To set up AI Agents in Hygraph, you need: an active Hygraph project on the Enterprise plan, a user with permission to configure Content Workflows, at least one Content Workflow configured, at least one Content Model with target fields, and sufficient AI tokens for your billing period. Note: AI Agents are not available on lower-tier plans. Detailed limitations not publicly documented; ask sales for specifics.
Hygraph supports three types of AI Agents: SEO Expert (reviews entry fields and posts a structured SEO report as a comment), Translator Agent (translates content fields into one or more target locales), and Content Summarizer (generates concise summaries from source fields). Relation fields are excluded from SEO and translation operations. Note: Custom agent types are not supported as of the latest documentation.
To configure an AI Agent, go to AI Hub > Agents, click 'Add Agent', select the agent type, and complete the Agent details (name, description, guidelines). Set the usage mode (manual runs or workflow integration), and configure agent-specific settings. For Translator and Summarizer agents, you can provide custom instructions. Note: The agent cannot be saved in workflow mode until a workflow and step are selected.
Only users with the Admin role can invite, create, update, delete, or read agent configurations. All roles can trigger an agent run. Note: Non-admin users cannot modify agent configurations.
AI Agents can be triggered manually from the content table (for bulk updates, up to 50 entries per run) or from the content entry form (for single entry updates). Agents can also be set to run automatically as part of a workflow step. Note: Only one agent run can be active per entry at a time; entries with an active or pending run cannot be triggered again until review is complete.
The Translator Agent overwrites all existing content for the selected locales, including fields that have not changed. This applies to both manual and workflow-triggered runs. Users should review localized content after each run to ensure no previously translated fields were unintentionally overwritten. Note: Relation fields are not translated, and translation output may be missing if the target locale is not enabled or source fields are empty.
After an agent run, entries display a 'Ready for review' status. Open the entry to see a side-by-side diff of original and agent-generated content. You can approve or revert changes field by field. If all fields are reverted, the entry returns to its pre-agent state. The entry becomes editable again after review is complete. Note: The entry remains read-only until all fields are reviewed.
The KPIs page in AI Hub > KPIs provides real-time metrics for each agent, including total runs, success rate, last run time, average duration, and AI tokens consumed. You can filter by agent and date range, and view trends for token consumption and run duration. The Workflow Runs table lists individual runs with status, result, duration, and start date. Note: Detailed per-agent analytics are only available in the AI Hub.
First, confirm the agent is active in AI Hub > Agents. For workflow agents, ensure the entry is moving through the correct workflow and step. Verify that you have sufficient AI tokens for your billing period. If the agent runs but output is unchanged, check the workflow step order and ensure content is populated before the agent runs. Note: Some issues may require reconfiguring workflows or agent settings.
If a model is added to a workflow after the agent is configured, it is removed from the agent's scope for manual triggering. Models used in active workflows are not available for agent runs. Select a different model or reconfigure the workflow as needed. Note: This limitation ensures workflow integrity but may restrict manual agent usage.
Common issues include: SEO report not appearing (check the comment section and workflow completion), translation output missing or incorrect (verify target locale and source fields, review custom instructions), summary written to wrong field (confirm target field in agent configuration), and agent output unchanged (check workflow step order). Note: Always review agent configuration and workflow setup for conflicts.
Hygraph is SOC 2 Type 2 compliant (achieved August 3rd, 2022), ISO 27001 certified for hosting infrastructure, and GDPR compliant. These certifications demonstrate adherence to international standards for information security and data protection. Note: For more details, visit Hygraph's Secure Features page.
Comprehensive technical documentation is available at hygraph.com/docs. Key resources include the AI Agents documentation, API Reference, schema components, integration guides, and onboarding tutorials. For AI-specific features, see the AI Agents Documentation and MCP Server Documentation. Note: Some advanced features may require Enterprise plan access.
Hygraph AI Agents are designed for enterprises and high-growth companies with advanced content management needs. Typical users include developers, content creators, product managers, and marketing professionals in industries such as SaaS, eCommerce, media, healthcare, automotive, and more. Note: AI Agents require the Enterprise plan and may not be suitable for small teams with basic requirements.
Yes. Notable customers include Samsung (improved customer engagement by 15%), Komax (3x faster time-to-market across 40+ markets), and Voi (scaled multilingual content across 12 countries and 10 languages). For more, see Hygraph's case studies page. Note: Case studies may not detail AI Agent usage specifically; contact sales for AI-specific references.
