Serval’s super agent Catalyst creates roving background agents to identify and fix IT issues before they’re ticketed
Serval is making Catalyst , its AI agent for building enterprise automations, generally available Thursday and enabling it by default for customers — allowing teams of AI agents to decide what should be automated and then build the automation itself. Catalyst sits above Serval’s AI-native service management platform as an admin-facing “super agent.” It can inspect ticket history, standard…
Serval has released Catalyst, its AI agent for building enterprise automations, and made it available to customers by default. This AI-native service management platform serves as a "super agent" for teams of AI agents, which can identify recurring work, draft the necessary workflows, skills, forms, access policies, journeys and dashboards, and even create proactive agents that continuously search for new work to automate.
Catalyst goes beyond simply creating workflows by analyzing ticket history, standard operating procedures, natural-language instructions, and more to determine what should be automated. The AI agent can also take existing help desk data and draft the required automation, presenting the result to administrators for review. Users can even upload a standard operating procedure or spreadsheet and ask Catalyst to turn it into an executable system.
Some of Catalyst's capabilities include building workflows, authoring help desk skills, creating onboarding and offboarding journeys, configuring access-management policies, constructing dashboards, investigating operational issues, and debugging failed workflow runs. Unlike Serval's previous workflow builder, Catalyst aims to become the primary interface for configuring the platform, with the long-term goal of making anything an administrator can do through the UI also achievable through Catalyst.
The underlying workflows are code-backed, and Catalyst can generate TypeScript based on requests, such as building password-reset workflows that connect with systems like Okta, Google Workspace, and Microsoft Entra. Administrators can then add approvals or restrict access to the workflow. Catalyst uses models from "frontier labs" and runs evaluations to determine which models work best for different tasks, making the models deliberately swappable.
Serval works with enterprises that have their own models and allows administrators to supply their own OpenAI or Anthropic API keys.
Written by urgent.news from VentureBeat's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
