Xpert + ChatKit now supports MCP Apps. Plugins can provide standard MCP tools and turn tool-call results into real interactive applications inside the conversation.

Users can ask a business question in ChatKit and then work directly with a chart, map, form, media browser, or analysis panel in the answer. The model understands the intent and starts the tool call; the MCP App carries the interaction, state, and follow-up actions.

Xpert + ChatKit MCP Apps architecture: tool calls, MCP Apps Host, sandboxed iframe, and plugin MCP server working together.

As enterprise agents move into production, the hardest question is often no longer whether the model can answer. It is whether the agent can safely understand and operate on real business data.

Across the industry, the conversation around agents is shifting from "prompt engineering" to "harness engineering."

CodeXpert is a next-generation Agentic coding product built on the XpertAI Agent platform, designed for enterprise engineering teams. It integrates conversational collaboration, task-oriented workflows, and an orchestrable agent system to help teams complete the full loop from requirement decomposition, code generation, execution verification, to PR collaboration in a secure and controllable environment.

Today we officially release ChatKit SDK, a full-stack UI solution purpose-built for agent-centric conversation experiences! Whether you’re creating an internal knowledge-base assistant, HR onboarding helper, research companion, shopping concierge, troubleshooting bot, or customer-support agent, ChatKit ships customizable chat embeds that handle every UX detail.

Today, we are excited to announce the official launch of XpertAI Agent Platform version 3.7! The core highlight of this update is the newly introduced Agent Middleware feature, providing developers with fine-grained control over agent execution processes and modular extension capabilities, further advancing agent construction from "functional implementation" to a new stage of "controllable processes and malleable capabilities."

XpertAI 3.6 is officially live! This release comprehensively streamlines every stage from knowledge pipeline creation, orchestration, authorization, publishing to knowledge base operations, enabling teams to visually build a reliable knowledge production line. Meanwhile, the plugin system is now a native capability of the pipeline, helping you quickly integrate external data sources and document processing tools via system integration or marketplace plugins.

With the rapid development of AI technology, enterprise-level intelligent applications have an increasing demand for flexible extensibility, modular decoupling, and cross-system integration. To meet the diverse scenarios of developers and enterprise users, the XpertAI platform officially launches the brand-new plugin system in this release, empowering the platform with true "infinite extensibility".

Introduction: The Evolution from "Tool" to "Partner"​

In today’s explosion of AI technology, most agents remain at the "one question, one answer" level—they can write code, perform analysis, or generate content, but they always require humans to issue step-by-step instructions. However, real-world complex tasks are never single-threaded. A market research project may require simultaneous data cleaning, trend forecasting, and report writing; a product development project often involves cycles of requirement analysis, code generation, and testing validation...

In today's rapidly evolving AI landscape, enterprises face a critical dilemma: how to balance the creativity of LLMs with the stability of processes? While purely agent-based architectures offer flexibility, they are difficult to control; traditional workflows, though reliable, lack adaptability. The Agent and Workflow Hybrid Architecture of the Xpert AI platform is designed to resolve this conflict — it allows AI to possess "free will" while adhering to "rules and order."