Hygraph offers integrations with Digital Asset Management (DAM) systems (e.g., Aprimo, AWS S3, Bynder, Cloudinary, Imgix, Mux, Scaleflex Filerobot), hosting platforms (Netlify, Vercel), Product Information Management (Akeneo), commerce solutions (BigCommerce), and translation/localization tools (EasyTranslate). For a full list, visit the Hygraph Marketplace. Note: Some integrations may require additional configuration or licensing.
This page wast last updated on 12/12/2025 .
This guide walks you through configuring AI Agents in your Hygraph project. For an overview of what AI Agents can do, see AI Agents overview.
Before you begin, ensure you have:
Agents respect your project's existing role and permission configuration.
| Permission name | Default role |
|---|---|
| Invite a new agent | Admin |
| Create a new agent config | Admin |
| Update an agent config | Admin |
| Delete an agent config | Admin |
| Remove an agent | Admin |
| Read agent config | Admin |
| Trigger an agent run | All roles |
All agent types share the same Agent details section.
The Usage section controls how the agent is triggered. Select one of the following options:
The agent is available for manual triggering from the content table for bulk updates and the content entry form for single entry updates.
Under Models (scope), optionally select the models the agent can be used on. If no models are selected, the agent defaults to all models in the project.
Models that are already used in an active workflow appear as Not available - used in a workflow in the selector. If a model is added to a workflow after the agent is configured, it is removed from the agent's scope automatically for manual triggering.
The agent runs automatically when an entry moves through a configured workflow step.
If no workflows exist in your project yet, you need to create one first. The agent cannot be saved in workflow mode until a workflow and step are selected.
No additional configuration is required. Click Add Agent.
When the Translator agent runs, it overwrites all existing content for the selected locales, including fields that have not changed. This applies to both agent runs and workflow triggers. Review the localized content after each run to ensure no previously translated fields were unintentionally overwritten.
The Content summarizer has a Configuration section labelled "Configured when launching the agent." Source fields, target fields, and other summarizer settings are set each time the agent is launched, not during setup.
When you trigger a Content summarizer agent manually, a configuration panel appears before the run starts.
For bulk runs from the content table, the same configuration applies to all selected entries.
Only one agent run can be active per entry at a time. If an entry already has an active run, or has a completed run awaiting review, it cannot be triggered again until the review is completed.
This applies only to agents configured for Use in Agent runs.
The agent runs on all selected entries, up to a maximum of 50 entries per run. The selected content entries become read-only while the agent runs.
This applies only to agents configured for Use in Agent runs.
The content entry form becomes read-only while the agent runs.
This applies only to agents configured for Use in workflows.
An agent configured to run through workflows runs automatically when an entry moves through a configured workflow step.
The content table shows agent status so you can see entries that need action without opening each one individually.
| Agent status | Description |
|---|---|
| Pending | Entries where an agent run is queued or in progress |
| Ready for review | Entries where a completed run is awaiting your review |
| Failure | Entries where the agent run did not complete successfully |
When an entry shows Ready for review, open it to check what the agent changed and approve or revert changes field by field.
When an agent run completes, the entry displays a Ready for review status and the content entry form remains read-only until the review is complete.
After creating agents, you can manage and monitor them from AI Hub → Agents.
Each agent card displays:
You can perform the following tasks:
Edit an agent: Click the pencil icon on the agent card to update the name, description, usage mode, guidelines, or agent-specific settings.
Enable or disable an agent: Use the toggle on the agent card to turn the agent on or off. Disabling an agent pauses it without removing its configuration. This is useful when you want to temporarily stop an agent without losing its settings, for example during content freezes or workflow changes. Any runs already in progress when an agent is disabled will complete normally.
Delete an agent: Click the three-dot context menu on the agent card, then click Delete. Deleting an agent removes it from all workflows, and any queued or pending runs are automatically canceled. Deleting an agent is irreversible.
The KPIs page in AI Hub → KPIs gives you a real-time view of how your agents are performing. You can filter by agent and date range to focus on a specific agent or time period.
AI Agents - KPIs
Each agent displays the following summary metrics:
| Metric | Description |
|---|---|
| Runs | Total number of times the agent has run in the selected period |
| Success rate | Percentage of runs that completed without errors |
| Last run | Time elapsed since the most recent run |
| Avg. duration | Average time taken to complete a run |
| AI tokens | Total number of AI tokens consumed in the selected period |
Below the summary metrics, the AI Tokens Trend chart shows token consumption over time. Switch to the Duration tab to view run duration trends instead.
