fabceolin

fabceolin on Hacker News

Re:Show HN: Build agents via YAML with Prolog validation and 110 built... on Saturday January 24, 2026 @08:09AM (#46743225)

Clean context for each iteration will make the LLM give your better results. Using LLM loop you will full the context faster degrading the LLM responses. Tea supports create a workflow from dot file https://fabceolin.github.io/the_edge_agent/articles/writing-...

Re:Show HN: Build agents via YAML with Prolog validation and 110 built... on Friday January 23, 2026 @09:15PM (#46740455)

Clean context for each iteration will make the LLM give your better results. Using LLM loop you will full the context faster degrading the LLM responses.

Re:Show HN: Build agents via YAML with Prolog validation and 110 built... on Friday January 23, 2026 @02:11PM (#46736471)

Yes, I wrote an article about this: Truth Resolution Agent: A Multi-Source Judicial Framework for Sports Disputes (Senna 1989 Case Study) using llm as a judge and prolog neurosymbolic as a judge

https://fabceolin.github.io/the_edge_agent/articles/truth-re...

Re:Show HN: Build agents via YAML with Prolog validation and 110 built... on Friday January 23, 2026 @09:16AM (#46732746)

The project started to be a Cyclic State Graph orchestrator, statically defined via YAML, leveraging Neurosymbolic validation (Prolog) to ensure deterministic transitions in edge environments. Langraph also it is, but python and the thread mechanism make not suitable for edge environments.

Re:Show HN: Build agents via YAML with Prolog validation and 110 built... on Friday January 23, 2026 @09:10AM (#46732668)

We have checkpoints implemented to save the state in the middle of graph navigation and we can restart from there. It's useful to implement interviews process like https://fabceolin.github.io/the_edge_agent/articles/intellig...

Re:Show HN: Build agents via YAML with Prolog validation and 110 built... on Friday January 23, 2026 @09:07AM (#46732634)

Thanks

Show HN: Build agents via YAML with Prolog validation and 110 built-in tools

Posted by fabceolin on Friday January 23, 2026 @06:32AM
from the show-hn dept.

https://fabceolin.github.io/the_edge_agent/index.html

I'm one of the creators of The Edge Agent (TEA). We built this because we needed a way to deploy agents that was verifiable and robust enough for production/edge cases, moving away from loose scripts.The architecture aims to solve critical gaps in deterministic orchestration identified by *Prof. Claudionor Coelho Jr. (Stanford alum, ML/DL Faculty at Santa Clara Univ., and Senior Fellow for AI...

( Read More... | 11 comments | on HN )