Activity
Mon
Wed
Fri
Sun
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
What is this?
Less
More
Owned by Dan
Become the developer your team looks up to. Build leadership, confidence, and career momentum. You've mastered code. Now master growth.
2 contributions to ZazenCodes Agentic Coding Club
Aug 14 •
Running agents in devcontainers or local
Hi, To keep your local system clean, do you guys run agents in devcontainers or just run it locally? I know some people run their dev work in devcontainers where claude or codex is present so they can go crazy without accidentally creating junk on their system.
1 like • 11d
I have run into the same dilemma. I love the idea of isolated "environments", but it adds complexity. If you are on Windows and you run your containers in WSL2, you may actually see the agents running faster. When I switched from Claude Code running on Windows against a git repo on the Windows file system to Claude Code running on WSL2 and/or a container in WSL2, I noticed a significant performance improvement. I guess it really depends on your motivation. If it's performance and isolation, go for it. If you want things simple and don't care about performance, then run them locally.
Sep 7 •
AI Agent Observability
I was following your YouTube video “Build an AI Bookkeeper with Pi Agent Harness” and found it very helpful. I extended the example with some basic logging, as shown in the screenshot. I'm currently logging things like: - request duration - token usage - estimated LLM cost - tool calls - user message / agent response Is this a reasonable approach for observability with a Pi-based agent, or is there a better/recommended way to instrument Pi agents?
0 likes • 11d
I'm looking to have this observability for all my tools and agents. I'll be sure to watch that YouTube video
1-2 of 2
@dan-schaefer-6524
I have over 20 years of experience as a software developer
Active 1d ago
Joined Oct 3, 2026
Akron, OH