Appian has added AI-assisted spec-driven development and model context protocol integration for agents to its software platform, extending the way AI tools connect to business processes and data.
This update focuses on two areas: AI agents that can operate across external systems with more context, and development tools that use AI to generate application specifications from legacy software. The goal is to place AI within a structured process model rather than treating it as a standalone layer.
Appian also reviewed new research on agent learning. Users will be able to track agent performance and apply agent memory to various processes to improve decision making. Future options are intended to allow users to set optimization goals and recommend changes that can be safely applied.
Change agent
Appian’s adoption of the Model Context Protocol (MCP) is intended to enable agents to securely connect with external systems. The same approach also enables third-party agents to use Appian tools, including the data fabric, which provides unified read/write access to enterprise data.
The data fabric has also been updated with a unified metadata model. Appian said the changes will provide agents with more context about how information is structured and linked across systems, with the goal of creating a common vocabulary for business data.
Appian has also begun a technology partnership with Snowflake. The deal is described as combining process orchestration and data fabric with Snowflake’s AI data cloud, including direct MCP-enabled integration between Appian data fabric and Snowflake.
Snowflake said this setup will allow agents to interact directly with Snowflake Cortex AI to support decision-making based on data held across enterprise systems.
“Enterprises don’t need more AI experimentation; they need AI that delivers real business outcomes based on managed data,” said Baris Gultekin, vice president of AI at Snowflake. “By combining Appian’s process orchestration and data fabric with Snowflake AI Data Cloud, we bring intelligence directly into business flows. Together, we enable secure, enterprise-grade AI where agents can access trusted data through Cortex AI, act in context, and drive measurable impact across the business.”
development tools
Alongside the agent update, Appian introduced what it calls AI-assisted spec-driven development. This feature uses AI to extract specifications from legacy applications and transform them into visual plans that include user interfaces, data models, and process flows.
AI developer agents can work under human supervision and complete tasks based on these specifications. Appian said this approach can reduce rework while helping teams modernize older applications.
The new developer MCP server enables organizations to build and update Appian applications using external AI development tools. Appian said it will support a variety of AI models to allow teams to work in the environment of their choice.
Mike Beckley, chief technology officer and founder of Appian, tied these tools into broader platform changes.
“Appian Composer, Agents, and Appian MCP Server enable reliable agent process orchestration and application modernization,” said Beckley. “Composer complements Appian’s agent orchestration and data fabric with new spec-driven development tools that are conversational and iterative. Under the hood, Appian Composer is built on Appian’s new open MCP, which enables complete application assets (requirements, apps, data entities, logic, workflows, security/governance rules, integrations, and multi-object dependencies). A model-driven representation of the software, exposed as a context for developers and agents to safely evolve and optimize.”
Customer example
Appian cited healthcare risk management provider Global Excel Management as an example of how a customer is applying AI to process change programs. The company is using Appian to reimagine its billing workflow.
“As part of our digital transformation, we are evolving our billing processes by moving from fragmented workflows to a highly operational level that takes advantage of technological advancements powered by AI capabilities,” said Pascal Tanguay, SVP, Global Technology Services, Global Excel Management. “Using Appian, our processes are unified. From initial reception to adjudication, our advanced technology reduces redundant tasks and reduces complexity for our team members. This ensures that our claims process is completed consistently, more efficiently and accurately.”
Appian’s broader message is that AI systems become more useful when coupled with formal business processes, connected data, and defined controls. Its latest platform changes are designed to make that model work for both business users running automated processes and developers updating applications.
The new capabilities cover agent interoperability, shared data context, developer tools, and cross-process memory, extending Appian’s commitment to creating process models as a framework for AI systems to access information and take actions.
