Ravi Srivastava: Agentic AI Framework

Autogen Framework Introduction: Autogen as an open-source framework from Microsoft, highlighting its asynchronous, event-driven architecture. The framework addresses issues such as observability, flexibility, control, and scalability in multi-agent systems.
Versioning and Package Management Issues: highlighted that installing Autogen via pip currently defaults to AG2, not the Microsoft version.

Autogen Core: Autogen Core serves as a generic, scalable runtime for multi-agent systems, managing messaging and agent interactions.
Agent Chat provides a lightweight abstraction for constructing agent-based workflows with LLMs and tool integrations.
Studio: Studio is a low-code/no-code visual app for building agent workflows.
Magentic One: Magentic One is a command-line application for running agents, both positioned as research tools rather than production-ready solutions.
Open Source and Research Focus: Autogen is developed as a Microsoft Research community project, with contributions from a broad base and a focus on open-source research rather than commercialization.
Key focus Areas: primarily work with Autogen Core and Agent Chat, avoiding the low-code/no-code tools.

Model Abstraction: The model abstraction in Autogen wraps LLMs such as GPT-4 O mini or other models like Llama.
Message Objects: Messages are core objects representing communication between agents, users, or internal tool calls, and can be simple text or multimodal (including images).
Agent Creation: Agents are instantiated with a model client, a name, and a system message, and can be configured to stream results. The Assistant Agent class is the primary agent type used.
Agent Interaction via on_messages: The on_messages method is used to pass messages to agents asynchronously.

Database Setup and Query Tool: A SQLite database was created and populated with city and ticket price data. A Python function was implemented to query ticket prices by city, serving as a tool for the agent.
Tool Integration Simplicity: Autogen allows direct passing of Python functions as tools without decorators or wrappers, simplifying the process and reducing boilerplate.
Agent Tool Usage Example: An agent was configured with the ticket price lookup tool and demonstrated querying the database and returning a humorous, context-aware response to a user message.
Reflect on Tool Use Attribute: The reflect_on_tool_use attribute ensures that agents can process tool results and continue the conversation, rather than stopping after a tool call.

Multimodal Message Handling: Autogen supports multimodal messages, allowing users to send images alongside text.
Structured Output with Pydantic: Structured outputs are easily achieved by specifying a Pydantic model as the expected output type.

Langchain Tool Adapter Usage: The Langchain tool adapter allows any Langchain tool to be wrapped and used as an Autogen tool, facilitating seamless integration between the two ecosystems.
Agent Task Execution: An agent was tasked with finding flights, using the integrated tools to search online, write results to a file, and select the best option, demonstrating the practical utility of tool integration.

Integration with Autogen: Autogen provides wrappers that enable users to easily incorporate any MCP-compliant tool, such as MCP Server Fetch, into their workflows, allowing for seamless tool usage without requiring additional glue code.
MCP Server Fetch Example: The session included a practical example where the MCP Server Fetch tool, which runs a headless Playwright browser to scrape web pages, was run locally and used within Autogen to review and summarize a website, with the assistant replying in Markdown.
Open Ecosystem and Community Tools: MCP's open standard allows anyone to write and share tools, creating a large, public, and open-source ecosystem accessible from within Autogen.

Semantic Kernel Overview: Microsoft Semantic Kernel is a framework similar to Langchain, focusing on wrapping calls to large language models (LLMs), handling memory, tool calling, plugins, and prompt templating for business-oriented tasks.
Autogen Core Focus: Autogen Core is more agent-focused, designed for building autonomous agentic applications, and is distinct from Semantic Kernel; it orchestrates LLM calls for business logic.
Overlap and Use Cases: There is some overlap between Semantic Kernel and Autogen Core.

Agent Roles: Multiple agents (e.g., Primary and Evaluator) were created with distinct roles and prompts, collaborating to find and evaluate flight options in a round-robin group chat.
Termination Conditions: set based on the evaluator agent replying with 'approve', which signals the end of the workflow. noted that more robust conditions are advisable for production use.
Managing Conversation Flow: the risk of agents entering infinite loops or excessive back-and-forth, recommending prompt tuning and kernel restarts to manage runaway conversations, as Autogen lacks built-in recursion limits.

Agent Interaction Framework: Autogen Core is a framework for managing interactions between agents, regardless of the underlying platform, programming language, or abstraction used to implement the agents.
Standalone vs Distributed Runtimes: Autogen Core supports two runtime types:

Decoupling Logic and Messaging: The framework separates agent logic from message delivery, handling agent lifecycle and communication, while developers are responsible for the agent's internal logic.
Comparison between Autogen Core and LangGraph

Distributed Runtime Architecture: The distributed runtime comprises a host service that manages connections and message delivery, and one or more worker runtimes that register and execute agents.
Session and Message Management: Direct messages are handled via GRPC sessions, with the framework managing the complexities of remote message delivery between processes, potentially in different languages.
Experimental Nature and Use Cases: emphasized that the distributed runtime is experimental, as an architectural preview, not for production use.

Autogen Documentation Confusion: confusion arising from differences between AG2 and Microsoft Autogen documentation for users.

Still in progress

Ravi Srivastava