Google DeepMind
Google's AI research laboratory, which builds the Gemini models and publishes research such as step-back prompting and the CaMeL defence.
In more detail
Gemini models are served through Google's APIs, and Google's Agent Development Kit targets them first. Its research papers are a common source for prompting and agent-security techniques.
Related terms
- Google ADK — Google's Agent Development Kit, an open-source framework for building, running and deploying agents with an event-driven runtime.
- CaMeL — A design from Google DeepMind that defeats prompt injection by having a privileged model write a plan as code while a quarantined model reads untrusted data, with data flow tracked and checked by policy.
- step-back prompting — Asking a model first for the general principle behind a question, then answering the question with that principle in view.
Taught in
- Reasoning Techniques — AI Engineering: LLM Apps, RAG & Agents
- Prompt Injection — AI Engineering: LLM Apps, RAG & Agents
References
- Zheng et al. (2023): Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
- Debenedetti et al. (2025): Defeating Prompt Injections by Design (CaMeL)