An effective classroom is a system that you can master, and it's easy to play catch-up. The same principle applies for agentic software development.
Here are some lessons I took away from @andrewzigler's keynote at @TheLeadDev's LDX3 on why Ms. Frizzle would be a fantastic SRE.
“If you're not throwing a bunch of things away every week and starting over or adding new stuff or simplifying ever like every week, then you're probably not iterating fast enough”
On the latest episode of the Agents + Engineers podcast, @andrewzigler and I discuss the importance of continue experimentation to improving agentic workflows.
Andrew is a GTM Engineer at LinearB and the host of Dev Interrupted. He has written extensively about agentic engineering, including his technique of Mise en Place.
We also discuss:
- Why individual gains from AI coding often fail to become organizational gains
- Andrew’s technique of Mise en Place + Beads for agentic dev
- The value of a humanities education in an agentic world
Listen directly to the episode and be sure to rate and subscribe to the show!
Apple: podcasts.apple.com/us/podcas…
Spotify: open.spotify.com/episode/2Mk…
a+e website: agentsandengineers.com/episo…
What does a newsroom built for humans *and* AI agents look like?
@DevInterrupted co-host @andrewzigler is already experimenting with the answer.
Offleash Media Strategist @vishalpersaud recently caught up with Andrew to discuss his agentic workflow and what it could mean for the future of tech media: offleashpr.com/inside-dev-in…
Token counts alone don't tell you if AI agent spend was worth it. "Are we using tokens?" isn't the question — "what did those tokens accomplish?" is.
@andrewzigler built a cost-attribution system that stamps every request with session/task IDs, tying spend to actual work units instead of PRs — including the $61.80 research task that produced zero code but drove every decision after it.
andrewzigler.com/feed/every-…
Great chat with @andrewzigler on @DevInterrupted: on agent sprawl inside big orgs, how AWS built an MCP server for 16,000 AWS APIs, what the latest MCP spec unlocks for server authors, and why building *less* on top of LLMs beats building more
youtube.com/watch?v=x8_OhVgb…
The AI experiment phase is fun. The "now what?" phase is where things get interesting.
@z00b + @andrewzigler on connecting AI investment to business outcomes: circle.ci/4vQcw75
Giving an agent every MCP tool a server exposes creates unnecessary risk. @andrewzigler, AAIF Ambassador, shows how @goose_oss + @agentgateway can federate MCP servers, scope tools per agent, route model and tool traffic through one gateway, and log every call with identity tracking.
Build: bit.ly/4gBVKVs#MCP728