on the tech, just the floatiness code, I'm not frontend dev but I knew what I wanted. Content: personal quotes from various sources, usually voice notes, therapy sessions, journalling, attempting to write. I've used claude to help me check tone, consistency, etc and sometimes followed its suggestions but the content is my particular brand. I do use AI (claude/notebookLM) a lot to analyse stuff though
It really depends by what you mean by "it works". A retrospective of the last 6months.
I've had great success coding infra (terraform). It at least 10x the generation of easily verifiable and tedious to write code. Results were audited to death as the client was highly regulated.
Professional feature dev is hit and miss for sure, although getting better and better. We're nowhere near full agentic coding. However, by reinvesting the speed gains from not writing boilerplate into devex and tests/security, I bring to life much better quality software, maintainable and a boy to work with.
I suddenly have the homelab of my dreams, all the ideas previously in the "too long to execute" category now get vibe coded while watching TV or doing other stuff.
As an old jaded engineer, everything code was getting a bit boring and repetitive (so many rest APIs). I guess you get the most value out of it when you know exactly what you want.
Most importantly though, and I've heard this from a few other seniors: I've found joy in making cool fun things with tech again. I like that new way of creating stuff at the speed of thought, and I guess for me that counts as "it works"
I bill myself as a consultant now. What I actually am is a guy who copies error messages into Claude and pastes the answers back into production systems. Last month I invoiced $67,000 doing exactly this.
The weird part isn't that it works. The weird part is how boring it's become.
It's already happening, and they're realising it's a lot more unsexy than using chatGPT, requires skilled people, cross team collaboration and deep shared understanding of processes and workflows.
I've had the same experience, cross-department shadowing at a listed fintech. It worked tremendously well... For 3 months until they invoked "too many meetings" rule to shut it all down.
IMO it died because it exposed how many people's entire job was controlling information flow. The "useless humans" you mentioned? Their job security depends on being the bottleneck. If developers understand customer problems directly, what's the PM doing all day? If sales knows what engineering can actually deliver, why do we need three layers of "roadmap prioritization"?
When engineers can talk directly to customers, when support understands the product, when sales knows what's actually possible, suddenly half the middle management layer has nothing to do.
I've been talking the a bunch of tech execs recently in and while they all talk exclusively about AI, they seem to have blinders on to the fact that their staff is using their personal GPT all day long... meanwhile the early messy adopters have already started to pull ahead and get results, mainly in tackling the bottom of backlog pain in the ass tasks, automating ops, SRE, improving safety, DevEx, and more. What's the story in your workplace?