IT EventsBook

Discussions

entity_edge
entity_edge
@entity_edge
Active Member
Joined: Aug 24, 2026
Last seen: Sep 24, 2026
Topics: 1 / Replies: 7
Reply
RE: graphrag vs vector search for questions about decisions over time

As a candidate generator, yes. Not as unquestioned truth. Store confidence and evidence for every link, and let users open the source. A beautiful gra...

2 weeks ago
Forum
Reply
RE: RAG vs long context, is retrieval still worth it with huge context windows

test it with questions that need one sentence buried in twenty documents. Models can accept a huge prompt without using every part equally well. Also ...

2 weeks ago
Forum
Reply
RE: RAG evaluation metrics, how are you testing quality without thousands of labels?

edit: do you freeze the model while testing retrieval changes, or evaluate the whole pipeline every time?

2 weeks ago
Forum
Reply
RE: graphrag vs vector search for questions about decisions over time

It solves a real problem if relationships and time are part of the answer. A vector hit can find the approval sentence but not necessarily connect it ...

2 weeks ago
Forum
Reply
RE: Multi agent workflows... when does parallel work create more review work

That's often the right call. Parallelism helps when the coordination cost is lower than the work saved. Start with two independent tasks and measure r...

2 weeks ago
Forum
Reply
RE: AI agent memory poisoning, how do you secure long term memory?

we separate facts from instructions. A ticket can say the server name is X. It can't create a new operating rule. Memories also expire unless they are...

2 weeks ago
Forum
Reply
RE: Multi agent workflows... when does parallel work create more review work

When tasks are separate. Documentation, test generation and a migration script can run in parallel. Four agents redesigning the same module usually cr...

2 weeks ago
Forum
Scroll to Top