A developer has released Shipping Floor, an open-source example repo that demonstrates an agentic software factory capable of automatically rolling back a bad change without human intervention. The pr…
Spotify's experimentation team argues that Bayesian A/B testing is not a single method but a family of configurations with different guarantees, and that default flat-prior Bayesian approaches can rep…
Glean Technologies Inc. unveiled Glean Tau, a desktop workspace connecting enterprise AI to local files, applications, and code, at its Glean:GO 2026 conference in San Francisco, claiming a 5.2-times …
PostHog, the open-source analytics platform, has rebranded itself as 'the platform for building self-driving products,' shifting its focus to AI agents that diagnose and fix issues autonomously. The c…
GitHub introduced four agent apps—Amplitude, Endor Labs, LaunchDarkly, and PagerDuty—that integrate software delivery workflows directly into GitHub, enabling developers to scope, secure, roll out, an…
LaunchDarkly is now available on the Vercel Marketplace, enabling developers to integrate feature flags with minimal setup. Users can sync flags into Global Config, target releases, run experiments, a…
LaunchDarkly's agent optimization feature was used to automatically tune an AI email-drafting agent to sound human, judged by the AI detector GPTZero. The developer built a workflow where Claude draft…
Cloudflare launched Flagship, a feature flag service for Workers and AI agents that eliminates network round trips by evaluating flags in Workers KV at zero additional latency. On July 16, Cloudflare …
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…
A developer's research reveals that AI coding agents like Claude, ChatGPT, and Gemini exhibit bias and inconsistency when recommending software dependencies. The study, published at llmrank.fyi, shows…
A developer argues that hardcoding system prompts in production LLM applications is an anti-pattern that causes operational failures. The practice leads to prompt drift, slow iteration cycles, and cos…
A platform team at a tech company pushed a new prompt template version to production at 9:02 AM, but the evaluation harness continued grading against the old version for eight hours due to a caching i…