All activity
Kavin Jeyasankarleft a comment
I really like the framing around trust and visibility. How do you think about preventing context drift over time as users keep adding and rearranging material? Does the system help users notice when the AI’s “mental model” starts diverging from theirs?
DessixVisual workspace to capture, organize, and create with AI
Kavin Jeyasankarleft a comment
This looks clean! How do you handle long-running conversations as context grows? Do you summarize, chunk, or apply any memory pruning over time?
Conversation API Build chatbots with memory using just an API
Kavin Jeyasankarleft a comment
Under the hood, Trainly focuses on graph-first retrieval instead of flat embeddings, which makes multi-hop questions and source tracing much easier. Curious how others here are handling complex document reasoning today.
TrainlyGraph-native RAG that turns chats into production APIs
Kavin Jeyasankarleft a comment
Hey Friends 👋 Trainly came from frustration. I wanted an easy way to build a RAG pipeline I could trust and ship, and I kept wishing ChatGPT’s Custom GPTs had APIs so I could actually use them in apps. They’re great for exploration, but not production. So I built Trainly to turn knowledge into structured graphs, make answers traceable, and let any chat become an API. It’s meant to be the...
TrainlyGraph-native RAG that turns chats into production APIs
Trainly is a graph-native RAG platform for developers building production AI apps. Go to prod in less than 2 minutes.
TrainlyGraph-native RAG that turns chats into production APIs
Kavin Jeyasankarleft a comment
Hey guys, I'm building a tool to help students learn more effectively. Please let me know what you'd like to see in the future.
EduPlayEducational video playlists