Kantata debuts Agent Studio for building custom AI agents in plain language

Professional services automation software company Kantata Inc. today unveiled Agent Studio, a tool that lets services firms build custom artificial intelligence agents by describing the job they want done in plain language.

The release goes after a problem Kantata says is building in the professional services automation market. Vendors are shipping narrow agents by the dozen, each scoped to a single job such as resourcing or risk reporting.

The company argues that every new one arrives as another silo to maintain. Kantata sells a single agent that it says carries context across the whole platform. That’s the Expertise Agent, which Kantata launched in June and calls the first AI superagent for professional services.

Agent Studio sits inside the Kantata Expertise Engine and works through conversation. A user describes the job, and the Expertise Agent assembles the new agent and refines it the same way, with every build and edit checked for correctly structured inputs and outputs before it is published.

Nobody has to fill in a form or write code. Once live, an agent can be triggered by a person or picked up automatically by a workflow on a single command.

The intended users are practice leads and delivery directors. Under Agent Studio a standard gets written down once, covering the format, the escalation rules and the outputs a recurring deliverable needs, then applied automatically rather than rebuilt by whoever happens to be staffed that week. Kantata calls the overhead it removes a “prompt tax,” the cycle of drafting and reformatting that a team repeats every time it re-explains the same job to an AI tool.