A research run used 11.1M tokens
109 top-tier agents ran in one workflow. Change: tiered models, a six-agent cap, and a usage table per run.
A multi-agent system built on Claude Code that runs a retention agency's daily operations. I designed it, wrote it, and use it every day.
A message from my phone, a scheduled job, or a client's post in a shared channel.
Pattern rules match the intent to an agent. Each client can override the routes.
One of 32, each with its own skills, spending limit and rule for what happens on failure.
A registered procedure that runs plan, dry run, then apply, with a way to roll back.
Klaviyo, Attentive, Figma, WordPress. Email and SMS sending rules (TCPA, CAN-SPAM) are enforced here.
Every run is logged with the agent, the skill, the model, the cost and the outcome, so I can see what the system did and what it spent.
109 top-tier agents ran in one workflow. Change: tiered models, a six-agent cap, and a usage table per run.
Two machines synced the whole repository. Change: code moves only through git; the sync covers two named folders.
Background jobs write tracked files every minute. Change: stashing is banned in the repository; side work happens in a separate working copy.
Hard-to-reverse decisions are written up as short decision records in the repository, so the next change starts from the reason and not from a guess.
The strategy, the concept, the copy edit, the final look, and the approval on every send.
Send anything. Invent a discount code or a claim. Publish a number without its evidence.