Iloveagents
AI agents worth falling in love with. Built by the community, loved by everyone.❤️
Last verified:
What is Iloveagents?
iLoveAgents is a content-first, developer-focused blog created by Christian Glessner that provides practical patterns and playbooks for building production-grade AI agents. The site focuses specifically on Microsoft Agent Framework and Azure AI Foundry, offering hands-on tutorials in both Python and .NET for developers who want to build real, production-ready AI agents rather than just experimenting with prototypes.
Key features of iLoveAgents include comprehensive tutorials on multi-agent workflows, tool integration and grounding techniques, deployment guides for moving from local development to managed Azure hosting, and practical coverage of observability, cost controls, and human-in-the-loop patterns. The site also offers a custom VS Code theme called "iLoveAgents AI Foundry Theme" designed specifically for Microsoft Foundry developers to make their day-to-day development experience more enjoyable.
iLoveAgents is designed for developers, engineers, and technical teams who are building AI agents using Microsoft's ecosystem. This includes developers working with Azure OpenAI, teams adopting Microsoft Agent Framework for new multi-agent projects, and organizations looking to deploy production-grade agentic applications with proper observability, safety guardrails, and enterprise governance. The content is particularly valuable for those transitioning from Semantic Kernel to the new Agent Framework or those starting fresh with agent development on Azure.
Iloveagents pricing
Pricing model: Freemium
iLoveAgents itself is a free blog resource with all tutorials, patterns, and content available at no cost. The custom VS Code theme is also free to install. However, implementing the tutorials requires Azure services that are paid: Azure OpenAI model usage has per-token pricing, Azure AI Foundry Agent Service hosting has associated costs, and Azure storage/logging services are billed separately. Model pricing, limits, and available regions vary by provider in the Azure catalog. The framework SDK itself is open source with no licensing fees.
Iloveagents pros
- Focuses on production-grade AI agents, not just prototypes
- Provides practical patterns and playbooks rather than theoretical content
- Covers both Python and .NET implementations
- Teaches multi-agent workflows comprehensively
- Includes tool integration and grounding techniques
- Offers deployment guides from local dev to Azure hosting
- Covers observability and monitoring for agent runs
- Addresses cost controls and optimization strategies
- Includes human-in-the-loop pattern implementations
- Provides custom VS Code theme for Foundry developers
- Independent community resource not affiliated with Microsoft
- Open to community contributions and topic suggestions
- Covers responsible AI guardrail patterns
- Teaches Azure AI Search integration for enterprise knowledge
- Includes real-world agent scenarios and telemetry lessons
Iloveagents cons
- Independent resource not officially affiliated with Microsoft
- Content focuses only on Microsoft ecosystem (Agent Framework, Azure AI Foundry)
- Microsoft Agent Framework is still in public preview with API changes expected
- Does not cover non-Microsoft AI agent frameworks
- Some deployment guides are still upcoming, not all content available yet
- Requires Azure account and paid Azure services for full implementation
- Model pricing, regions, and limits vary by provider requiring separate research
- Migration from Semantic Kernel requires incremental approach not fully automated
Frequently asked questions about Iloveagents
What is iLoveAgents?
iLoveAgents is a content-first blog by Christian Glessner with practical patterns and playbooks for building production-grade AI agents on Microsoft Agent Framework and Azure AI Foundry. It offers Python/.NET tutorials, multi-agent workflows, tools & grounding techniques, and deployment guides for developers building real, production-ready AI agents.
Is iLoveAgents affiliated with Microsoft?
No. iLoveAgents is an independent community and learning effort. The opinions expressed are the author's and contributors' own, not Microsoft's official position or documentation.
What is the Microsoft Agent Framework?
The Microsoft Agent Framework is an open-source SDK and runtime for building AI agents and multi-agent workflows in Python and .NET. It unifies learnings from Semantic Kernel and AutoGen and integrates with Azure AI Foundry for deployment, observability, and governance.
How is the Microsoft Agent Framework different from Semantic Kernel?
Semantic Kernel emphasized connectors, memory, and reliability. The Microsoft Agent Framework brings those enterprise foundations together with first-class agent orchestration and a cleaner abstraction surface. The recommendation is to keep stable SK applications but start new agent projects on the Agent Framework.
Which LLMs can I use with the Microsoft Agent Framework?
The Agent Framework is model-agnostic. It ships chat clients for Azure OpenAI and the OpenAI API and can target any inference service that implements the Microsoft.Extensions.AI IChatClient interface, including local/OSS models via adapters like Ollama. In Azure AI Foundry, you can pick from the model catalog which includes Azure OpenAI plus other providers. For providers not in your catalog or region, you can call them via a compatible client or small adapter.
How do agents call tools and use data with the Microsoft Agent Framework?
Tools can be registered via OpenAPI or through supported/partner connectors so agents can call external systems safely. For enterprise knowledge, agents are grounded with Azure AI Search or other sources surfaced through Foundry. Interop patterns like MCP (Model Context Protocol) and agent-to-agent (A2A) communication are supported across the ecosystem.
How stable are the Microsoft Agent Framework APIs today?
The framework is in public preview. Core concepts like agents, tools, messages, and workflows are converging, but you should expect some changes while the surface area settles. Best practices include pinning package versions, watching the GitHub repo for updates, and budgeting time for minor updates as the framework evolves.
What is Azure AI Foundry?
Azure AI Foundry is Microsoft's unified platform to build, evaluate, secure, and operate generative-AI and agentic apps. It centralizes models from Azure OpenAI and the catalog, orchestration capabilities, data grounding, safety features, evaluations, hosted endpoints, monitoring, governance, and lifecycle management all in one workspace.
Can I trace and debug agent runs in Azure AI Foundry?
Yes. Foundry provides observability to inspect conversations, tool calls, token and latency metrics, and failures. You can export traces using OpenTelemetry and iterate locally before promoting to production environments.
Can I contribute to iLoveAgents or suggest topics?
Absolutely. You can open an issue or pull request on the repository, or reach out on LinkedIn. The author is especially interested in real-world agent scenarios, telemetry lessons, and responsible-AI guardrail patterns from contributors.