Measure them on merit, their body of work and how well they will fit into the team culture.

As for the questions you’re asking, instead of asking old-school coding interview questions ask them stuff that is actually relevant to agentic programming.

Ask them to build a harness, have them explain what skills are, have them build a self-made implementation of Claude Code as take-home assignment.

The times have changed, you need to update interviewing questions to meet them. Start with agentic questions and ramp them up into more complex scenarios. This is how you gauge your candidates, see how they think and solve their way out of it.

Try to determine how creative, adaptable, motivated the candidate is. Figure out what there actual skill-sets are that they can bring to you, not whether they know some CS pedantry

After doing agenetic engineering in anger for about a year now, I'm starting to sour on it quite a bit. If I got this as a take-home, I think I would decline to go further. Watching the atrophy of people's skills and judgement has taught me that I value working with humans who can think for themselves.

Totally agreed. Burying head in the sand which a bunch of the industry seems to be doing is a recipe for disappointment and dissatisfaction with the changing tides.

Try to ride the wave rather than being swept under.

AI is coming for hardware. I’m 2 weeks into working with ESP32 devices using nothing but AI and my intuition to build new firmware for the type of hardware I want to build. Haven’t touched electronics for 10+ years since uni.

Could be producing a bunch of slop but that’s where the decades of engineering experience comes in to still find a way to ship reliably.

yeah, its like coaching a kid

> This work flow really took away my passion and joy of writing and building software systems.

With agentic development and senior experience you are now able to write and build systems that are 100x more complex and powerful. You’re no longer thinking about how to some mundane data massaging or crud - rather you can spend time thinking about how to solve actual problems that matter and have an impact - as a solo engineer!

Got a problem with climate change? Start brainstorming.

Want to model how a chemical factory works to simulate its IoT topology? It’s at your fingertips.

Think bigger. A lot bigger. Forget about the trees. Look for the forest.

Your decade plus of engineering experience combined with AI is a super power many other new comers to game would benefit from. Capitalize on it and do something cool.

That's true, and thanks for shedding light in a positive direction :)

"Forget about trees. Look for the Forest" - linesofcode

I should frame this on my wall

There’s nothing you can do to stop this. If your stuff is on the internet it will be crawled.

Don’t want the LLMs or anyone else to gobble up your project then keep it private.

The licenses are a gentleman’s agreement in a world of no gentlemen.

It’s implemented. You can build teams across generations or even build a deck or binder.

Also check out the comparison feature.

Totally! I was copy and pasting screenshots to Claude endlessly. Also this lets you do a more intentional review, build up a batch of changes and then fire them at the agent in one go. Or give the devbar to a non-tech person on the team and have them export a PDF / HTML / Markdown of their notes, mapped to a screenshot and an x-path automatically.

Thanks! Please let me know if there’s any questions or bugs or feature requests!

Use AI to tackle larger projects and complex problems, that’s how you’ll get your competitive edge back. There have to be freelance projects beyond CRUD.

The “competitive edge” these days is partially being a domain expert, try to find a niche you can grow and learn in. It could be some industry or some tech, but that’s how you differentiate yourself in the LLM age, not by writing code.