Building TeamRescue: Finding the Right Expert with FalkorDB

Description and use

TeamRescue uses FalkorDB to recommend an expert when a service fails and its owner is unavailable, considering ownership, dependencies, and incident history. Recommendations update with availability changes and are saved for future handoff.

Problem

During an incident, knowing the service owner is useful—but what happens when that person is unavailable?

Outcome

TeamRescue successfully recommends an available expert based on graph traversal, and the recommendation adapts when availability changes. Draft handoffs preserve context for future review.

Workflow

• 1. User queries "Checkout is failing. Who can help?"
• 2. Backend checks for an available owner of the failing service.
• 3. If no owner is available, backend traverses service dependencies to find incidents affecting dependent services.
• 4. Backend selects a person who resolved a related incident and is currently available.
• 5. AI formats the recommendation with supporting evidence (ownership, dependencies, incident history).
• 6. User can save a draft handoff containing the recommendation and context.

Evidence

When Priya is unavailable and Rahul is available, TeamRescue recommends Rahul based on his previous incident experience.

Source

The application first checks for an available owner. A person with relevant resolved-incident experience is the fallback.

Source

TeamRescue lets users save a draft handoff containing the recommended person, service, a note, and supporting context in FalkorDB.

Source