instalilyAI·AI Engineer·Take-home Assignment·Intermediate

IntermediatePrefer not to say

Jun 2026

Summary

instalilyAI gave me a 48-hour take-home for an AI Engineer role and it was a lot more involved than I expected. You're basically building a full product from scratch: scraper, backend, agent, frontend, all wired together and working end-to-end.

Questions Asked (1)

Build a complete AI agent chat application within 48 hours. This includes writing a custom web scraper to pull product data from an e-commerce site, building a backend and frontend, and wiring an AI agent that can answer user queries grounded in the scraped data.

System DesignAPI & IntegrationsTechnical Trade-offs

Author's notes

The scope of this thing did not fully register until I was about six hours in and realized the scraper alone was going to eat most of my time.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying requirements and constraints, then propose a phased plan that prioritizes a working end-to-end MVP within 48 hours. Focus on pragmatic trade-offs, such as using existing libraries for scraping and AI orchestration, and defer non-essential features. Emphasize risk mitigation and clear communication of assumptions.

Pro tip: Demonstrate awareness of legal and ethical scraping boundaries (e.g., robots.txt, rate limiting) and propose a fallback to mock data if scraping is blocked. Also, highlight the importance of observability and error handling in a time-constrained build.

1. Clarify Requirements and Constraints

Ask questions to understand the e-commerce site, expected query types, user load, and deployment environment. Confirm the 48-hour deadline and what 'complete' means (e.g., MVP vs. production-ready).

2. Design the Architecture

Outline a simple architecture: scraper -> data store -> backend API -> frontend -> AI agent. Choose technologies that enable rapid development (e.g., Python with BeautifulSoup/Scrapy, FastAPI, React, LangChain).

3. Prioritize and Sequence Tasks

Break down work into must-have vs. nice-to-have. Sequence: scraping and data storage first, then backend API, then AI integration, then frontend. Allocate time for testing and integration.

4. Address Key Trade-offs and Risks

Discuss trade-offs like scraping robustness vs. speed, AI model choice (cost vs. accuracy), and frontend complexity. Identify risks (e.g., site blocking, API limits) and mitigation strategies.

5. Define Success Metrics and Next Steps

Specify how you'll measure success (e.g., end-to-end query answering, latency, accuracy). Mention post-MVP improvements like caching, scaling, and monitoring.

Key Points to Mention

Scraping ethics and legality: respecting robots.txt, rate limiting, and user-agent headers
Data pipeline: cleaning, storing, and indexing scraped data for efficient retrieval
AI agent grounding: using RAG (Retrieval-Augmented Generation) with vector search or keyword search
Technology choices: frameworks and libraries that accelerate development (e.g., LangChain, FastAPI, React)
Trade-offs: build vs. buy, model selection (open-source vs. API), and complexity vs. speed
Testing and observability: logging, error handling, and simple monitoring to ensure reliability

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.