Franklin Hayes

A platform ( canivibecodeit) recently went viral on X for showing which paid tools you could realistically rebuild yourself.

Design tools, ChatGPT, or Claude are obviously hard to replace. But invoice tools, forms, simple CMSs, or dictation apps seem much more realistic.

Same effort every time, same comment, just a different thread each time. The spread came entirely from which thread I picked, not from anything I changed about what I wrote.

That has changed how I think about distribution. It stopped being a channel decision and became a research step before I write anything: how fresh the thread is, how many replies it already has, whether the person asking is actually going to read what comes back.

Curious to crowd-check something any researchers/analysts here who still have to loop in an external team (or a colleague) just to get basic data pulls, literature reviews, or first-pass analysis done? Not the deep, judgment-heavy stuff just the grunt work that eats days before the "real" research even starts.

If that's you what's the actual bottleneck?

• Is it that the tooling/agents just aren't there yet?

• Is it trust you don't believe the output without a human checking it?

• Or is it that setting up an agent/pipeline yourself takes longer than just asking a person?

Trying to figure out where an out-of-box research agent would genuinely save time vs. where people still want (and will keep wanting) a human in the loop.