The fastest way to corrupt money is an agent-built payment system.
Not all code is equally expensive to get wrong. Stop reviewing your agent's output uniformly and spend your scrutiny where a mistake double-charges a customer.
10 posts tagged #plan-mode.
Not all code is equally expensive to get wrong. Stop reviewing your agent's output uniformly and spend your scrutiny where a mistake double-charges a customer.
Subagents are sold as parallelism. The real win is context hygiene plus model arbitrage: cheap explorers read, and your expensive model sees only findings.
Vibe-coding a service you have never touched traps you at the first failure. Point the agent at its docs over MCP and force it to teach you back.
Stop fighting the context limit with a bigger window. Write an exhaustive plan to a file, then relay fresh sessions that each tick off items until it ships.
An agent reviewing its own plan shares its blind spots. Wire a different vendor's model in as a gate, and a fail verdict re-engages planning before any code.
Reviewing irreversible actions after the fact is too late. Split tools by reversibility, force a plan, and gate the destructive step behind a human interrupt.
Hand the agent two committed documents - a requirements doc that fixes the destination, a phased plan that fixes the journey - and a big feature still ships.
Let peer agents talk freely and a query hot-potatoes between them while your bill climbs. Route everything through one orchestrator with a turn cap instead.
Your judgment lives in your head until something extracts it. A procedure that explores the repo, then grills you branch by branch, turns an idea into a spec.
A million-token window won't fix a long build. Externalize state to a plan file and relay across fresh sessions - quality dies long before the window fills.