What is a context warehouse?
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…
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 …
A developer built an AI alt text generator for WordPress to automate the creation of descriptive alt text for images, aiming to improve accessibility and SEO. The project evolved into a full-stack sys…
A developer's deterministic code analyzer, DACIP, found three real bugs across nine unfamiliar codebases after fixing 19 false-positive gap classes. The tool extracts backend routes and frontend calls…
Depot uses PostHog's AI observability tools to monitor and maintain its AI assistant Sherlock, which helps customers analyze builds and jobs. Sherlock usage from the dashboard grew to 5x the volume of…
A security researcher using Hacktron's pentest tool discovered that PostHog launched Playwright Chromium with `--no-sandbox` for heatmap screenshots, then used Anthropic's Claude to write an exploit f…
Developer CyrusNuevoDia released Capn-hook, an open-source tool that gives coding agents persistent memory by saving file locations for previously answered questions and automatically deleting stale a…
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…
A developer ran a probe asking four AI models (ChatGPT, Claude, Perplexity, Gemini) to recommend tools in three SaaS categories—product analytics, feature flags, and error monitoring—20 times each. Th…
Tech workers are splitting into two camps: those amplified by AI and those shaken by it, according to a 2026 survey. Burnout surged 11 points to 55.7%, career optimism fell to 48.7%, and 53% would not…
A developer forked the open-source Meetily v0.4.0 codebase into a new project called LibreMeet, rebranding 73 files and removing 928 lines of PostHog analytics infrastructure to create a privacy-first…
Loop Engineering, a 2026 AI workflow pattern where developers build systems that prompt agents instead of doing it manually, has a dirty secret: without a proper evaluation component, the loop becomes…
A new tool called Codex connects PostHog analytics to external market events, allowing users to overlay AI-identified news markers on traffic charts to correlate growth with real-world occurrences.…
Weave released a smart model routing proxy that works with Claude, Codex, and Cursor, ranking #1 on the RouterArena leaderboard. The open-source tool uses an on-box embedder to select the best model p…
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 …
PostHog engineer Robbie Coomber rebuilt the company's SQL parser using AI agents, replacing an ANTLR-generated parser with a hand-rolled recursive-descent parser that runs 70 times faster. The project…
PostHog built an AI onboarding wizard that uses context engineering to complete two hours of integration work in eight minutes, achieving a 5x increase in conversion and 2x increase in activation. The…
PostHog engineer rewrote the company's SQL parser using AI agents, achieving a 70x speedup with 16K lines of hand-rolled parser code. The new parser replaces an ANTLR-generated parser and is equivalen…
AI has made building software faster, but the bottleneck has shifted from delivery to decision-making. Teams must now focus on understanding problems and running experiments rather than just shipping …