Rahul Patil

Hi @lovable , I dont want to use your Lovable Cloud, I want all my tables and backend to be connected to Supabase, however the app doesn't allow me to? Worst of all your lovable cloud doesnt allow me to connect to the database? I dont see any connection details

@ForrestPKnight More than 90% at this point! Not sure if this is right, but at this point I ask the agent to code and instead of checking each and every line of code, I just check if the feature is working, and if it works it works! However I have added a lot of guard rails on the agent

it's been 6 months... is AI writing 90% of your code?

@budapp Hey cant wait to test it out! we currently use Claude as backend engineer and Lovable as our front end

@sama to try it right away, make sure to first update codex cli to v0.36.0: `npm install -g @openai/codex@latest` and then run codex with: `codex -m gpt-5-codex -c model_reasoning_effort="high"`

Is it me or the new OpenAI responses api is kind of similar to the apple ecosystem. The new API is soo good for building tools and agents but the catch is that you can use only OpenAI LLM's. Fair on them to try to push and make their product better but you get locked in to OpenAI

I have to build an agentic workflow for a product. Its main task is based on users prompt it should choose from a bunch of tools available to it and run them in a particular order decided by an LLM. Split between using the OpenAI Responses API vs Langchain. Any recommendations?

@GeminiApp @Google #Gemini #GoogleAI

Was trying the Gemini Banana Model. It looked so promising at first for image editing. But when asked to remove a simple shadow from below the car it failed! Tried this was all prompting strategies but I simply cant get it to work! Is it just me or am I doing something wrong?

the best part! the repo at a bird eye view conneected to a data source and published it to various consumers. Claude asked me at the end if I want simulate the remote data source locally for testing by creating a config to redirect the connections

I primarily code in python everyday however today I had to work on a hefty GoLang Repository. I have 0 knowledge of golang and have never worked with it before. I spent about 10-15 minutes trying to understand the codebase and even though I understood the overall process.. (1/N)

the documented it crated was so thorough! ait was a like getting a KT from a senior developer regarding the repository It had everything from how to install with the exact version followed by documentation for each api along with its parameters and data types

It was time consuming for me to understand the details of API such as the allowed params. authentication the detailed conditions and fallbacks for each API. So I asked claude to generate a detailed readme for the repo with steps to install and a detailed doc for each API used

One thing that I found useful with claude is to give it a feature and ask it create a detailed implementation plan in a "planning.md" file. Then as a follow up prompt ask it to refer the planning file and implement all the steps. Makes fewer errors!

I am trying to make a conscious decision where even though I know 95% of my code will be written by agents, I will fix atleast small bugs or understand what the agent is writing. No more a game of if it works it works! I need to know why and how it works

I was vibe coding yesterday and I reached my api limit on claude and codex which rarely ever happens. But then I still had some bugs to fix and then panic set in on how to fix these, I started looking for low cost agents like grok code fast to solve those bugs (1/N)

These bugs would have been trivial for me a couple of months ago. But the dependency we are building on agents is scary! The balance between me being a lead coder and the agent being an assistant has slowly tilted over to the agent being lead and me being just a passive observer

But for some reason the agents were not working, I was having some connectivity issues and then more panic set in because the bugs needed to be solved asap. After panicking for about a minute I realized I AM A CODER. I have created entire systems by typing each and every line

@ganeshsonawane A not so flashy one! But an AI powered logistics management system that can identify bottlenecks or gaps in system based on historical data and current conditions and alert in real time in case of delays and provide alternative routing solutions and escalations

Frido AI powered products coming soon!

@immad Most trekkers in India go solo. Our platform makes trekking social—discover treks, see who’s going, connect with groups, share stories and book directly, creating a community-driven hub for trekkers with revenue via operator bookings.

Respond to this tweet with a startup idea. I will tell you whether I would take a investor meeting or not and why for that idea, assuming it came in from a strong warm intro. I can tell in 280 chars whether an idea is interesting to me and why. Maybe it will be useful feedback.

With enough context codex cli is actually pretty good given that it does not have any limits. In general Claude will outperform Codex however, claude has a very conservative limit and it refreshes every 5 hours, while codex doesnt have any such limits!