Your Agent Picks the Wrong Tool. It’s Not the Agent’s Fault.

Lesson 2.1: When your agent reaches for the wrong tool, the answer isn’t a routing classifier. It’s a description that says when NOT to use the tool.

Weekend Dispatch: The Quiet Ones Are the Production Layer

Everyone’s reading this week’s AI stories wrong: AI didn’t replace the careful thinkers. It exposed how long the org has been ignoring them. /goal just shipped in Claude Code to close the gap.

Tokenmaxxing Is a Dead End. Learn to Manage Agent Portfolios Instead.

Tokenmaxxing is the data warehouse mistake at a different layer. The fix isn’t compressing tokens. It’s deciding which agents in your portfolio earn their keep.

You Built the Agent. Don't Stop at Wiring. Agent Ops Is Next.

The capstone part 1 wired the agent. Operating it takes three architectures: a persona that defines the job, a decomposition that scales the work, and a session model that survives the closed laptop.

Weekend Dispatch: Architect or Be Architected

Everyone’s reading this week’s four AI stories wrong: the FDE rebrand, Karpathy’s compression test, the brake Citrini missed, and Nvidia on your wall.

You’re Not Being Hired Strictly for Output Anymore. Your Judgment Is What Is in Demand Now.

Companies are running Agile retrospectives while the production function underneath them has changed. The work that built your career was output. The work that holds it now is judgment.

You Can’t Prompt-Engineer Your Way to Reliable Agents. Wire the Architecture Around It.

Domain 1 Capstone: Reliability is not in the prompt. It’s in the loop, the hooks, the policy gates that fire whether the model wants them to or not, and that the model can’t talk past.

The Tolerance for Non-Builders Is Shrinking. Especially If You're Mid-Level or Senior.

New expectations are emerging where everyone is a potential builder, supported by agent portfolio governance and data-driven prioritization.