Ask HN: Building LLM apps? How are you handling user context?

I've been building stuff with LLMs, and every time I need user context, I end up manually wiring up a context pipeline.

Sure, the model can reason and answer questions well, but it has zero idea who the user is, where they came from, or what they've been doing in the app. Without that, I either have to make the model ask awkward initial questions to figure it out or let it guess, which is usually wrong.

So I keep rebuilding the same setup: tracking events, enriching sessions, summarizing

27d | Hacker news
Show HN: Directory of 100 SaaS tools that support enterprise SSO (SAML, SCIM)

I’ve been working on enterprise SSO integrations and realized there’s no simple way to check which SaaS tools actually support SAML, SCIM, or OIDC.

So I compiled a public directory of 100+ SaaS apps grouped by category (AI, DevTools, Productivity, etc.). It’s meant to save time during vendor evaluations, especially when dealing with IdPs like Okta or Azure AD.

Happy to share it here if folks are interested. Open to suggestions if there’s a better place to maintain something like this lon

27d | Hacker news

Vyhledávání