← 3 Agents


These simple demos show how deterministic agents can leverage TF/UFA semantic capabilities. The focus is not on autonomous AI, but on how traditional software can leverage language models for tasks such as tool use, file analysis, retrieval, and tool selection.

The TF/UFA semantic capabilities are marked with “@” and are described in 2.5 Agentic LLM (TF/UFA semantic) functionality.

For details see the lab notes docx #606_ai_ides.docx on the Gdrive.

TOC

  • 1b Basic tool (with AI). Demonstrates a simple deterministic tool enhanced with LLM semantic capabilities. Shows how AI can improve a traditional tool without changing the overall control flow.
  • 3 Filesystem. Demonstrates how an agent can explore, read, and organize files using semantic understanding. Shows the combination of deterministic filesystem operations with LLM-assisted interpretation.
  • 5 RAG. Demonstrates Retrieval-Augmented Generation (RAG). The agent retrieves relevant documents and uses an LLM to summarize or answer questions based on the retrieved information.
  • 6c MCP (LLM tool choice). Demonstrates Model Context Protocol (MCP) style tool selection. The LLM determines which tool should be used while deterministic code performs the actual execution.


26.0618 (0521)