google · Google AI Docs

Gemini API Safety and factuality guidance

Guidelines for configuring safety settings and managing factuality to mitigate risks such as hate speech, harassment, and hallucinations in Gemini API responses.

Import to Prompt Buddy

Derived skill

Files assembled from official documentation

Viewing SKILL.md

Gemini API Safety and factuality guidance

Guidelines for configuring safety settings and managing factuality to mitigate risks such as hate speech, harassment, and hallucinations in Gemini API responses.

When To Use

Use when you need to configure safety thresholds or implement strategies to reduce model hallucinations and harmful content in an application.

Reference Files

File	Contains	Use For
`SKILL.md`	Entry point: scope, routing table, and workflow.	Start here.
`docs/gemini-api-safety-and-factuality-guidance-workflow-guide.md`	Guidelines for understanding and mitigating safety risks, bias, and factuality issues when using the Gemini API.	Questions about guidelines for understanding and mitigating safety risks, bias, and factuality issues when using the Gemini API.

What This Skill Covers

Generative artificial intelligence models are powerful tools, but they are not without their limitations. Their versatility and applicability can sometimes l...
Main sections: Understand the safety risks of your application, Advanced tips, Consider adjustments to mitigate safety and factuality risks, Perform safety testing appropriate to your use case, Monitor for problems.

Workflow

Open the most relevant file under docs/ for the exact documented workflow and wording.
Open schemas/ files for exact structured contracts.
Open examples/ files for concrete requests, commands, snippets, and manifests.
Do not add behavior or configuration that is not present in the attached source files.

Canonical source: https://ai.google.dev/gemini-api/docs/safety-guidance