# AI Examples > Start with the AI samples of TX Text Control: the web sample, a first local chat, document analysis demos that need no model, Agent Skills and MCP servers. - **Product:** TX Text Control .NET Server - **Section:** Documentation - **Kind:** Topic - **Path:** TX Text Control .NET Server > Examples > AI Examples - **1286 words** - **Web URL:** https://docs.textcontrol.com/tx-text-control-dotnet-server/examples/ai/ - **LLMs URL:** https://docs.textcontrol.com/tx-text-control-dotnet-server/examples/ai/llms.txt - **LLMs-Full URL:** https://docs.textcontrol.com/tx-text-control-dotnet-server/examples/ai/llms-full.txt --- AI samples for TX Text Control .NET Server range from a console chat with a local language model to a complete web application and a document server for AI agents. [Examples](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/examples/llms-full.txt) in AI Integration lists all of them with their repositories. Where to begin, which online demos cover the same tasks without a model and which articles introduce the skills and MCP servers are collected below. ### Where to Start The samples of the TX Text Control AI preview, version 0.1.0-beta.3 at the time of writing, are in the repository [txtextcontrol-ai-samples](https://github.com/TextControl/txtextcontrol-ai-samples). They need a GGUF model and an inference runtime that you provide; [Run the Samples](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/text-control-ai/#run-the-samples) in Text Control AI describes the setup. | Example | What it shows | Where | |---|---|---| | The complete web application | Chat, Document Studio, runtime administration, knowledge collections and the Document Editor in one ASP.NET Core application. Text Control names it the best way to explore the whole workflow; it uses the MCP document server sample, which you start first | [samples/WebDocumentAssistant](https://github.com/TextControl/txtextcontrol-ai-samples/tree/master/samples/WebDocumentAssistant) | | A first local chat | The smallest sample: a console loop that answers prompts with a local model | [samples/LocalChat](https://github.com/TextControl/txtextcontrol-ai-samples/tree/master/samples/LocalChat) | | A local chat without the repository | A streaming console chat built step by step in a new project, written for version 0.1.0-beta.1 of the preview | [Running a Local LLM in .NET C# with TX Text Control AI](https://www.textcontrol.com/blog/2026/09/10/running-a-local-llm-in-dot-net-c-sharp-with-tx-text-control-ai/) | The blog article [Introducing TX Text Control AI: Private AI for Real Document Workflows in .NET C#](https://www.textcontrol.com/blog/2026/09/09/introducing-tx-text-control-ai-private-ai-for-real-document-workflows-in-dot-net-c-sharp/) introduces the preview and its samples. ### Document Analysis Without a Model Not every analysis needs a language model. Four online demos classify documents, extract tables, map form fields and sanitize documents with rules that give the same, explainable result every time. Each has a sample project on GitHub: | Example | What it shows | Where | |---|---|---| | Document classification | DOCX files classified with weighted rules, with the confidence and the evidence behind each result | [Document Classification](https://demos.textcontrol.com/demos/server-side-processing/document-classification), [TXTextControl.Document.Classification](https://github.com/TextControl/TXTextControl.Document.Classification) | | Table extraction | The domain of a table detected, its columns normalized and its data extracted as JSON | [Structured Table Extraction](https://demos.textcontrol.com/demos/server-side-processing/structured-table-extraction), [TXTextControl.SmartTableExtraction](https://github.com/TextControl/TXTextControl.SmartTableExtraction) | | Form field mapping | Form field names matched to the properties of JSON data with confidence scores, then merged | [Form Field Mapping](https://demos.textcontrol.com/demos/server-side-processing/form-field-mapping), [TXTextControl.FormFieldMapper](https://github.com/TextControl/TXTextControl.FormFieldMapper) | | Sanitization | Metadata, form values, comments, tracked changes and embedded content found and removed before a document leaves your system | [Document Sanitization](https://demos.textcontrol.com/demos/server-side-processing/document-sanitization), [TXTextControl.Sanitize.Data](https://github.com/TextControl/TXTextControl.Sanitize.Data) | The sample projects target .NET 10 and version 34.0. The blog article [From Classification to Data Extraction: New Document Analysis Samples](https://www.textcontrol.com/blog/2026/08/31/from-classification-to-data-extraction-new-document-analysis-samples/) introduces the demos, and [Document Analysis](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/analysis/llms-full.txt) compares these approaches with a language model. ### Agent Skills and MCP The repositories of the MCP document server and the Agent Skills are listed in [Examples](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/examples/#mcp-servers-and-agent-skills) in AI Integration. These articles introduce them: | Example | What it shows | Where | |---|---|---| | Agent Skills | Skills that teach AI coding assistants to integrate the Document Editor | [Introducing Text Control Agent Skills](https://www.textcontrol.com/blog/2026/03/27/introducing-text-control-agent-skills/) | | ServerTextControl skills | Skills for document processing with `ServerTextControl` | [Expanding Text Control Agent Skills: New ServerTextControl Skills for AI Assisted Document Processing](https://www.textcontrol.com/blog/2026/04/13/expanding-text-control-agent-skills-new-servertextcontrol-skills-for-ai-assisted-document-processing/) | | MCP document backend | A backend whose document operations AI agents discover and call as MCP tools | [Build Your Own MCP-Powered Document Processing Backend with TX Text Control](https://www.textcontrol.com/blog/2026/04/16/build-your-own-mcp-powered-document-processing-backend-with-tx-text-control/) | | Documents from natural language | Documents created from instructions in natural language through the MCP server | [AI Natural Language Document Generation with MCP and TX Text Control .NET](https://www.textcontrol.com/blog/2026/07/16/ai-natural-language-document-generation-with-mcp-server-and-tx-text-control-dotnet/) | The blog samples that call OpenAI's hosted API are listed in [Examples](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/examples/#blog-samples-with-a-repository) in AI Integration; three of them were written for versions 31.0 and 32.0. ### Next Steps - [Text Control AI](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/text-control-ai/llms-full.txt): the packages of the preview and how to run the samples. - [Local / Private LLMs](https://docs.textcontrol.com/tx-text-control-dotnet-server/ai/local-llms/llms-full.txt): run models on your own hardware. - [Document Processing Examples](https://docs.textcontrol.com/tx-text-control-dotnet-server/examples/document-processing/llms-full.txt): samples of document processing without AI. --- ## Nearby - **Previous:** [Digital Signature Examples](https://docs.textcontrol.com/tx-text-control-dotnet-server/examples/digital-signatures/llms-full.txt) - **Next:** [What's New](https://docs.textcontrol.com/tx-text-control-dotnet-server/whats-new/llms-full.txt)