Apr 19 · 11 min read · Github repo: https://github.com/SubhanshuMG/agents-as-state-machines The thesis in one paragraph Stop calling them agents. They are state machines that invoke LLMs at certain transitions. The multi-a
Eermastondang71-lang commented
Apr 18 · 7 min read · Step 7 is a condition: if the HTTP response came back 200, continue to step 8 and step 9. If not, skip them and jump to step 10. Five steps downstream of a single boolean, two possible paths, and a directed acyclic graph that only understands one thi...
Join discussionJan 13 · 5 min read · Aethas indexes local files like Obsidian vaults, or markdown folders for context-aware conversations. This happens at startup, when users manually trigger a re-index, and continuously via file watchers. After some use I found it annoying to guess if ...
Join discussionDec 30, 2025 · 4 min read · Back in 2022, I wrote Building a Traffic Light React App exploring how to model UI state as a finite state machine. The key insight was naming states by their business meaning rather than their visual representation, like PriorityStraight instead of ...
Join discussionSep 3, 2025 · 4 min read · The good thing about agentic coding is, you can easily awake dead repos out of experiments back to life. Event sourced grain state machines is such an example. Short version: take a clean Stateless state machine, host it as a grain, and let events be...
Join discussion
