Overview
What this challenge is about.
Build the v0 agent: given a company URL, it gathers 5 fact bullets (recent news, headcount range, tech stack hints, hiring patterns, a recent leadership change) and drafts a 4-line cold-outreach email in a specified voice. Use a single LLM with web search + scraping tools. Then write a 5-page 90-day plan covering: how to log outcomes (replies/no-replies), which prompts/strategies to A/B test, what a 'learning loop' actually looks like for this product, and what NOT to automate yet (founders are skeptical of full autonomy).
The Brief
What you'll do, and what you'll demonstrate.
Build a v0 sales-research agent and write the 90-day plan to make it self-improving in production.
Earning criteria — what you'll demonstrate
- Build a useful tool-using LLM agent end-to-end in a week
- Design a learning-loop plan for an LLM-powered product
- Reason about which parts of an agent product should NOT be automated
- Translate an agent prototype into a design-partner pitch
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
AI Engineer
Shipping the v0 agent in a week and documenting the learning loop is the AI-engineer half of an early-stage agent product.
This challenge sharpens
- llm-agents
- agent-design
- evaluation