Ask HN: What's the hardest part of building AI Agents?
I know I'm struggling. Am I the only one who is confused and struggling to build AI Agents? What are you having problems with?
Every agent uses a meta-workflow (eg. ReAct is plan->act->observe, with some added steps to check for completion etc.).
The teams that have been successful with agents do so by building better but more complex workflows.
Most notably, AlphaCodium's "From Prompt Engineering to Flow Engineering" https://github.com/Codium-ai/AlphaCodium
Our current tools don't do a great job of making it simple to build and iterate on these workflows.
For example, here's a HN post from yesterday where a user created their own workflow management platform because of their frustration with the leading tooling providers: https://news.ycombinator.com/item?id=42299098
I think once we get this tooling right and start to build more expertise in the process of flow engineering, we'll start to faster improvement in agent quality.