LogicGate GRC Agents for automating actions in workflows

GRC Agent is your AI teammate — an agentic automation that executes GRC workflow steps on behalf of your users, so your team can focus on higher-value work.

LogicGate GRC Agents is a paid add-on. Contact your account team to activate and configure agents in your environment.

Understanding GRC Agents in Your Environment

Note: To add new agents or adjust existing configurations, contact your account team.

1. Check activation status: Go to Admin > Spark AI to see whether GRC Agents is active and which LLM model each agent runs on.
2. View configured agents: Go to Build > GRC Agents to see all agents in your environment, including the app, trigger step, and current status for each.
   
3. How agents are set up: During implementation, your LogicGate team will work with you to define:
   1. Trigger application and workflow step
   2. Agent name and prompt with necessary context

4. Agent users: Each GRC agent is associated with a system-generated agent user that can be tracked and governed like a human user. To control its access:
   1. Add or remove it from a Permission Set to set its level of access
   2. Use User Groups to restrict access to certain human users only to protect your sensitive records

See the Risk Cloud Permissions and Access help article to learn more

Running a GRC Agent

Note: Agents can currently only be triggered on demand from a record at the configured trigger step.

1. When an agent is enabled on a workflow step, the record assignee will see a Run GRC Agent banner.
   
2. Click Run GRC Agent. The record is temporarily assigned to the agent while it works.
   
3. Once execution completes, the record is reassigned to you with a status summary — what the agent did, what needs your review, and any errors encountered. 
   
4. All agent-populated fields are labeled with a confidence score, reasoning, and source citations so you can quickly assess what to accept or correct.
   
   
    
5. The agent also posts a comment with the same summary, so the human assignee (reviewer) can refer back to it at any time.
   1. If you refresh the page, it resets to the initial run state — refer to the record comment for a persistent summary.

What Agents Can Do

Agents perform actions based on the agent prompt and the step permissions configured for your workflow.

1. Autofill fields: Populates blank and supported fields using values on the current record and up to 5 attachments. Only high-confidence values are autofilled — including conditional fields that the agent unhides as part of execution. Each populated field is labeled with the agent name and displays a confidence score, reasoning, and source citations.
2. Link records: Links records with a strong/possible match strength (≥60%) using Record Linking Recommendations. Behavior depends on your workflow mapping between triggering WF and linked WF:

• 1-to-1 or many-to-1 mapping — links the single strongest match
• 1-to-many or many-to-many mapping — links all strong matches
• If the agent prompt specifies linking only one record, the agent honors that instruction

3. Create records: Creates new records based on linked workflow configurations and agent prompt instructions:

• 1-to-1 or many-to-1 mapping — creates one record
• 1-to-many or many-to-many mapping — creates multiple records

4. If both linking and creation are enabled, the agent first attempts to link strong/possible matches (≥60%). If no strong/possible match is found, it creates a new record instead
5. Assign and reassign records: When triggered, the record is temporarily reassigned to the agent while it works. Once execution completes, the record is automatically reassigned back to the original human assignee.
6. Post execution summary & notify reviewer: After execution, the agent leaves a comment on the record tagging and notifying the original assignee with a summary of what it did, what needs review, and any issues encountered — so the summary is accessible at any time, not just immediately after execution.
7. Audit trial: All field and record changes made by the agent are tracked in Record History and Field History — the same audit trail used for human user actions — so you always have a clear record of what the agent did and when.

FAQs

1. Do I need to pre-configure Autofill or Record Linking Recommendations for agents to use those skills?
   1. No. All agents have Autofill, Link Record, and Create Record skills built in. The agent uses them based on the prompt and step permissions — no separate configuration needed.
   2. To get the best results, we recommend:
      1. Writing clear field names, guidance text, and tooltips so the agent has more context
      2. Configuring RLR by selecting the top 5 most descriptive fields for each linked workflow.
2. What step permissions does the agent need?
   1. Agents follow the same step permission model as human users. Grant the agent user Edit permission on the trigger step so it can populate fields and perform link or create actions.
3. Which field types can agents populate?
   1. GRC Agents use Autofill to populate fields, so the same field support applies:

2. Agents populate blank, visible, and editable fields on the current workflow step. When an agent unhides a conditional field during execution, it will also autofill those newly revealed fields — but only if confidence is high.

4. How do I troubleshoot an agent?
   1. Go to Build > GRC Agents, click the gear icon on the top right corner to review agent status and execution details

Coming Soon

• Autofill using linked workflow section layout or Table Report view as context.
• Agent execution stats (fields populated, records linked/created, execution time)
• Autofill linked records created by the agent 
• Self-serve agent builder for builders to edit configurations after initial setup
• Trigger agents via job triggers, including record move