mljourney

The supervisor agent pattern is one of the most widely deployed multi-agent architectures. It organises agents into a two-tier hierarchy: a supervisor (also called a manager, orchestrator, or coordinator) that plans and delegates, and worker agents that execute specific tasks within a defined scope. The supervisor receives the high-level goal, decides which workers to engage … Read more

Debugging AI agent loops is one of the most practically important skills for anyone building agent systems, and it is harder than debugging conventional software. The non-determinism of language model outputs means the same input can produce different behaviour on different runs. Failures can occur anywhere in a multi-step loop and propagate silently through subsequent … Read more

The swarm agent pattern organises multiple agents as peers that hand tasks between themselves based on which agent is best suited to handle the current step. Unlike the supervisor pattern, there is no central coordinator — each agent makes its own routing decisions, passing the task to the most appropriate next agent when the current … Read more

Agent orchestration patterns are the architectural templates that determine how multiple agents (or a single agent across multiple steps) coordinate to accomplish a task. Just as software engineering has design patterns for recurring problems — factory, observer, singleton — agent systems have patterns for recurring coordination challenges: how to divide work, how to manage dependencies, … Read more

Claude’s tool use API lets you give the model a set of callable functions — web search, database queries, code execution, API calls — and have it decide when to call them, with what arguments, and how to use the results to complete a task. It is the foundational mechanism for building agents with Anthropic’s … Read more

Evaluating AI agents is harder than evaluating standard language models, and teams that do not invest in it early pay for it later through production failures they cannot diagnose. The challenge is that agent quality is multidimensional: an agent can produce a correct final answer via a broken reasoning path, or produce a wrong answer … Read more

Pydantic AI is an agent framework built by the team behind Pydantic, the Python data validation library used by FastAPI and most of the modern Python ecosystem. Released in late 2024, it takes a different design philosophy from LangGraph, CrewAI, and AutoGen: it prioritises type safety, structured outputs, and native integration with Python’s type system … Read more

LangMem is LangChain’s dedicated memory library for AI agents, released in early 2025. It provides a structured system for managing the four types of agent memory — in-context working memory, episodic memory of past interactions, semantic memory of facts about the user and domain, and procedural memory of learned workflows — with explicit extraction, storage, … Read more

A coding agent and a standard LLM used for coding are not the same thing, even when the underlying model is identical. The distinction is architectural: a standard LLM generates code in a single prompt-response cycle and stops. A coding agent operates in a loop — it writes code, executes it, reads the output, decides … Read more

Agno (formerly Phidata) is an agent framework designed for building multi-modal, multi-agent applications with a strong emphasis on built-in memory, knowledge, and tool integrations. It positions itself as a full-stack agent platform rather than a minimal orchestration layer — providing pre-built integrations for databases, vector stores, file systems, and external APIs alongside the agent loop … Read more