What We Didn't Build

Last winter, someone close to me was running a senior-level job search. The kind where everyone in the room is qualified and the outcome turns on how well you show up, over and over, for months.

We went looking for tools. Everything we found was built for somebody else. Resume builders for first-time applicants. Trackers that recorded what you'd done without improving what you did next. Text generators with no sense of what makes a senior candidacy land.

So we built something. At first just a way to stay organized on a bad Tuesday. It worked better than we expected, and then it stopped being a personal workaround and started being a product.

That product is Exec Foundry, and it's live at execfoundry.com. Catalyst Forge operates it.

What it does

You paste a job posting URL. A few minutes later you have a tailored resume, a cover letter, and a sourced dossier on the company, all built from your real history instead of a template. Underneath sits a pipeline built for a search that runs six to twelve months, plus interview prep tied to the specific role. Three things, done properly, for people whose track record is already strong.

What we didn't build

There's an obvious feature we turned down: auto-apply. Point it at a job board, let it fire applications on your behalf, watch the number climb. Plenty of products in this category do exactly that. It demos beautifully, and it's the first thing people ask for.

We said no, and we're not planning to change our minds.

Volume destroys quality. The person on their fortieth application sends weaker material than they sent on their first, not through laziness but because nobody can hold that standard alone across months. A tool that helps you send more, faster, solves the wrong problem with more horsepower.

So the product carries the operational weight and hands the judgment back. You review the prep. You shape the narrative. You decide when it's ready. The AI absorbs the part that was breaking you and stops at the part that makes you worth hiring.

It took me a while to notice this is the same thing I tell consulting clients. The goal was never to hand your work to a machine. It's to stop losing your judgment to volume so you can spend it where it counts.

Three things shipping it taught me

Generic output is worth nothing. The difference between a free resume generator and something people pay for monthly is that ours starts from your actual history and your own way of describing what you did. Ungrounded AI produces confident, plausible, useless text. Every hour on grounding paid for itself. Every hour on clever prompting alone did not.

The unglamorous engineering is most of the job. Early on, a user's cover letter came out with their login handle where their name should have been. Small bug, ugly one, and exactly the kind of thing that never shows up in a demo. Fixing it properly meant reworking how identity flows through document generation. Most of the work looks like that. The model was never the hard part.

The distance between "the AI can do this" and "people can rely on this" is measured in months. Over two thousand commits in the last few months, and we're still going daily. If someone tells you their AI feature took a weekend, they built a demo.

Where it stands

Exec Foundry is live, it's paid, people are running searches on it, and we're still hardening it every week. There's a free trial with no card if you want to look around.

We didn't set out to build a product. We set out to solve one person's problem, and it turned out a lot of people had the same one.

The raw material was never the problem. The foundry was.