Building Safe AI Agents with Guardrails
We start with a DataTalks.Club Data Engineering Zoomcamp FAQ assistant, then add checks that keep the agent on topic, block unsafe responses, and show how to cancel wasted work when a guardrail fails. The workshop uses the OpenAI Agents SDK for built-in guardrails, then rebuilds the same idea with tools and plain `asyncio` so you can use it with other agent frameworks. ## Links The external resources: - [Related course: AI Bootcamp: From RAG to Agents](https://maven.com/alexey-grigorev/from-rag-to-agents) - [FAQ data used by the agent](https://datatalks.club/faq/) - [AI Hero email course for the docs.py loader](https://alexeygrigorev.com/aihero/) - [OpenAI Agents SDK guardrails documentation](https://openai.github.io/openai-agents-python/guardrails/) ## The notebook you will build The final notebook has guardrails around a tool-using FAQ agent: ```mermaid flowchart LR USER["User question"] INPUT["Input topic guardrail"] FAQ["FAQ assistant agent"] SEARCH["search_faq tool<br/>minsearch index"] OUTPUT["Output safety guardrail"] ANSWER["User-facing answer"] OPENAI["OpenAI model calls"] USER --> INPUT INPUT -->|passes| FAQ INPUT -->|trips| ANSWER FAQ --> SEARCH FAQ --> OPENAI INPUT --> OPENAI OUTPUT --> OPENAI FAQ --> OUTPUT OUTPUT -->|passes| ANSWER OUTPUT -->|trips| ANSWER ``` The base agent can already search the FAQ, but it tries to answer unrelated questions too. The input guardrail blocks questions outside the course domain. The output guardrail checks the agent response for policy problems such as promising deadline extensions or writing homework for a student. The later parts show the same checks as tools and as a small async runner that can cancel work when a guardrail trips.