Pydantic AI

Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j

May 29, 2026 · 20:12

Zach Blumenfeld from Neo4j argues that context graphs—a graph-based layer storing decision traces, precedence, and causal chains—extend standard RAG to make AI agents more accurate and explainable. A financial analyst agent, for example, can reject or accept a request by retrieving past decision traces and structurally similar precedents via graph embeddings, not just semantic similarity. Neo4j's one-command tool `uvx create-context-graph` scaffolds a full-stack app with backend, frontend, demo data, and MCP server, supporting 22 built-in domains or custom ontology generation. The underlying `neo4j-agent-memory` package handles entity extraction through a spaCy-to-GLiNER-to-LLM pipeline with deduplication and integrates with pydantic AI, LangGraph, Crew, Google ADK, and others. The episode also covers data connectors for GitHub, Notion, Jira, and Slack, and the ability to store and query decision traces with timestamps, though automated trace quality evaluation is still evolving.

Agent Optimization with Pydantic AI: GEPA, Evals, Feedback Loops — Samuel Colvin, Pydantic

May 7, 2026 · 1:20:40

Samuel Colvin shows how to improve production agents without redeploying using Pydantic AI's GEPA, evals, and Logfire managed variables. GEPA uses a genetic algorithm to evolve prompts, achieving 96.7% accuracy — up from 87% with a simple prompt and 92% with an expert prompt — on a Wikipedia-based political relations task. Managed variables let you update prompts, models, and parameters live via a web interface and A/B test targeting. Evals compare against a golden dataset of 650 MPs; Colvin runs 65 cases in 30 seconds using GPT-4.1. He discusses that prompt optimization is most valuable with private data, that implicit user feedback (e.g., user's next action) can build golden datasets, and that overfitting to small test sets is a risk — the GEPA optimizer may exclude valid relations like 'uncle' if they don't appear in the training split.

DSPy: The End of Prompt Engineering - Kevin Madura, AlixPartners

Jan 8, 2026 · 1:13:13

Kevin Madura of AlixPartners argues that building robust enterprise AI applications requires shifting from brittle prompt engineering to programming with LLMs using DSPy, a declarative framework that treats prompts as implementation details optimized by the system. He demonstrates how typed interfaces (Signatures) and modular logic (Modules) allow developers to focus on control flow while deferring implementation to the LLM, with Adapters controlling prompt formats (e.g., JSON vs. BAML) to improve performance by 5-10%. The talk's core is Optimizers (like MIPRO and JEPA), which automatically tune prompts by learning from data, shown improving a time entry corrector from 86% to 89% accuracy. Real-world examples include routing files by type (SEC filings vs. contracts), using a 'poor man's RAG' with attachments for multimodal documents, and a boundary detector that segments legal documents from images. Madura emphasizes that DSPy enables transferability across models (e.g., GPT-4.1 to GPT-4.1 Nano) and addresses cost concerns by allowing offline optimization to reduce LLM calls.

From Stateless Nightmares to Durable Agents — Samuel Colvin, Pydantic

Nov 24, 2025 · 22:13

Samuel Colvin of Pydantic demonstrates building production-grade durable AI agents using PydanticAI, Temporal, and Pydantic Logfire, arguing that stateless architectures fail at scale and that durable execution with checkpointing and recovery is essential. He shows a 20 questions game where two agents play, but with 20% simulated failures, restarts are avoided by wrapping agents in Temporal wrappers for automatic retries. Colvin then implements a Deep Research agent that plans searches, runs parallel web searches via Tavilli, and synthesizes results, all recoverable. In a live demo, killing the workflow and restarting resumes instantly, replaying cached LLM calls in milliseconds. He also previews Pydantic AI Gateway and demonstrates Pydantic Evals comparing Gemini, GPT-4.1, and Claude Sonnet 4.5 on performance and cost.

