Format: no restrictions

Build a working proof-of-concept for the Agentic Travel Recommendations API

• Include at least one MCP server endpoint that an AI agent could discover and invoke (e.g., get_recommendations, get_member_profile)
• Implement partner-specific rule enforcement — the service must respect partner configuration (recommendation caps, category exclusions)
• Use any language and framework from arrivia's stack: TypeScript/JavaScript, Python, or C#/.NET
• Include both a backend API and a minimal frontend or CLI that demonstrates the recommendation flow end-to-end
• Mock the upstream services (member data, partner config) — we are evaluating your service design, not your ability to integrate with real APIs

Format: .pdf, .doc, .docx, .rtf, .txt, .md

Section A — Architecture & Trade-offs (300–500 words)

Architecture Overview

Explain your architecture: how the recommendation service, MCP server, member data, and partner config interact.

Design Trade-offs

Name at least two design trade-offs you made and explain why you chose this approach over alternatives.

Handling Partner Configuration Changes

Describe how your service handles a partner that suddenly changes their recommendation cap or adds a new category exclusion — what would need to change?

Section B — Production Readiness & Incident Response

Incident Runbook Entry

Write a brief incident runbook entry: a member reports that the AI Concierge is showing cruise recommendations even though their partner's configuration excludes cruises. Walk through how you would diagnose, confirm, and resolve this in production.

Part B2 — Required Reasoning Question (answer without AI assistance)

Describe a scenario where an AI coding assistant would give you a plausible but incorrect answer for this type of problem — building an API that enforces partner-specific business rules. Explain specifically how you would catch the error and what you would check before acting on it.

Section C — AI Usage Log (Mandatory)

This is not a trick. We want to see how you work with AI — not whether you used it.

In a short section of your README, document your AI collaboration process. For each significant interaction with an AI tool, briefly note:

• What you asked the AI to help with
• What it gave you
• What you kept, changed, or rejected — and why

Three interactions documented is sufficient. The log does not need to be exhaustive.

Format: .mp4, .mov, .webm

• Senior / Level III: 8–10 minutes | Level I / II: 5–7 minutes
• Record your walkthrough as an MP4 or MOV file and upload it directly on the Provn platform as a separate file.

Structure your video as follows:

• Summary (60 seconds): The problem, your approach, and your recommended architecture.
• Code walkthrough (2–4 minutes): Walk through your implementation — explain your MCP server design, how partner rules are enforced, and one design decision you are most proud of.
• What would you do differently? (1–2 minutes): If you had another hour, what would you change? What would you validate before shipping this to production?
• Mandatory AI question: Walk me through one moment where you disagreed with, pushed back on, or redirected what the AI gave you — and what you did instead. Name the specific moment. Explain what the AI produced that did not meet the bar, what you did differently, and why.