<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI agents for travel agencies · Agentic Feats</title><description>Real examples of AI agents in travel agencies.</description><link>https://agenticfeats.com/</link><language>en</language><item><title>Travel agent that learns from trips</title><link>https://agenticfeats.com/c/travel-agent-that-learns-from-trips-hermes-agent/</link><guid isPermaLink="true">https://agenticfeats.com/c/travel-agent-that-learns-from-trips-hermes-agent/</guid><description>Hermes Agent plans trips using stored traveler preferences, researches flights and hotels by web search, and rewrites its own memory after a post-trip debrief. Result: After a debrief on a 6-hour layover, the agent added a 3-hour layover cap and applied it unprompted when re-planning the next trip. Evidence: Shown. Source: https://dev.to/christopher_mburu_7b7e0ba/hermes-travelops-an-agent-that-learns-from-every-trip-5805</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>Hermes Agent</category><category>Personal and Family</category></item><item><title>Client notes to Belmond shortlist</title><link>https://agenticfeats.com/c/client-notes-to-belmond-shortlist-codex/</link><guid isPermaLink="true">https://agenticfeats.com/c/client-notes-to-belmond-shortlist-codex/</guid><description>Codex Desktop read a client notes Word doc, checked Belmond&apos;s live booking site, and built a three-option comparison matching the client&apos;s past trip preferences. Result: Codex returned a ranked comparison of three Belmond properties with availability and nightly rate ranges for a sample window, plus a more detailed Word doc. Evidence: Numbers. Source: https://worldviatravelnetwork.com/blog/ai-tip-use-codex-desktop-to-connect-your-files-chatgpt-and-the-web</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>Codex</category><category>Research</category></item></channel></rss>