Responsible Generative AI Toolkit  |  Google AI for Developers (original) (raw)

Tools and guidance to design, build and evaluate open AI models responsibly.

Get started

Define system-level policies

Determine what type of content your application should and should not generate.

• Define policies
• See examples

Design for safety

Define your overall approach to implement risk mitigation techniques, considering technical and business tradeoffs.

• Learn more

Be transparent

Communicate your approach with artifacts like model cards.

• See Templates

Get started

Craft safer, more robust prompts

Use the power of LLMs to help craft safer prompt templates with the Model Alignment library.

• Try now
• Model Alignment

Investigate model prompts

Build safe and helpful prompts through iterative improvement with the Learning Interpretability Tool (LIT).

Model prompts video

• Try now
• Learning Interpretability Tool

Get started

LLM Comparator

Conduct side-by-side evaluations with LLM Comparator to qualitatively assess differences in responses between models, different prompts for the same model, or even different tunings of a model

LLM Comparator video

• Try demo
• Learn about LLM Comparator

Get started

Agile classifiers

Create safety classifiers for your specific policies using parameter efficient tuning (PET) with relatively little training data

• Create safety classifiers

Checks AI Safety

Ensure AI safety compliance against your content policies with APIs and monitoring dashboards.

• Checks AI Safety

Text moderation service

Detect a list of safety attributes, including various potentially harmful categories and topics that may be considered sensitive with this Google Cloud Natural Language API available for free below a certain usage limit.

• Cloud Natural Language API
• Cloud Natural Language pricing

Perspective API

Identify "toxic" comments with this free Google Jigsaw API to mitigate online toxicity and ensure healthy dialogue.

• Perspective API