Playbooks

Platform-specific, step-by-step guides for hardening your AI agent pipelines. Pick your stack, follow the playbook.

Securing LangChain Agent Pipelines

LangChain's flexibility is its strength and its risk. This playbook shows how to add permission wrappers, structured logging, and evaluation gates to your agent pipelines.

2026-03-08Read playbook →

OpenAI10 min read

Hardening OpenAI Function Calling Agents

OpenAI's function calling is powerful and dangerously easy to misconfigure. This playbook covers permission boundaries, input validation, and cost controls.

2026-03-01Read playbook →

Stay clawproof

New checks, playbooks, and postmortems. Twice a month.

No spam. Unsubscribe anytime.