PostHog found that over 90 days only 64 users ever started a shared context file for its PostHog Desktop Spaces and only 14 ever edited it, prompting the company to build an AI-powered context layer t…
Feature flag providers are warning engineering teams that the real cost of building an in-house feature flag service lies in integrations and reliability, not the core key-value function. The company …
PostHog moved from roughly 20% of its monorepo pull requests being opened by AI agents to 70% over the last four months, according to a PostHog blog post, a shift the company says breaks the definitio…
Session Replay provider Replay Vision built a rasterizer to convert rrweb session data into MP4 videos so multimodal AI models like Gemini can analyze user recordings, addressing the problem that mode…
PostHog's context warehouse is named the best data warehouse for developers in a comparison that also evaluates MotherDuck, ClickHouse, Databricks, Snowflake, and BigQuery. The article highlights Post…
PostHog reports that AI coding agents are now performing worse with excessive context, prompting Anthropic to remove 80% of Claude Code's system prompt and Boris Cherny, creator of Claude Code, to rec…
PostHog is named the best overall LLM evaluation tool for production, according to a new guide, because it ties eval scores to user sessions, traces, and feature flags, while Braintrust is highlighted…
PostHog has launched PostHog Desktop, an open-beta product built around multiplayer spaces and generative UI artifacts, as part of its effort to disrupt itself and find product-market fit again. The c…
PostHog product marketer Andy Vandervell reports that AI product development is stalling because AI ambition is outrunning data readiness, trust, and governance, citing that 56% of teams name data qua…
PostHog has built a semantic layer into its context warehouse to ensure AI agents and humans define metrics like MRR consistently, after tests showed that Claude, Cursor, and PostHog AI returned three…
PostHog's engineering team reports that optimizing token spend, or 'tokenminning,' can significantly reduce LLM costs, citing an example where a product's daily LLM costs doubled from $5,000 to $10,00…
PostHog's Andy Vandervell argues that AI agents are not killing user interfaces but adding a new layer, citing that every product now has both human and agent users. He advises builders to design dual…
PostHog has published 226 skills to its internal skill store and maintains 187 SKILL.md files across 28 products, using them to improve both PostHog and individual workflows. The company emphasizes pr…
PostHog launched Replay Vision, an AI layer for session recordings that detects user struggles and automatically drafts fixes as pull requests, with two internal cases solved in a week. The tool ident…
PostHog has accelerated its shipping cadence from 1,441 PRs in January to 4,725 PRs in June, with only a 10% increase in engineering headcount, driven by widespread use of AI agents and internal tooli…
PostHog introduces the concept of a context warehouse, a unified tool that ingests, models, stores, and queries product and business data for AI agents, eliminating the need for separate ETL pipelines…
By 2030, AI agents will be the primary users of software, according to PostHog, which is building '2030-shaped software' with an agent-first approach. The company argues that human work will shift to …
PostHog engineers share four workflow changes to stop being a code review bottleneck when using AI-generated code, including having multiple agents review each other's code and triaging results to esc…
PostHog's Replay Vision AI layer automatically reads session replays, detects user struggles, and opens pull requests to fix bugs. In one case, the system identified a rage-clicking issue, diagnosed t…
PostHog, Langfuse, and seven other AI observability tools are compared for developers building LLM-powered applications. These tools provide tracing, cost tracking, evaluations, and prompt management …