I've read several comments in the last few months citing this kind of approach. What I'm trying to do is to make the implementation phase more reliable.
By the way, if you're not doing that yet, something that can really help when doing UI/UX work is to have the agent create some mockups, and then tests based on those - I'm using Cucumber with some extra sauce for this. It's a very nice way to guide the agent in a falsifiable way.
But seriously, if you care, this is just like using an existing library to do the lower level development work which I think is already pretty well done by the existing agents. It's not a design decision.
Interesting. From time to time I'm thinking about completely replacing the agent layer with my own, so that I would be able to enforce some rules at a lower level, but I'm wondering if it's worth it. What's been your experience with that?
Yes, like many others I've been experimenting a lot. What I've got so far is a harness-of-harnesses - ie, a harness which sits on top of Claude Code, Codex or OpenCode. I still use Claude Code or Codex directly for the initial planning of features, to investigate issues, and for small fixes, but whenever there's something even just a bit complex to do, I use my second-level harness.
Summarizing it a lot, what it does is:
* help you make better plans
* split plans into iterations, in a module-aware way for projects which have strict modularity (for now I'm doing this specifically with TypeScript and dependency cruiser) - this helps a lot when a project becomes complex
* ask an agent to implement an iteration, and then programmatically run a lot of checks after each iteration - not just regression tests, but also checks against project principles and conventions
* when possible, automatically fix deviations; when not possible, raise them to myself for an end-of-plan review
In this way, instead of having to constantly be engaged with the chat interface, with all the shorter or longer wait times which break my flow, I spend a lot of highly focused time during initial planning and final review. A plan implementation can go on for hours, and the various anchoring mechanisms added to the tool keep drift to a minimum.
At some point I'm planning to release this tool as open source. As this is the result of months of trial and errors, dogfooding, and vibecoding on the tool itself, the codebase is chaotic and the UI is still full of experiments I mostly basically abandoned, and I'm not used to releasing stuff in this status. But perhaps, in this brave new world, I should just do it and see what happens?
No, we shouldn't act like (stupid) children. We should enact a transition based on what we can do and when. I know that nuanced and complex solutions to complex problems don't fire up voters anywhere, but that's the only way to not shoot our own feet.
Of course life isn't fair. But here the result is that companies will ignore potentially great candidates which dedicate all their programming time to their job and instead consider candidates which may be not just worse programmers, but also are more interested in their hobbies (or padding their CV) that doing their job.
I'm saying this as somebody who most of the time has some side project going on.
What will happen is that the EU will start treating the US as a hostile nation, develop its own computer tech to replace American tech (probably together with Japan, South Korea, Taiwan, UK, Canada, Australia) and THEN they will start denying ASML tech to the US. Bullies always think that there will be no consequences to their bullying... until they find out.
According to this logic, Taiwan should keep the most advanced chips to itself, the EU should keep the most advanced chip lithography machines to itself, etc etc.
It will almost for sure surpass the models which Trump will allow US "allies" (which he just considers client states) to use. This, together with China's growing dominance in PV, rechargeable batteries, EV, could really be the nail in the coffin for the post WWII economic world order.
Even when the UK was in the EU, you could create a limited liability company (LTD) for something like 200 pounds or less, no capital needed. So it's not true at all that setting up a business at a low cost is somehow against EU legislation.
By the way, if you're not doing that yet, something that can really help when doing UI/UX work is to have the agent create some mockups, and then tests based on those - I'm using Cucumber with some extra sauce for this. It's a very nice way to guide the agent in a falsifiable way.