Human seeded Evals — Samuel Colvin, Pydantic

Jul 25, 2025 · 12:02

Samuel Colvin, creator of Pydantic, demonstrates how type safety and validation loops in Pydantic AI build reliable GenAI applications. He argues that type-safe frameworks enable confident refactoring, a necessity for evolving AI apps, and shows how returning validation errors to the model fixes simple mistakes like incorrect date formats. The agentic loop with tools and final result tools ensures structured extraction, while type-safe dependencies on tools prevent runtime errors. Colvin also highlights Logfire observability, which traces calls, shows pricing, and helps debug failures like failed memory retrieval. The talk covers agent definitions, validation error retries, and the importance of explicit exit conditions in agent loops.

MCP is all you need — Samuel Colvin, Pydantic

Jul 18, 2025 · 15:24

Samuel Colvin, creator of Pydantic, argues that MCP (Model Context Protocol) is all you need for agent-to-agent communication, simplifying what many are overcomplicating. He explains that MCP's tool calling primitive offers advantages over OpenAPI, such as dynamic tools, logging, and sampling—a mechanism for MCP servers to request LLM calls through the client, enabling nested agentic workflows. Colvin demonstrates a research agent using Pydantic AI that queries the BigQuery public PyPI dataset via an MCP server over stdio, showing how sampling allows the server to generate SQL itself while keeping the main agent's context lean. The demo logs progress to Logfire, an observability platform, and outputs human-readable results. He emphasizes that MCP’s standard I/O mode and extensibility make it ideal for autonomous agents beyond its original desktop coding use case.

Breaking the Chain: Agent Continuations for Resumable AI Workflows - Greg Benson

Jun 3, 2025 · 27:02

Greg Benson from SnapLogic introduces Agent Continuations, a mechanism to capture and resume the full state of AI agents, enabling human-in-the-loop approval and reliable checkpointing for long-running agent workflows. The solution borrows from programming language continuations: at any suspension point (e.g., a tool needing human approval), the agent’s state is bundled into a JSON continuation object containing the messages array, resume request, and approval metadata. This object can be saved or passed to an application layer, allowing agent loops to be fully shut down and later restored without losing progress. Benson demonstrates with a multi-level HR agent that suspends for human approval of an account authorization tool, then resumes seamlessly. The approach handles arbitrary nesting of subagents and is implemented as an open-source Python prototype that works with any OpenAI-compatible API. Future work includes general suspension triggers and integration with existing frameworks like LangChain or Pydantic AI.

Will Agent evaluation via MCP Stabilize Agent Networks? - Ari Heljakka

Jun 3, 2025 · 14:11

Ari Heljakka, CEO of Root Signals, argues that agent evaluation via the Model Context Protocol (MCP) can stabilize agent networks by enabling self-improvement loops. Using a hotel reservation agent example, he shows that without MCP the agent wrongly recommended a competitor hotel, but with MCP it invoked policy evaluators and corrected its behavior automatically. He also demonstrates marketing message optimization via Cursor, where the agent scored and improved text using an MCP-connected evaluation charge. Heljakka emphasizes that success requires a powerful evaluation library with systematic lifecycle maintenance, and introduces Root Signals' free MCP server. The approach promises more controllable, transparent, and dynamically self-correcting agents across different frameworks.

Function Calling is All You Need — Full Workshop, with Ilan Bigio of OpenAI

Apr 23, 2025 · 1:42:54

Ilan Bigio from OpenAI argues function calling is the essential primitive for building AI agents, demonstrating how to implement memory, delegation, asynchronous task execution, and even self-modifying tools—all using the same loop. Starting from a basic weather tool, he builds an agent that stores user facts in a JSON file, delegates complex requests to o1, runs multiple weather lookups in parallel with asyncio, and creates a Bootstrap agent that writes its own Python functions on the fly. He also shares practical tips from his work on Swarm and the Real-Time API, including a stay-silent function to prevent premature responses and the ability to read scripts with XML tags. The workshop emphasizes that sophisticated agent behaviors emerge from simple function calling patterns without needing heavy frameworks.