ZizkaDB, an open-source operational database for LLM agents, introduces causal lineage and session replay features to address behavioral debugging gaps in traditional tracing tools. The database store…
A developer's blog post argues that production-grade agentic AI systems depend on 'boring engineering' practices rather than flashy model capabilities. The post emphasizes tracing, testing, resumable …
A developer's guide argues that OpenTelemetry alone is insufficient for AI observability due to the stochastic nature of LLMs and the need for semantic understanding. The article recommends a hybrid p…
AgentCheck, a new open-source regression testing tool for AI agents, lets developers define expected agent behavior in YAML and run pass/fail checks against any CLI command or HTTP endpoint, with an L…
Promptfoo is recommended as the primary evaluation tool for AI agents focused on documentation and RAG tasks, with Ragas and LangSmith suggested for deeper analysis. The guidance from Promptfoo, Huggi…
European regulators have made incomplete deletion in AI agent stacks an enforceable liability, with the European Data Protection Board's February 2026 coordinated enforcement action across 32 supervis…
Langfuse v4 introduces an observations-first model for tracing agentic AI systems, treating LLM calls, tool executions, and agent steps as first-class queryable objects grouped by a shared trace_id, w…
Langfuse v4 is live on Langfuse Cloud and generally available for self-hosted deployments, rebuilding traces and evaluations on one immutable ClickHouse table to cut initial table loads from seconds t…
Lakshman Pandey has shipped a production retrieval-augmented generation (RAG) system for UK arts and culture clients that implements NIST AI Risk Management Framework controls. The system uses Claude …
Developer Ashwin Ugale released tracelint, an open-source linter that detects structural defects in AI agent execution traces without using an LLM. The tool reads telemetry from OpenInference, Arize P…
Anthropic shut down the legacy Claude Workbench and three experimental API endpoints on August 17, 2026, breaking applications that used them and deleting unexported prompts. The retired endpoints—/v1…
Langfuse 4.14.4 and OpenTelemetry can be used to trace a two-agent Claude pipeline, capturing every LLM call, tool invocation, token count, and dollar cost in a single nested trace timeline. The tutor…
A developer investigating discrepancies between tracked LLM spend and provider invoices found that the two numbers almost never match, with causes documented in the tools' own docs. OpenAI and Anthrop…
A developer detailed how Langfuse provides the trace/span/generation hierarchy needed to debug multi-step agentic LLM workflows, contrasting it with observability tools that only capture top-level cal…
TokenOps, an open-source system from The Agent Plane, provides real-time, run-scoped cost control for AI agents, addressing the problem of runaway token spend across multi-call runs. Unlike traditiona…
A 32-attempt Claude Code evaluation on August 11, 2026, found that Langfuse was selected in every tracing and production-monitoring task but in none of the prompt comparison and release-gate tasks. Ho…
A developer surveyed the metric catalogs of five widely-used LLM evaluation tools—Arize Phoenix, DeepEval, Future AGI, Langfuse, and Ragas—and found that the built-in metrics are converging into a com…
A developer's analysis of LLM evaluation monitoring reveals that alert thresholds on eval scores are hypothesis tests whose false-alarm rates are often ignored. With 150 judge scores per hour and a 92…
An engineer's analysis reveals that AI agents often fail in production due to compound error rates, with an 8-step agent at 85% per-step reliability yielding only a 27% end-to-end success rate. Citing…
The LLM observability platform market is projected to grow from $1.97 billion in 2025 to $2.69 billion in 2026 and reach $9.26 billion by 2030 at a 36.2% CAGR, according to The Business Research Compa…