An Intellyx Brain Candy Brief
You can tell Adopt AI to exercise any application like an end user would in order to create a functioning Agent, which the business developer or other agents can then address via natural language prompts or API requests within the context of a multi-agent workflow.
This zero-shot agent building approach may sound overly straightforward in today’s overhyped market, where superhuman “AI magic” is often touted behind the scenes. But it really makes sense when you consider an AI’s ability to rationalize skills and extract tooling by simply operating and encapsulating the existing software packages and knowledge bases that the enterprise already depends on, rather than requiring hand-wiring of each integration.
New agents can be run and tested in private sandboxes to reduce the potential impact of modernization on existing applications. In addition to a command center UI with low-code automated discovery and deployment of agents from existing apps, there’s also a semi-pro-code approach that allows developers to publish captured agents and actions to the MCP server of their AI framework of choice.
Copyright ©2025 Intellyx B.V. Intellyx is an industry analysis and advisory firm focused on enterprise digital transformation. Covering every angle of enterprise IT from mainframes to artificial intelligence, our broad focus across technologies allows business executives and IT professionals to connect the dots among disruptive trends. At the time of writing, Adopt AI is not an Intellyx customer. No AI was used to write this article. To be considered for a Brain Candy article or event visit, email us at pr@intellyx.com.
