Some startups pride themselves on having prestigious financial backers, but having prestigious customers is just as important. This is a primary point of pride for Serval, an enterprise AI company that announced a forty-seven million dollar Series A funding round. The round was led by Redpoint Ventures, with participation from prominent venture firms including First Round, General Catalyst, and Box Group. Even more impressive than its funders is the company’s client list, which includes major AI players like Perplexity, Mercor, and Together AI.
Serval uses agentic AI models to automate IT service management. The company takes a unique approach that leverages the power of agentic AI while avoiding many of its common pitfalls. One agent is used to code internal automations for everyday tasks, such as authorizing software or provisioning a device. The founders describe it as a vibe-coding tool, overseen by an IT manager but performing most of the work independently. A separate help desk agent responds to user requests by calling those tools on command, following the rules established for each one.
Serval CEO Jake Stauch says the key was to make the process of building a tool as simple as possible. The goal is to ensure companies do not feel the marginal cost of building these automations. The aim is to make it easier to automate something forever than to do it manually just once.
Splitting the task into two agents provides managers with a way to monitor permissions. When an automation is created, the manager sets rules for when it can be used. This provides an extra line of defense against overeager help desk agents. Enterprise clients are very aware of the risks of a rogue AI system, which is part of why Serval decided against a single all-purpose Help Desk Agent.
You would not want someone to go into a messaging system and request that all company data be deleted, only to have a helpful AI agent agree to do it. Instead, the agent should state that it does not have a tool for deleting all company data, but that it can help with other tasks like resetting a password.
Because the tools themselves are deterministic, they can include extremely complex permissions. These can require specific multi-factor authentication or only allow actions within a certain time frame. Whenever those rules need to be changed, an AI agent is ready to dive into the codebase and make the adjustment.
This is a new approach to the common problem of how to oversee agentic AI systems. You want full visibility and control into what an AI agent is doing. This is achieved by using Serval to build those tools and customize the permissions and approvals behind them.