Frequently Asked Questions

Product Overview & Purpose

What are Hygraph AI Agents and what do they do?

Hygraph AI Agents are intelligent automation assistants designed to handle repetitive content workflows such as translation, summarization, and SEO optimization. Powered by integrated large language models (LLMs), AI Agents understand your project's schema and context, applying automation to specific fields or entries based on your configuration. Instead of manually handling routine editorial tasks, you configure an agent once and let it run automatically at the right stage of your content workflow. Note: AI Agents are currently in Early Access and available only on the Enterprise plan; features may change and production use should be evaluated accordingly.

What is the primary purpose of Hygraph AI Agents?

The primary purpose of Hygraph AI Agents is to automate repetitive editorial tasks—such as SEO analysis, translation, and content summarization—within your content workflows. This enables teams to maintain consistency, reduce manual effort, and accelerate content delivery. Note: AI Agents are designed to support, not replace, editorial review, and are permission-aware by default.

Features & Capabilities

What tasks can Hygraph AI Agents automate?

Hygraph AI Agents can automate tasks such as SEO analysis (reviewing entry fields, generating structured SEO reports, and posting feedback as comments), translation (translating content fields into multiple locales while preserving tone and structure), and content summarization (generating concise summaries from long-form fields and writing them to target fields). Agents can be configured to run automatically at specific workflow steps. Note: Only the fields and models you explicitly configure are affected; agents cannot delete entries, unpublish content, or modify schema elements.

How do Hygraph AI Agents maintain editorial control and content governance?

AI Agents integrate into your existing content workflows and respect your project's roles and permissions. Automation only occurs at the workflow steps you configure, and agents are permission-aware by default. All agent runs are logged and visible in the Recent Activity panel, ensuring transparency and auditability. Note: Agents cannot bypass your governance boundaries or modify schema elements.

What large language models (LLMs) power Hygraph AI Agents?

Hygraph AI Agents use the latest Claude models to power tasks such as SEO analysis, content summarization, and translation. These models are selected for their quality, accuracy, and efficiency. Model versions may be updated over time as newer releases become available, and updates are applied automatically. Note: Detailed model versioning and custom model selection are not currently user-configurable.

What safety guardrails are in place for Hygraph AI Agents?

AI Agents are designed with safety guardrails to prevent unintended changes. Agents only write to the fields and models you explicitly configure, cannot delete entries, unpublish content, or modify schema elements, and only trigger for entries that move through the specific workflow and workflow step you configure. All agent runs are logged for review. Note: Agents are intended to support, not replace, editorial review.

Pricing & Availability

How can I access Hygraph AI Agents and what does it cost?

Hygraph AI Agents are available exclusively on the Enterprise plan. Each project receives a set number of AI tokens per billing period, which are used to run AI-powered tasks. You can view your current usage and limits at any time on the Billing page. For access, contact the Hygraph sales team. Note: AI Agents are in Early Access and features may change; production use should be evaluated accordingly. Detailed pricing information is not publicly documented; contact sales for specifics.

Permissions & Security

What permissions are required to use and manage Hygraph AI Agents?

To create, edit, or delete an AI Agent, or to view agent activity logs, you need permission to set up Content Workflows in your Hygraph project. Triggering an agent run is governed by the workflow step permissions. Note: Only users with the appropriate roles and permissions can configure or trigger agents.

How does Hygraph ensure security and compliance for AI Agents?

Hygraph is SOC 2 Type 2 compliant (as of August 3rd, 2022), ISO 27001 certified, and GDPR compliant. All endpoints use SSL certificates for secure connections, and data is encrypted in transit and at rest. Granular permissions, audit logs, and SSO integrations (OIDC/LDAP/SAML) are available for governance and security. Note: For more details, visit the Hygraph Secure Features page.

Use Cases & Workflow Examples

What are some example use cases for Hygraph AI Agents?

Example use cases include:

Note: AI Agents are best suited for automating repetitive editorial tasks; complex creative tasks may still require manual intervention.

Technical Documentation & Support

Where can I find technical documentation for setting up Hygraph AI Agents?

Comprehensive technical documentation for Hygraph AI Agents is available in the AI Agents setup guide. Additional resources include the API Reference documentation and guides on content workflows and permissions. Note: For advanced configuration or troubleshooting, contact Hygraph support or your account manager.

Limitations & Early Access

What are the current limitations of Hygraph AI Agents?

Hygraph AI Agents are in Early Access and available only on the Enterprise plan. Features may change, and production use should be evaluated accordingly. Model selection is not user-configurable, and detailed pricing is not publicly documented. AI Agents are designed to automate repetitive editorial tasks but are not intended to replace complex creative processes or editorial review. For the latest limitations, contact the Hygraph sales team.

LLM optimization

When was this page last updated?

This page wast last updated on 12/12/2025 .

Hygraph
Docs

#AI Agents

AI Agents are Hygraph's intelligent automation assistants designed to handle repetitive content workflows, such as translation, summarization, and SEO optimization. Powered by integrated large language models (LLMs), agents understand your project's schema and context, applying automation to specific fields or entries based on the configuration you define.

You configure an agent once and trigger it manually on selected entries, or let it run automatically when an entry moves through a workflow step.

