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.

Growth.StartupRadar is built around the two-week hiring-lag window that opens after a company announces new funding. A live ticker on the landing page tracks named recent raises — from BRYM's €650K pre-seed to Quantum Systems' $1.2B Series C+ — and the product walks users through a four-step flow: upload a resume, match against this week's funded companies, generate an application kit, and send outreach. The framing centers on turning "this Monday's shortlist" into a tailored, resume-matched message for each company.
Pranav shipped a deployed web app you can open. This read comes from the artifact and Pranav's own account of it — no scores, just what the build does and does not show.
What it demonstrates
What is not shown
Take this awayA solid research surface. Adding the schedule is usually a day of work, and it is what turns a thing you visit into a thing that arrives.
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.