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.

PM Radar.ai reframes the funded-companies job hunt from "more listings" to "better bets," using a weighted scoring model across signal layers such as hiring activity (25%), business strength (20%), and funding (15%). It draws on named sources including Inc42, YourStory, Entrackr, VCCircle, and StartupNews.fyi, and describes a profile-match layer that generates strategy notes, outreach templates, and a verdict for each company — illustrated on the public page with a sample card for Ikin Global.
Saket shipped a deployed web app you can open. This read comes from the artifact and Saket'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 awayWhat makes this an agent rather than a search box is that it decides something — which companies matter to you, and what to say to them — before you get involved.
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.