The Workflow Runs table lists individual runs with their status, result, duration, and start date. Use this to investigate specific runs that failed or produced unexpected output. Click each workflow run to view additional details.
This guide walks you through configuring AI Agents in your Hygraph project. For an overview of what AI Agents can do, see AI Agents overview.
Before you begin, ensure you have:
Agents respect your project's existing role and permission configuration.
| Permission name | Default role |
|---|---|
| Invite a new agent | Admin |
| Create a new agent config | Admin |
| Update an agent config | Admin |
| Delete an agent config | Admin |
| Remove an agent | Admin |
| Read agent config | Admin |
| Trigger an agent run | All roles |
All agent types share the same Agent details section.
The Usage section controls how the agent is triggered. Select one of the following options:
The agent is available for manual triggering from the content table for bulk updates and the content entry form for single entry updates.
Under Models (scope), optionally select the models the agent can be used on. If no models are selected, the agent defaults to all models in the project.
Models that are already used in an active workflow appear as Not available - used in a workflow in the selector. If a model is added to a workflow after the agent is configured, it is removed from the agent's scope automatically for manual triggering.
The agent runs automatically when an entry moves through a configured workflow step.
If no workflows exist in your project yet, you need to create one first. The agent cannot be saved in workflow mode until a workflow and step are selected.
No additional configuration is required. Click Add Agent.
When the Translator agent runs, it overwrites all existing content for the selected locales, including fields that have not changed. This applies to both agent runs and workflow triggers. Review the localized content after each run to ensure no previously translated fields were unintentionally overwritten.
The Content summarizer has a Configuration section labelled "Configured when launching the agent." Source fields, target fields, and other summarizer settings are set each time the agent is launched, not during setup.
When you trigger a Content summarizer agent manually, a configuration panel appears before the run starts.
For bulk runs from the content table, the same configuration applies to all selected entries.
Only one agent run can be active per entry at a time. If an entry already has an active run, or has a completed run awaiting review, it cannot be triggered again until the review is completed.
This applies only to agents configured for Use in Agent runs.
The agent runs on all selected entries, up to a maximum of 50 entries per run. The selected content entries become read-only while the agent runs.
This applies only to agents configured for Use in Agent runs.
The content entry form becomes read-only while the agent runs.
This applies only to agents configured for Use in workflows.
An agent configured to run through workflows runs automatically when an entry moves through a configured workflow step.
The content table shows agent status so you can see entries that need action without opening each one individually.
| Agent status | Description |
|---|---|
| Pending | Entries where an agent run is queued or in progress |
| Ready for review | Entries where a completed run is awaiting your review |
| Failure | Entries where the agent run did not complete successfully |
When an entry shows Ready for review, open it to check what the agent changed and approve or revert changes field by field.
When an agent run completes, the entry displays a Ready for review status and the content entry form remains read-only until the review is complete.
After creating agents, you can manage and monitor them from AI Hub → Agents.
Each agent card displays:
You can perform the following tasks:
Edit an agent: Click the pencil icon on the agent card to update the name, description, usage mode, guidelines, or agent-specific settings.
Enable or disable an agent: Use the toggle on the agent card to turn the agent on or off. Disabling an agent pauses it without removing its configuration. This is useful when you want to temporarily stop an agent without losing its settings, for example during content freezes or workflow changes. Any runs already in progress when an agent is disabled will complete normally.
Delete an agent: Click the three-dot context menu on the agent card, then click Delete. Deleting an agent removes it from all workflows, and any queued or pending runs are automatically canceled. Deleting an agent is irreversible.
The KPIs page in AI Hub → KPIs gives you a real-time view of how your agents are performing. You can filter by agent and date range to focus on a specific agent or time period.
AI Agents - KPIs
Each agent displays the following summary metrics:
| Metric | Description |
|---|---|
| Runs | Total number of times the agent has run in the selected period |
| Success rate | Percentage of runs that completed without errors |
| Last run | Time elapsed since the most recent run |
| Avg. duration | Average time taken to complete a run |
| AI tokens | Total number of AI tokens consumed in the selected period |
Below the summary metrics, the AI Tokens Trend chart shows token consumption over time. Switch to the Duration tab to view run duration trends instead.
The Workflow Runs table lists individual runs with their status, result, duration, and start date. Use this to investigate specific runs that failed or produced unexpected output. Click each workflow run to view additional details.