AI agent observability requires capturing five signals — the agentic loop as spans, one correlated full-stack trace, per-step cost and latency, session correlation across multi-agent handoffs, and Ope…
Pydantic released a hosted Logfire MCP server that exposes OpenTelemetry traces, logs, and metrics to any Model Context Protocol client, running at https://logfire-us.pydantic.dev/mcp for US projects …
Pydantic AI 2.50.0 adds support for running agents on Jev, the typed-decision model from TypeSafe, via a new TypeSafeModel adapter and a DecisionModel base class, with a decide span added under the ch…
Pydantic AI Gateway now supports Jev, TypeSafe's classification model, letting applications call Jev through a single gateway key alongside their language models. Jev takes text plus typed questions a…
TypeSafe's Jev, paired with Pydantic AI 2.46.0 and Pydantic Evals, scores one million evaluations with three results each for $42 in Jev inference and $20 in Logfire telemetry, according to Pydantic's…
Pydantic AI released a dedicated ImageGenerator API that lets developers generate images directly without running an agent, supporting OpenAI GPT Image, Google Gemini via both the Gemini Developer API…
Pydantic has open-sourced Monty, a minimal, secure Python interpreter written in Rust for running code written by AI agents, with the goal of letting LLMs write Python instead of making sequential too…
Pydantic AI Harness now ships AWSLambdaDurability, a capability that checkpoints every model request, function tool call, MCP call, and dynamic-toolset resolution as an AWS Lambda durable functions st…
Anthropic's Claude models have adopted the archaic term 'seam' to describe software connection points, and the usage has proliferated across codebases and other AI models, according to a developer's a…
Pydantic AI Harness now integrates You.com's YouSearch and YouResearch web search capabilities, providing real-time LLM-ready access and deep research for agentic workflows. You.com reports 93.48% on …
A comparison of Langfuse alternatives in 2026 finds that teams leave Langfuse due to its billing model, lack of log and metric ingestion, enterprise-only governance features, and its acquisition by Cl…
Pydantic AI has launched realtime voice support for its AI agents, enabling live speech-to-speech conversations through a provider-agnostic API that works with OpenAI Realtime, Azure OpenAI, Gemini Li…
Pydantic Logfire, from the team behind Pydantic, is named the best OpenTelemetry backend in 2026 in a comparison that evaluates cross-signal querying, high-cardinality tolerance, and GenAI awareness. …
Pydantic Logfire is the top pick among seven LLM evaluation tools compared in a guide updated August 26, 2026, which also covers Braintrust, Langfuse, LangSmith, Arize Phoenix, Confident AI, and Galil…
Pydantic Logfire managed variables give AI engineers a control plane for changing models, prompts, and tools in production without redeploying, enabling feature flags that are typed, versioned, and ta…
Crusoe is now a native model provider in Pydantic AI, enabling developers to run agents on Crusoe Managed Inference with a single string like 'crusoe:zai/GLM-5.2'. The integration, contributed upstrea…
StackOne, the integration gateway for AI agents, is now a capability in Pydantic AI Harness, allowing agents to access actions on linked accounts such as Workday, BambooHR, Salesforce, and Zendesk wit…
Snowflake and Pydantic AI have launched a native integration, adding SnowflakeModel and SnowflakeProvider to Pydantic AI, enabling governed AI agents to run on Snowflake data via the Snowflake Cortex …
Airbnb published a playbook for evaluating generative AI at scale, recommending teams read roughly 100 outputs and traces before building evaluators, then layer programmatic checks, LLM judges, and hu…
Logfire, a full observability suite from Pydantic, announced it charges $0 per thousand AI evaluation scores, attaching each gen_ai.evaluation.result as an OpenTelemetry event billed at the standard t…