Most "build your first agent" tutorials start with a framework and four new vocabulary words before you've written anything that does something. This one skips that, it's just the goal, tool call, observe, decide loop, built by hand, no framework.
Bad: "Read note-1.txt, then read note-2.txt, then summarize each one."
Good: "Look at every file in ./notes. For each one that describes an unresolved question, draft a short reply and save it to ./drafts with the same filename."
A hard step limit matters more than picking the "best" model. Without one, a small misunderstanding early in the run can turn into a long, expensive loop of the model trying to correct a mistake it doesn't realize it made.
The first time an agent does something unexpected, the log is the only way you'll figure out why.
The full walkthrough with code, plus the follow-up on frameworks (LangGraph vs CrewAI vs AutoGen vs Claude Agent SDK), is here:
source & further reading
dev.to — original article
The Secret to Always-On Audio AI: Why Your Android App Needs a DSP (and How to Implement It)
PVM:Give any LLM long-term memory.No API keys,no GPU,~800 lines Python.
Developers are not searching for more powerful Claude Code skills. They are searching for taste.