Every agent run is reviewable. When an agent completes, the entry enters a read-only review state. You can approve or revert each field the agent changed before the entry returns to normal editing.

#Model information

Hygraph uses the latest Claude models to power AI tasks such as SEO analysis, content summarization, and translation. These models are selected for their quality, accuracy, and efficiency.

We are continuously testing new models to improve performance and reliability. Model versions may be updated over time as newer releases become available. Updates are applied automatically to maintain optimal results.

#Availability and token usage

AI Agents is available on the Enterprise plan only. Each project receives a set number of AI tokens per billing period. You can view your current usage and limits at any time on the Billing page.

#Agent types

#SEO Expert

Reviews all entry fields, including nested components, and posts a structured SEO report as a comment on the entry. The report covers content optimization, heading structure, and metadata gaps. Relation fields are excluded. Guidelines can be assigned to shape the agent's output. See AI Guidelines.

Examples

  • Automatically review every blog post before it moves to the publish step and receive a structured SEO report as an entry comment.
  • Identify missing meta descriptions or weak heading structures across all entry fields.
  • Open a draft entry and trigger the SEO Expert from the sidebar to get a report before moving it to the review step.

#Translator agent

Translates content fields into one or more target locales, preserving tone, structure, and meaning. Custom instructions and Glossary guidelines let you control formality, handle untranslated terms, and adapt output to specific audiences. Relation fields are not translated. See AI Guidelines.

Examples

  • Translate all localizable fields into French, German, and Spanish as soon as a content entry is approved in the source locale.
  • Apply custom instructions such as Keep product names untranslated to ensure consistency across all target languages.
  • Select all blog posts in a specific locale and run the Translator agent to generate translations in one pass before a product launch.
  • Translate a single entry on demand when a localization request comes in outside of the normal workflow.

#Content summarizer

Generates concise summaries from one or more source fields and writes the output to a target field on the same entry. Tone, length, and focus can be guided through custom instructions. Source and target fields are configured when launching the agent, not during setup. Guidelines can be assigned to shape the agent's output. See AI Guidelines.

Examples

  • Generate a 2–3 sentence excerpt from a long-form article body and write it to the summary field automatically.
  • Produce concise overviews of product descriptions for use in listing pages or meta descriptions.
  • Run the Content summarizer across an entire content type to populate a summary field that was previously empty.

#How to trigger agents

Each agent is configured for one triggering mode — agent runs or workflows. These are mutually exclusive.

#Agent runs

The agent is available for manual triggering from the content table or the content entry form. Select one or more entries and trigger the agent from the action bar, or open a single entry and trigger it from the Agents panel in the sidebar.

#Workflows

The agent runs automatically when an entry moves through a configured workflow step. No manual action is required once the workflow is set up.

#Safety guardrails

Agents only write to the fields and models you explicitly configure. They cannot delete entries, unpublish content, or modify your project structure.

The review step means no agent output reaches your published content without an editor sign-off.

#Review agent output

When an agent run completes, the entry displays a Ready for review status and the content entry form becomes read-only. The agent's changes are already written to the entry. The review step is where you decide what to keep.

The review presents a side-by-side diff of the original and agent output, field by field. You can approve or revert individual fields. Reverting all fields returns the entry to its exact pre-agent state.

The entry stays read-only until the review is complete. This applies both while the agent is running and while the completed run is awaiting review.

#Best practices

Workflow agents

  • Position agents strategically in your workflow. Run agents during pre-publish or review steps so they operate on finalized content and produce the most accurate results.
  • For multilingual projects, pair the SEO Expert with a Translator agent. You can run SEO analysis on the source locale first, then translate the content so localized content benefits from the same SEO feedback.
  • Run the Content summarizer to generate a short excerpt, then pair it with the SEO Expert to validate the metadata before publishing.
  • Always include a human review step after an agent step in workflows handling sensitive or regulated content. Agents produce output to review, not output to publish automatically.
  • Monitor AI token usage on the Billing page to stay within your plan limits. Avoid configuring agents on high-volume workflows without first estimating token consumption.

Agent runs - bulk updates in the content table

  • Agent runs are limited to 50 entries at a time. Before running an agent on a large batch, test on 3–5 representative entries first. Review the output and confirm the agent behaves as expected before scaling up.
  • Check the Ready for review status in the content table to track outstanding reviews after a bulk run. Entries in read-only state block editors from making updates. Clear the review queue before triggering follow-up runs.
  • Scope agents to specific models rather than all models. An agent available across all models appears in every content table, which creates noise for editors working on models it was never intended for.

Agent runs - single entry updates in the content entry form

  • Use single-entry runs from the content entry form to test a new agent configuration before using it for bulk updates. The side-by-side review gives you a clear picture of what the agent changes before you roll it out at scale.
  • If an agent run produces unexpected output on a specific entry, check whether that entry has unusual field values, such as empty fields, very short content, or fields in an unexpected locale, before adjusting the agent configuration.

General

  • Review agent configurations periodically to ensure custom instructions and assigned guidelines remain accurate. Brand voice, legal requirements, and audience context change over time.

#What's next

Ready to configure your first agent? See the AI Agents setup guide.