk I'm doubtful. Convince me it's better than Civ 5!

[James Hurburgh @JamesHurburgh]

@mattpocockuk I'm learning new things every day. Makes me feel like I'll never know everything, which is probably true anyway, but conversing with agents seems to be an accelerator to learning the most relevant concepts, provided you can adequately steer the conversation.

[James Hurburgh @JamesHurburgh]

@plainionist Interested how it goes. We've been doing C4 models by hand so it was as easy as just feeding our standards into @mattpocockuk's writing for agent skill and then using that skill to get it to update our C4 diagrams.

[Michael Lawrence @michael_c_law]

Being a senior developer in 2026 is being the person who remembers
why we don't do that, and explaining it to an AI that just did it.

[James Hurburgh @JamesHurburgh]

@simonbrown Oh man. I love using my agent to make my C4 diagrams with puml. Just gave it the standards and chatted to it until the model in my brain was reflected on the diagram.

[Matt Pocock @mattpocockuk]

Tactical vs Strategic Programming, and why I'm nervous for juniors:

Good programming involves a mix of tactical and strategic decision-making:

- Tactical: on the ground, short-term. The soldier doing the fighting.
- Strategic: high-view, long-term. The general planning the war.

You need to be a tactician to write good code. To choose the right syntax. To figure out the file structure. To figure out how best to test your changes.

But you need to be a strategist to build code that lasts. To design the architecture. To automate away problems. To think beyond today.

Agents have eaten the tactical part of programming. When you can pay below minimum wage for code, there's no point going into the trenches yourself.

But AI cannot code strategically. Agents need someone at the top of the pyramid to tell them what to do. They need oversight.

So, a developer's day-to-day job has become 100% strategy. Long-term thinking, all the time. (maybe this is why I'm so tired all the time now)

If you identify as a tactical programmer - a code monkey - then you are out of luck. The job has changed.

Personally, I like it. I always preferred thinking strategically about code. If you asked me what my job was about, I'd say 'building apps', not 'writing code'.

But what makes me nervous is that we've pulled down the only bridge that brought juniors into the industry.

We used to train juniors like this:

1. Give them only tactical tasks
2. Let them build up their strategic experience slowly

Eventually, they are a good enough strategist that they are no longer a junior.

But what happens when all tactical code is written by AI? What is the point of a junior?

We obviously need juniors. We need new lifeblood coming into the industry. We need to leave paths open for extraordinary hires to enrich our companies.

But how do we train them? How do you train strategic thinking?

These are the questions I'm thinking about. I'd love to know your thoughts.

[James Hurburgh @JamesHurburgh]

@dotnet What is this AI slop post meant to achieve?

[James Hurburgh @JamesHurburgh]

@plainionist @mattpocockuk /grilling
No contest.

[James Hurburgh @JamesHurburgh]

@mattpocockuk I love that all your skills encourage the agent to guide the conversation towards the goal instead of making assumptions and trying to one-shot everything. The conversations are where I'm getting the most value.
Any tips on that aspect of writing skills specifically?

[James Hurburgh @JamesHurburgh]

@plainionist When I can justify the cost of the tech.

[James Hurburgh @JamesHurburgh]

@SchipperAI @mattpocockuk How's this working for you? I've taken a workflow approach and only just tried it once, but the results were what I was expecting. https://t.co/un0ewYQRV6

[James Hurburgh @JamesHurburgh]

@stillpointlab @mattpocockuk This is my instinct as well as it's how I think, and for agents this might work. It might even work most of the time. But the agent will still be burning tokens reading (and adding to the context) irrelevant and incorrect information.

[lauren @poteto]

every time you intervene and correct your agent, you should think about how to eliminate it entirely.

in order of value:
1. categorically eliminate the problem through better architecture or choice of data structures
2. turn it into a lint rule or test so CI catches it
3. turn it into a skill or rule
4. have humans review the code to catch it (ngmi)

[James Hurburgh @JamesHurburgh]

@BenoBilo61874 @mattpocockuk @theo It's more expensive not using them IMHO.

[James Hurburgh @JamesHurburgh]

@mattpocockuk @fil_ships I've found them especially useful for finding where the concept isn't being used correctly as well.

[James Hurburgh @JamesHurburgh]

In order to improve over time, you need metrics to measure that thing. If you use the wrong metric you optimise for the wrong thing. Good engineers aren't always the greatest technical minds, but they have taste in what 'good' looks like.

[James Hurburgh @JamesHurburgh]

@gdb Why don't they just get their own bot to respond?