Pydantic
20 stories
PydanticToolsPydantic runs on RunsOn Pydantic runs on RunsOn . We moved to RunsOn on September 1. It launches ephemeral EC2 runners for Logfire's GitHub Actions workflows in our AWS account.
PydanticToolsAnnouncement: Pydantic v2.14 Release Pydantic v2.14 was released on October 8th. You can install it now from PyPI : pip install --upgrade pydantic This release features the work of 13 external contributors and provides various new…
PydanticToolsWould you deploy an agent you don't control? I have spent my career believing that software should be explicit. Explicit dependencies. Minimal privileges. Observable behavior. The usual sane software practices.
PydanticToolsBuilding production agents: the observability layer This piece is a guest post from Vstorm. A while back, one of our agents handed a customer a wrong answer with total confidence. No exception. No failed test. The logs were clean.
PydanticToolsDebugging production from your editor with the Logfire MCP server The bug report says checkout is failing. Cursor is open on the file you suspect, and Pydantic Logfire is open in another window on the trace that proves you suspect the wrong file.
PydanticToolsRunning Pydantic AI agents on Jev, and seeing what they decided A lot of the agents I see in production don't write anything. They read a support ticket and decide who owns it. They look at a shell command and decide whether it's safe to run.
PydanticToolsJev is now available in Pydantic AI Gateway You can now call Jev , TypeSafe's classification model, through Pydantic AI Gateway . Your application keeps one gateway key, and Jev requests show up next to your language models in the same spend…
PydanticToolsHigh-volume AI scoring with Jev and Pydantic Evals An evaluator often needs to return a category, a yes/no judgment, or a position on a rubric. Writing an explanation can be useful, but you don't always need one for every production response.
PydanticToolsLogfire dashboards: more beautiful, more usable We've given Pydantic Logfire dashboards a lot of polish over the past few weeks. I want to highlight some of the improvements we've made in their look and feel, share some of my design thinking, and…
PydanticToolsGenerate images with Pydantic AI The news upfront: you can now use dedicated image-generation models through Pydantic AI! Previously, our image-generation support went through conversational models with image-generation abilities .
PydanticToolsDurable execution in Pydantic AI agents with AWS Lambda Durability Picture this: an AI support agent spends fifteen minutes working on a ticket. It reads the order, calls the billing API, asks the model what to do next, calls another tool, and somewhere in the…
PydanticToolsLinguistic drift at the frontier I've noticed some strange behavior coming out of the top frontier models lately. Models are getting better and better at coding, design, problem solving, and more.
PydanticToolsYou.com is now a Pydantic AI capability Pydantic AI Harness now has two new web search capabilities from You.com , YouSearch and YouResearch .
PydanticToolsThe best Langfuse alternatives in 2026, honestly compared An agent gives a wrong answer at 2am. The Langfuse trace is right there: prompt, model call, tool call, tokens, cost. Nothing in it looks broken.
PydanticToolsThe 7 best LLM evaluation tools in 2026 By Bill Easton. Evaluation workflows updated September 12, 2026; pricing and licenses checked August 26, 2026. Picking a metric is the easy part of evaluating an LLM application.
PydanticToolsThe best OpenTelemetry backends in 2026, honestly compared The whole point of OpenTelemetry is that this decision is reversible. Instrument once with the open standard, and the backend (the thing that stores your traces, logs, and metrics and answers…
PydanticToolsThe best prompt management tools in 2026 The prompt that shipped is often not the prompt in the repository. Someone patched it during an incident, someone else edited a copy in a vendor console, and the git history that was supposed to be…
PydanticToolsYour Pydantic AI agents just gained a voice A Pydantic AI agent is a plain Python object with no interface baked in. The same agent already runs as an object you call run() on , in the terminal , behind a built-in web chat , and streamed to…
PydanticToolsThe best Sentry alternatives in 2026, honestly compared The bill is usually what starts the search. An error storm burns through the month's quota in an afternoon, the pay-as-you-go budget follows it, and then Sentry does what its own documentation says…
PydanticToolsFeature flags for production AI AI makes software accessible to more people. One agent may serve an AI-native specialist and a first-time user who expects an ordinary request to work.
Nothing matches this filter yet.