HelloPM · AI Builder Series Explore builds →
Quest 4 · Weekly funded-companies agent

Weekly funded-companies agent

AI agentsWeb scrapingAutomationLinkedIn post

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.

Screenshot of Shaswat Koul's Weekly funded-companies agent submission
Weekly funded-companies agent — Quest 4, built by Shaswat Koul

What Shaswat shipped

FundPulse is a PM job-search copilot built around funded startups, designed to surface companies that raised funding in the last seven days and research each one. For every match, it generates an OKR-based six-month plan, a drafted cold email, and a proof-of-work export tied to the company's real problems — built on the idea that standing out in a PM job search means showing up with a plan, not just another application.

View the LinkedIn post ↗ Shaswat's full portfolio

Our read on this build

Shaswat shipped a LinkedIn post. This read comes from the artifact and Shaswat's own account of it — no scores, just what the build does and does not show.

What it demonstrates

  • Fresh input is part of the machine: live search.
  • It goes past listing companies into proposing a way in — drafted emails and an application path.
  • Worth noting: research sits in front of the outreach, which is the difference between a targeted note and a mass send.

What is not shown

  • No schedule or trigger is described, so it reads as a tool you remember to open rather than an agent that shows up on Monday.

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.


Why this quest matters

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.

What separated the strongest builds

Across the 29 builds we could open for this quest, the same three or four things kept deciding whether one landed. Useful whether you are judging this one or attempting your own.

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.

More from Shaswat

Quest 1Quest 2Quest 3Quest 4Quest 5Quest 6Quest 7
← Back to Shaswat's portfolio