<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>PYX Labs Blog</title><description>Research, findings, and field notes on evaluating and improving AI for workplace use.</description><link>https://www.pyxlabs.ai/</link><language>en-us</language><item><title>AI Can Summarize Employee Feedback. A New Benchmark Shows It Doesn&apos;t Always Understand It.</title><link>https://www.pyxlabs.ai/blog/new-benchmark-shows-ai-doesnt-always-understand-employee-feedback/</link><guid isPermaLink="true">https://www.pyxlabs.ai/blog/new-benchmark-shows-ai-doesnt-always-understand-employee-feedback/</guid><description>PYX-Voice, the industry&apos;s first benchmark for how AI understands employee feedback, finds it often misses the meaning behind complex workplace experiences.</description><pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Introducing PYX Labs: How Good Is AI, Really, at Understanding People at Work?</title><link>https://www.pyxlabs.ai/blog/introducing-pyx-labs/</link><guid isPermaLink="true">https://www.pyxlabs.ai/blog/introducing-pyx-labs/</guid><description>AI already shapes how organizations read employee feedback. PYX-Voice, our first benchmark, found frontier models far stronger on numbers than interpretation.</description><pubDate>Thu, 09 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>