Skip to content
View jonathanscholtes's full-sized avatar
🏗️
Designing Always-On Agent Systems.
🏗️
Designing Always-On Agent Systems.
25 followers · 5 following

Achievements

Achievement: StarstruckAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: StarstruckAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Block or report jonathanscholtes

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jonathanscholtes/README.md

Jonathan Scholtes

Senior AI Engineer / Architect @ Microsoft
Designing agentic, event-driven AI systems that integrate tools, data, and workflows in real-world environments

Start Here

These are the best entry points to understand how agentic systems operate in real-world environments.

  • BrandSense (Multi-Agent Brand Intelligence)
    → Brand analysis pipeline combining retrieval, scoring, and validation
    → Applies agent-based workflows to business evaluation scenarios

  • Contract Risk Analysis (MCP + Foundry)
    → Contract analysis using MCP for tool-based evaluation and data access
    → Enables structured, repeatable, and auditable analysis workflows

  • ITSM Multi-Agent System (Microsoft Foundry)
    → IT service management implemented with agents and structured orchestration
    → Covers ticket classification, routing, and lifecycle handling

  • Agents Audit System
    → Observability and evaluation framework for agent/tool interactions
    → Tracks execution flow, decisions, and tool usage across workflows

These systems move beyond prompt-response interactions into structured, tool-driven execution.

Foundations

Core components and architectural patterns used across agentic systems.

Learn More

📌 Notes

All projects focus on:

  • Real-world applicability
  • System design over isolated prompts
  • Production-oriented architectures

Pinned Loading

  1. LangChain-RAG-Pattern-with-React-FastAPI-and-Cosmos-DB-Vector-Store LangChain-RAG-Pattern-with-React-FastAPI-and-Cosmos-DB-Vector-Store Public

    Complete project (web, api, data) covering the implementation of the RAG (Retrieval Augmented Generation) pattern using Azure Cosmos DB for MongoDB vCore and LangChain. The RAG pattern combines lev…

    Python 16 6

  2. Travel-AI-Agent-React-FastAPI-and-Cosmos-DB-Vector-Store Travel-AI-Agent-React-FastAPI-and-Cosmos-DB-Vector-Store Public

    Explores the implementation of a LangChain Agent using Azure Cosmos DB for MongoDB vCore to handle traveler inquiries and bookings. The project provides detailed instructions for setting up the env…

    Python 24 15

  3. azure-ai-foundry-agentic-workshop azure-ai-foundry-agentic-workshop Public

    Workshop for building intelligent AI solutions using Azure AI Foundry, featuring Vector Search, RAG, Agentic AI, and multi-agent orchestration with LangChain and Azure AI Search.

    Jupyter Notebook 25 12

  4. Azure-AI-Foundry-Semantic-Kernel-RAG Azure-AI-Foundry-Semantic-Kernel-RAG Public

    Demonstrates an end-to-end conversational knowledge agent using Azure AI Foundry and Semantic Kernel, featuring a primary HR agent with Azure AI Search and supporting agents for observability and m…

    Python 1

  5. contract-risk-mcp-foundry contract-risk-mcp-foundry Public

    An always-on, autonomous agentic risk platform demonstrating event-driven AI agents on Azure for continuous FX and interest rate contract risk monitoring.

    Python 1 1

  6. Azure-AI-Foundry-BrandSense Azure-AI-Foundry-BrandSense Public

    Multi-agent marketing asset validation on Microsoft Foundry. Checks brand, legal, and SEO compliance from uploaded PDFs and produces a scored creative brief.

    Python 1