guardrails

Pre- and post-model guardrails to block unsafe prompts/outputs in production.

Open-source + managed framework for input/output checks and structured outputs.

Real-time guardrails, automated red teaming, and moderation workflows.

Framework for collaborative multi-agent crews with roles, memory, tools, and guardrails.

Programmable guardrails (topic control, PII, jailbreak prevention) for LLM apps.

Managed access to many foundation models, agents, guardrails, and knowledge bases via one API.

Centralized, reusable guardrails for prompts and responses across models.