News for hackers. Stuff that matters.
Re:Show HN: UltraContext – A simple context API for AI agent... by nicklo on Wednesday January 21, 2026 @05:20PM (#46712434)
i've always wondered (for this, portkey, etc) - why not have a parallel option that fires an extra request instead of mitm the llm call?
Re:Show HN: UltraContext – A simple context API for AI agent... by ofabioroma on Wednesday January 21, 2026 @05:23PM (#46712486)
You can fire them in parallel for simple cases. The issue is when you have multi-agent setups. If context isn't persisted before a sub-agent reads it, you get stale state. Single source of truth matters when agents are reading and writing to the same context.

For single-agent flows, parallel works fine.