The assignment
Build a weekly agent that scrapes last week's funded startups from the web and proposes your way in — a tailored application path.

A weekly funding-intelligence pipeline built around a real engineering stack — Crunchbase, TechCrunch, and Y Combinator for sourcing, Serper and OpenAI for extraction, and Resend for a Thursday email digest. The build targets product operations, implementation, and digital transformation roles, surfacing a relevance score, sector match, and recommended job titles per company, with one concrete action — apply or network — suggested for each. The author's LinkedIn post walks through the engineering path from source validation and date handling to scoring logic and deployment.
Ritu shipped a deployed web app you can open. This read comes from the artifact and Ritu's own account of it — no scores, just what the build does and does not show.
What it demonstrates
Take this awayThe transferable pattern is a three-stage pipeline — fresh signal in, judgment in the middle, a draft out. That is most useful agents, whatever the domain.
Agents earn their keep when they run without you. The bar isn't 'can AI write an outreach note' — it's 'does fresh data flow in on a schedule and come out tailored,' which is the real shape of an autonomous workflow.
Real companies, funded recently
Data pulled from a live source. A hardcoded list of startups everyone already knows about is a demo of a UI, not of an agent.
An application path that changes per company
The specific round, the sector, the role that funding implies. One paragraph with the company name swapped in is the failure mode here.
It runs without you
A schedule, a cron, a workflow trigger — something that makes 'weekly' true rather than aspirational.
Outreach you would actually send
Notes with judgment behind them. Volume is the easy part and the part that gets people ignored.
No numeric scores are published here. These pages are written reads of what each builder shipped — the build is the point, not a mark out of a hundred.