Comment by CharlieDigital
1 month ago
> Agentic search
All you've proposed is moving the context problem somewhere else. You still need to build the search index. It's still a problem of building and providing context.
1 month ago
> Agentic search
All you've proposed is moving the context problem somewhere else. You still need to build the search index. It's still a problem of building and providing context.
I disagree, these search indexes already exist, they just need to be navigated much how Cursor uses agentic search to navigate your codebase or you call Perplexity to get documentation. If the knowledge exists outside of your mind it can be searched agentically.
what do you think about these guys: https://exa.ai/
Crawling web data is ETL. I think the case stands: the winners in AI/LLM SaaS startup space are the ones that really do ETL well. Whether that's ETL is across an enterprise data set or a codebase.
The AI and LLM are just the the "bake" button. If you want anything good, you still have to prep and put good ingredients in.