The Agent Benchmark That Should Scare Managers

The Agent Benchmark That Should Scare Managers

Agentic coding tools are moving into enterprise workflows, but the week's most useful signal is a benchmark where frontier models still struggle below 50% on real IT tasks. Alex and Sam unpack Microsoft Learn grounding, agent deception, Copilot data leaks, and the practical harness every team should build before handing agents production authority.

The Workflow Feature That Makes Agents Less Expensive

Claude Code workflows, enterprise Codex deployments, and rising token costs all point to the same lesson: coding agents need operating systems, not just better prompts. Alex and Sam dig into /workflows, on-prem Codex, CI for agents, and the new decision fatigue of choosing where each task should run.

Codex on Windows Changes the Agent Sandbox

OpenAI's Windows sandbox work is the practical story behind safer coding agents this week. Alex and Sam dig into Codex on Windows, remote cloud coding agents, Claude Code billing splits, and why a Raspberry Pi running rm -rf is the warning label every agent workflow needs.

A Cursor Agent Wiped a Prod DB in 10 Seconds. Let's Talk About That.

A Cursor AI agent deleted PocketOS's entire production database on April 25th — in under 10 seconds. This week Alex and Sam dig into the AI agent credential crisis, Anthropic's wild SpaceX/xAI compute deal, Mozilla using Claude to find hundreds of Firefox vulnerabilities, and whether OpenAI Codex is actually closing the gap on Claude Code. If you've ever given an agent database access, listen before your next deploy.

Claude Security Just Went Public — Is Your Codebase Already Exposed?

Anthropic's Claude Security tool just dropped out of closed preview and it will scan your entire codebase for vulnerabilities — and the results might be uncomfortable. This week we also dig into Cursor's $60 billion bet on being the "harness" rather than the model, why AI agents are literally forcing developers to keep their laptops open, and the Zig project's nuclear take on AI contributions. If you write code with AI help, this episode is required listening.