<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Anthropic on Kuldeep Pisda</title><link>https://kdpisda.in/tag/anthropic/</link><description>Recent content in Anthropic on Kuldeep Pisda</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 26 Aug 2026 09:00:00 +0530</lastBuildDate><atom:link href="https://kdpisda.in/tag/anthropic/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude's Memory Now Follows You From Chat Into Cowork, and You Can Audit Every Topic It Kept</title><link>https://kdpisda.in/claude-unified-memory-cowork-chat-topics/</link><pubDate>Wed, 26 Aug 2026 09:00:00 +0530</pubDate><guid>https://kdpisda.in/claude-unified-memory-cowork-chat-topics/</guid><description>&lt;p&gt;Yesterday Anthropic shipped a change that sounds small in a changelog and is not small in practice: Claude&amp;rsquo;s memory now works the same way whether you are typing in chat or handing a task to Cowork, its agent that runs multistep jobs in the cloud. Tell Claude in chat that your manager hates bullet points that start with a &amp;ldquo;loud&amp;rdquo; verb, and the next time Cowork drafts a report for that manager, it already knows. Explain once how your team defines a metric, and every slide deck Cowork builds from then on uses that definition without you repeating yourself.&lt;/p&gt;</description></item></channel></rss>