Releasesby IbisStop AI slop: Run evals with LLM-as-a-Judge
GA9 months agoUnverifiedAdded Sep 24, 2026
PostHog now provides automated evaluation tools that use LLMs to score generative AI outputs based on criteria like relevance and helpfulness. It includes pre-built templates for common use cases.
Topics: LLMs, Observability
More PostHog releases
Every PostHog releaseYour logs' final destination is in GA. You always end up here anyway
PostHog Logs is now generally available, providing a centralized destination for logs alongside errors, session replays, and product data.
Your product data just got a job: Workflows is now out
Workflows allows users to automate actions like sending emails or Slack alerts directly from PostHog event data. It eliminates the need for external syncing tools or custom API integrations.
PostHog × Vercel: feature flags, minus the plumbing
PostHog has released an integration with Vercel that syncs feature flags and experiments into Vercel's native Flags system, automating credential management.
Meet Logs (beta) – more debugging context, all in PostHog
PostHog has introduced a logs feature in beta, allowing developers to view backend logs directly alongside session replays and error tracking without switching platforms.
PostHog is now available in Vercel’s v0
PostHog has extended its Vercel integration to v0 via MCP. This allows v0 to generate code based on real product data, including experiment results and feature flag states.
How we built user behavior analysis with multi-modal LLMs (in 5 not-so-easy steps)
PostHog released Session Summaries in beta, a tool that uses multi-modal LLMs to analyze user session recordings and highlight issues automatically.
8 learnings from 1 year of agents – PostHog AI
PostHog AI is an integrated agent that can access product data, write SQL queries, manage feature flags, and perform multi-step analyses of product usage.
How we built automatic clustering for LLM traces
PostHog has introduced automatic clustering for LLM traces and generations. This feature helps AI product teams analyze usage patterns and identify outlier behaviors in their AI applications.
Also shipped on Jan 15, 2026
PostHog in January 2026Mobile Apps on Replit: Idea to App Store in Minutes
Replit has introduced Mobile Apps on Replit, a feature that allows users to build and publish mobile apps using natural language without native development experience.
Announcing New Models and Expanded Availability
Voyage AI introduced the Voyage 4 embedding model series with shared embedding spaces and the voyage-multimodal-3.5 model with video retrieval support. The models are now available on MongoDB Atlas and GCP.
The Voyage 4 model family: shared embedding space with MoE architecture
The Voyage 4 series features a shared embedding space for cross-model compatibility. The flagship voyage-4-large model uses a mixture-of-experts architecture to improve retrieval accuracy while reducing costs.
voyage-multimodal-3.5: a new multimodal retrieval frontier with video support
The voyage-multimodal-3.5 model adds support for embedding video frames alongside text and images. It also supports Matryoshka embeddings for flexible dimensionality.
WAF Release - 2026-01-15
This week's release focuses on improvements to existing detections to enhance coverage. Key Findings Existing rule enhancements have been deployed to improve detection resilience against SQL Injection.
Grafana Assistant in Slack enters Public Preview
Today Grafana Assistant in Slack enters Public Preview! Grafana Assistant is the premier AI feature in Grafana Cloud that lets you create dashboards, query data, analyze alerts, manage incidents, improve instrumentation and much more. With the Assistant, you can ramp up faster than ever.