IT EventsBook

Discussions

mcp_curious
mcp_curious
@mcp_curious
Active Member
Joined: Aug 26, 2026
Last seen: Sep 24, 2026
Topics: 2 / Replies: 7
Reply
RE: RAG vs long context, is retrieval still worth it with huge context windows

Exactly. You still need a retrieval and permission layer. Bigger context lets you send richer evidence once you find it. It can reduce aggressive chun...

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

Our metadata is inconsistent, so that probably explains more than the embedding model. Would you let an LLM create the links?

2 weeks ago
Forum
Reply
RE: MCP server security, would you give it real production credentials?

Tool descriptions can change behavior too. A trusted server update could add instructions the agent follows. We log the tool schema and diff it during...

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

Exactly. Store structured items and keep the original evidence. When a memory influences an action, show it in the trace. Users need a way to edit and...

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

Large context is great when the document set is small and you already know which files matter. It doesnt solve finding those files, access control, fr...

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

We had a task list but no interface decisions. The agents all solved the gaps differently. A single agent might have been slower but coherent.

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

Do not let retrieved content write directly to long term memory. Candidate memories need a type, source, timestamp and confidence. Some should require...

2 weeks ago
Forum
Scroll to Top