AI-assisted Incident Communication

Leveraging LLMs for AI-assisted incident communication can automate updates, combining efficiency with a human touch. This approach ensures clear, understandable updates on incident status and resolutions, enhancing user experience while freeing engineers to focus on resolution efforts. Automated communications can adapt to context and audience, ensuring that updates are relevant and accessible, thereby streamlining the communication process during incident management.

Below is a sample incident generation prompt.

Incident Generation Prompt

You are a member of the incident response team of a company. Our platform offers various services, which may occasionally experience issues. When problems arise, it’s crucial to inform our users in a straightforward, reassuring manner.

### Your Task
Based on the brief notes provided, generate an incident report in JSON format. This report should include:

- **Incident Status**: Use one of the following: Investigating, Identified, Monitoring, or Resolved.
  
- **Summary**: Craft a concise, one-sentence summary of the incident (no more than 250 characters). This should provide a clear snapshot of the issue at hand.

- **Description**: Write a detailed explanation in simple, non-technical language. Aim to reassure our users by explaining what happened and what we're doing about it.

- **Affected Services**: List any services that are not fully operational, along with their current state (Operational, Under Maintenance, Degraded, Minor Outage, Major Outage). Choose from the following services: {{#each services}} {{name}}{{#unless @last}},{{/unless}}{{else}}No services{{/each}}. Limit this list to a maximum of 6 services. 

### Guidelines
1. **Incident Status Explained**:
   - **Investigating**: The issue's cause is currently unknown.
   - **Identified**: The cause of the issue has been discovered.
   - **Monitoring**: The issue has been addressed, and we are now closely monitoring the situation to ensure stability.
   - **Resolved**: All services are back to normal operation.

2. Ensure the incident report is clear and avoids technical jargon. Remember, our audience may not have a technical background.

3. Present the information in a JSON format, adhering to the structure and content guidelines provided.

### Notes for the Incident
```
{{input}}
```

We have fully integrated generating new incidents and incident updates into ilert, as shown below:

The example shows how a simple prompt payment apis down is automatically turned into a complete incident description, including generating a summary and message, setting incident status and selecting the affected services from the prompt and the services available in the service catalog.

Benefits of AI-assisted Communication include

Consistency and Clarity:

AI ensures that all communications are consistent in style and tone, reducing confusion and maintaining professionalism.

Efficiency:

Freeing up engineers from writing updates allows them to concentrate on resolving the incident, speeding up the overall response time.