Please don't take offense to this very dumb question:
Why can't you do the planning ? Figure out what needs to be done , break it down into small tasks and then ask the agent to execute those small tasks?
When we executed projects in the past, this is what I would do as a lead: figure out the overall software architecture and delegate the tasks to developers.
This way I always knew how the system worked and could extend it as needed. I am not in development role anymore but I am trying to understand why we are delegating planning and software architecture to coding agents?
Has anyone used Keycloak for actual production? I have often thought about it but I stick to Auth0 just because I don't know if Keycloak has a good track record?
I am not following this obsession with SOTA and benchmark rankings
I have been using DeepSeek and GLMnmodels with OpenCode and Codex and Claudr side by side.
I have not found the Chinese models lacking. I enjoy for coding and like to maintain full control of my codebade and deeply care about the GOF patterns. So I am very stringent in terms of what I want the LLM to code and how to code.
So from my perspective, they are all about the same.
Humans are accountable to each other. Humans can be shamed in a code review and reprimanded and threatened with consequences for sloppy work. Most,
humans once reprimanded , will not make the same kind of mistake twice.
I used to be a big advocate for Salesforce in my organization. And it was really great .. allowing us to deliver new functionality without the usual IT procurement bureaucracy.
Now with cloud maturity and Vibe coders who will get better and cheaper, I think it's possible to replace all the features we use on Salesforce at a fraction of the cost of our Salesforce licensing cost.
Gemini's large context window is incredible. I concatenate the my entire repo and repos of supporting libraries and then ask it questions.
My last use case was like this : I had a old codebase code that was using bakbone.js for ui with jquery and a bunch of old js with little documentation to generat UI for a clojure web application.
Gemini was able to unravel this hairball of code and guiding me step by step to htmx. I am not using AI studio; I am using Gemini subscription.
Since I manually patch the code, its like pair programming with an incredibly patient and smart programmer.
For the record, I am too old for vibe coding .. I like to maintain total control over my code and all the abstractions and logic.
I had Gemini ingest our huge aws cloudformation repo . I had it describe each infrastructure component and how it related to others and creation hierarchy and IAM.
I got a nice and comprehensive infrastructure requirement document out of this.
Now I am using it to create Terraform repo , deploying it via OpenTofu and comparing it to my existing AWS cloud formation . This part is still a WIP .
However, the cost of software maintenance went up by 1000% . Lets hope you don't need to ever add a new business rule or user interface to your vibe coded software.
I am curious : could GenAI have written the paper "Attention is all you need"? We were trapped in CNN RNN architectures for a while : could genAi have arrived at a better architecture ?
BS. I grew up in Delhi. We used to have a large open space where I and neighborhood kids used to play cricket . Eventually the whole area converted to slums with people from Bangladesh. They took over the whole area. I was too young to care about ethnicity but the loss of my cricket field still bothers me. My neighbor was a bank manager and he once said that the government politicians forced him to give "loans" to Bangladeshi people , with no documents and only their thumbprint,before elections to those people to ensure victory of the ruling party.
Mass Unemployment with no healthcare or supporting social services , very few opportunities and lots of guns.
It will not be ok.