Topic
Source-linked workflows that name Architecture. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
An Ask HN on controlling agents that take real actions converges on: LLM proposes → deterministic validator (rules, spend ceilings, replay checks) → human approve—especially for refunds, payments, and database writes where prompt 'never do X' fails.
An Indie Hackers post breaks down the architecture for an AI secretary that actually keeps context: session vs short-term task vs long-term preference layers so birthday/contact and calendar commitments survive across chats.
Learnable test: keep deterministic paths in code; put the agent loop only on the flowchart box whose next step depends on discoveries (multi-source state, content-driven checks, unencoded domain knowledge)—else it’s an API call in a badge.