Honeycomb published a complete, annotated OpenTelemetry Collector configuration for LLM observability that receives traces over OTLP, normalizes OpenInference and OpenLLMetry schemas onto GenAI semant…
Honeycomb Private Cloud's Tenant team built an automated drift report, refactored its own configuration to make diffing possible, and added an AI triage skill to track configuration changes across the…
Honeycomb announced early access to AI Ecosystem, an AI agent fleet-level analysis layer built on its context-rich data model that covers AI Agent Fleet Performance, LLM Cost Tracking, and Agent Conve…
Honeycomb launched Canvas Connectors in general availability, offering 12 connectors including GitHub, PagerDuty, Jira and Amplitude that let the Canvas AI agent read from and act in systems outside H…
Microsoft Foundry's agent observability stack captures agent execution as OpenTelemetry traces, using GenAI semantic conventions such as gen_ai.request.model, gen_ai.usage.input_tokens, and gen_ai.too…
Honeycomb contributed its adaptive_tail_sampling processor to the OpenTelemetry Collector, re-expressing the adaptive sampling algorithms behind Refinery and dynsampler-go in OpenTelemetry-native term…
Honeycomb announced that Canvas, its AI-guided observability workspace for building AI agents, is now Generally Available for all Honeycomb users, with connectors including GitHub and Linear currently…
Honeycomb's Nick Travaglini argues that the traditional three pillars of observability—metrics, logs, and traces—drive up AI observability costs, and recommends wide events as a single format to keep …
Honeycomb's SVP of Engineering, Emily Nakashima, issued a note to the engineering org explaining the company's all-in AI adoption, one year after founders mandated a 2x productivity goal with AI. The …
Fin (formerly Intercom) CTO Darragh Curran nearly tripled engineering productivity after setting a public goal to double it, driven by AI-generated code, an AI-driven PR review system, and observabili…
A new guide from Honeycomb compares seven Datadog alternatives for AI and agent observability, highlighting cost predictability, investigation complexity, and OpenTelemetry portability as key factors.…
GitHub reports that commits have doubled, Honeycomb's PR rate has roughly doubled, and Anthropic cites a 67% increase in code production, but production incidents are also rising as existing Developer…
Honeycomb CEO Charity Majors reflects on the first year since the company issued its AI mandate, reporting that teams with strong learning culture improved while those shipping slop scaled their outpu…
Ileanell Perez, an engineering manager at Honeycomb, responded to the company's push for AI tool adoption by creating dedicated time for connection, collaboration, and discussion rather than writing a…
AI Flight Recorder, an open-source developer tool for recording, replaying, and inspecting AI application sessions, has been released on GitHub. The tool captures prompts, streamed tokens, tool calls,…
Charity Majors, CTO and cofounder of Honeycomb, said in a podcast episode that skepticism about AI in software development is no longer rational in 2026, comparing AI's industry impact to that of clou…
Charity Majors, co-founder and CTO of Honeycomb, said AI is forcing engineering teams to adopt better instrumentation and observability practices, with traces becoming the source of truth and a produc…
Honeycomb announced the general availability of AI BubbleUp, an AI-powered feature that summarizes significant correlations in BubbleUp results, available to all customers who have enabled Honeycomb I…
Trail, a new Python SDK, captures AI agent activity as signed OpenTelemetry spans, adding agent-aware tool taxonomy, MCP injection flagging, and skill hashing to detect silent substitution, while expo…
Grafana Labs has expanded Grafana Assistant to query and correlate data across more than 30 data sources through natural language, aiming to unify observability for operators, developers, and SREs. Th…