Nitish Kumar

Glad to meet you guys again! During Creaibo s private beta, I noticed a common problem among AI-native creators: the creative workflow is long, and while different tools boost efficiency at each stage, the context between stages prompts, asset images, still frames, storyboards, etc. is scattered everywhere. Syncing them is a headache every time.

The essence of creation is context alignment. The more fragmentation, the harder the alignment. That s why Cora came to be.

Bitgrain is playing a bit off the field. We are aiming towards a "No AI" tool, whereas almost every other product currently targets the AI market.
This has been both, good & bad at the same time. Good because I found lots of like minded people willing to support this. Bad because again, a lot of people don't actually support this in the era of "AI Boom".
Yeah that's the direction Bitgrain is proceeding in. If it works, great. If it doesn't, then too great : )

I've been working with LineageLens and just added a custom agent adapter so our internal CLI tool is attributed with prompts, model metadata, and confidence evidence. The registry design makes this surprisingly low-friction: implement a detect(input) that returns a NormalizedAgentContext (tool name, model, session ids, confidence, and evidence), register the adapter, then run the quickstart proxy to validate captures.

Why this matters: your team can capture private or bespoke tools without sending data to a vendor, and you get prompt code linkage in PR reviews and dashboards. I followed the recent repo changes (custom agents landed in late May) and found the adapter API predictable: detection should be conservative, emit evidence items, and choose appropriate ordering so your specialist adapter wins over the fallback.

If you ve extended LineageLens for an internal tool, what heuristics did you use to build confidence and avoid false positives?