팀이 Claude Code / Codex / Cursor를 함께 쓸 때 컨텍스트는 어떻게 공유할까?
Claude Code, Codex, Cursor, Windsurf all seem to have slightly different ways of handling project context, rules, memories and session history.
Capability gaps raised again and again inside AI developer communities.
Claude Code, Codex, Cursor, Windsurf all seem to have slightly different ways of handling project context, rules, memories and session history.
Functionally, Cursor is doing a good job… The problem is visual design. No matter how detailed I make the prompt.
We found ourselves frequently switching between different coding agents (Claude Code, Codex, Cursor) anytime we ran out of usage limits or a newer model came out. We became increasingly frustrated with having to re-explain our tasks, workflows, common mistake patterns, etc. anytime we switched agents.
I want to resolve it against a large list of known breeds (400+) and pick the closest one from the list.
I really need some way for users to purchase usage for my chatbot… a way to buy a ChatGPT Card or Gift Code that can only be used by my service.
Users could send an email to initiate a conversation, and the model would respond via email once a reply is formulated.
Share ideas like clearer documentation, detailed logging and better error diagnostics, expanded token limits…
We need to extract a text string from documents… 20 different formats and sometimes needs OCR. Is there an API that does this for you?
I find myself switching between ChatGPT voice mode on my phone and Codex a lot to copy and paste requirements I've brainstormed.
Looking for a Babelfish: real-time speech-to-speech translation on an Android phone, fully offline and open source — set the output language, talk to the phone in English, and it speaks the translation.
Converting German text to speech, even OpenAI and ElevenLabs make lots of mistakes — '74000€' and '1.' come out garbled, so users hand-rewrite the text.
Google Voice SMS forwards to Gmail with the subject 'New text message from ...'. I want the subject to summarize the text, like 'Request: Pick up milk'.
High-end phones have embedded LLMs accessible via AICore, usable offline. I'm building an app on this SDK and want to crowdsource real responses across devices.
3rd parties we're working with have no way of knowing if we generated those responses ourselves… there are implications.