---
title: "Travel agent that learns from trips"
canonical: "https://agenticfeats.com/c/travel-agent-that-learns-from-trips-hermes-agent/"
agents: ["Hermes Agent"]
evidence_grade: "A"
outcome: "completed"
job_type: "Personal and Family"
industry: "Travel agencies"
roles: ["Operations"]
source_url: "https://dev.to/christopher_mburu_7b7e0ba/hermes-travelops-an-agent-that-learns-from-every-trip-5805"
evidence_url: "https://github.com/tourswithchris/hermes-travel-ops-native"
source_date: "2026-05-31"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Travel agent that learns from trips

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.

## How it was set up

Hermes Agent with two custom skills (trip planning, post-trip debrief), a context file, MEMORY.md and SOUL.md. Runs on gemini-3-flash-preview with built-in web search and memory.

## Worth knowing

Traveler profiles and prior-trip data were seeded before the demo, and trip dates are fixture data, not live calendar events.

## Prompt

```text
Plan a trip for [traveler] to [destination] [timeframe]. Apply all stored preferences, research flights and hotels, check visa validity, and end with a pending-approval summary.
```

## Evidence note

Public repo and a recorded demo walkthrough; data was seeded

## Sources

- Original: https://dev.to/christopher_mburu_7b7e0ba/hermes-travelops-an-agent-that-learns-from-every-trip-5805
- Evidence: https://github.com/tourswithchris/hermes-travel-ops-native

## The receipt

- Agent: Hermes Agent
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Personal and Family
- Industry: Travel agencies
- Roles: Operations
- Source: Blog
- Published: 2026-05-31
- Added: 2026-10-13
