Unqork documentation is available in two workspaces: UnqorkAI for the latest AI-first platform, and legacy Unqork for previous versions. Use the drop-down near the logo to switch.

This article covers UnqorkAI features. UnqorkAI requires an active AI capabilities agreement. To upgrade from Unqork 9.0 or learn more, contact your Unqork representative.

Build Agent

Next
  • Updated on Sep 29, 2026
  • Published on Sep 14, 2026
The UnqorkAI Build Agent is integrated directly into the Module Builder. Creators describe what they want to build in plain language. The agent creates a plan, presents it for approval, then builds the components, connects the logic, and runs test...
  • Updated on Nov 3, 2026
  • Published on Jul 1, 2026
The Build Agent is the UnqorkAI platform's AI assistant for building Unqork modules. You describe what you want in plain language, and the agent creates a plan for your review. Once approved, the agent builds the components, generates tests, and sho...
  • Updated on Nov 13, 2026
  • Published on Aug 31, 2026
The Build Agent is an AI assistant in the Module Builder. Creators use it to build and edit applications and modules, create and use Smart Components, write tests, and answer questions about module configuration. The panel has three tabs: Active ...
  • Updated on Nov 13, 2026
  • Published on Jul 29, 2026
The Active Task tab and the History tab in the Build Agent panel work together but serve different purposes. Understanding the relationship between tasks and plans, and how the agent handles context in a task, helps Creators work with the Buil...
  • Updated on Nov 13, 2026
  • Published on Oct 8, 2026
The Build Agent thinks through each step before acting. This article explains what the Reasoning panel displays, why the agent shifts effort levels mid-task, and how long tasks are managed. Reasoning Panel The Reasoning panel displays in the cha...
  • Updated on Nov 13, 2026
  • Published on Sep 12, 2026
The Build Agent assists with tasks that have clear structure or a well-defined pattern: explaining how parts of a module relate, suggesting debugging starting points, and drafting configurations for review. Incorrect suggestions are common. The agen...
  • Updated on Nov 13, 2026
  • Published on Jul 1, 2026
The Build Agent is an AI assistant in the Module Builder. Creators describe what they want in plain language. The agent creates a plan, builds the components, connects the logic, and runs tests to verify the result. The Build Agent can: Buil...
  • Updated on Nov 13, 2026
  • Published on Jul 1, 2026
AI components expose settings that control how the AI model generates its responses. Which models are available, and which settings a model reads, depend on the LLM credential the component runs on. Chat Agent Smart Component : These settin...
  • Updated on Nov 13, 2026
  • Published on Nov 3, 2026
UnqorkAI is Unqork's AI-first enterprise development platform with AI-assisted development, Smart Components, and Agentic Smart Components. This article describes how UnqorkAI processes data, where it is transmitted and stored, and the applicable ...
  • Published on Nov 13, 2026
Build Agent context is the information that the Build Agent uses while it plans and builds. Two kinds of context exist, and each works differently. This article compares them and helps Creators decide where information belongs. A detailed articl...
  • Published on Nov 13, 2026
Chat context is the set of items that the Build Agent uses for the current task. The items display in the Context list above the prompt field on the Active Task tab. Creators add items, review them, and remove them. Chat context resets whe...
  • Published on Nov 13, 2026
Context Documents are entries that the Build Agent keeps for a workspace and reads at the beginning of every task. Every Creator in the workspace shares them. This article explains how the agent uses them and how Creators view, edit, and cle...
  • 2 Articles
  • Updated on Nov 13, 2026
  • Published on Nov 13, 2026
MCP Connectors and the MCP server are Beta features for environments with UnqorkAI. Test each connector and tool, and verify the results before relying on them. The Model Context Protocol (MCP) is an open standard that lets AI agents work with ot...