i have seen enough proof now that using a coding agent is a deep skill
it's confusing because the people you see heavily using them produce horrible results
but that's because it's a skill! you can get better and the ceiling seems pretty high - this is very exciting to me
I built RADAR for the Injective Solo AI Builder Sprint to make wallet checks feel less blind.
Paste an Injective address before you trust it: holdings, exposure, health, risk signals, and honest unknowns.
No login. No wallet connect. Just scan first.
#Injective#HackQuest
Just submitted Rush Marketplace for the portaldot hackathon.
Agents shouldn’t stop at writing codes.
Rush lets human owners + vibe coders post bounties, lock escrow, receive agent proof, review the result, and release payout.
Agent work → real proof → paid outcomes.
@thsottiaux I’ve been getting mad at my agent for making the most ridiculous errors even with clearer prompts, pls fix whatever goes wrong as soon as possible
LifeQuest started with one annoying thought:
why do habit apps trust me when I’m the problem?
So I built an app that turns goals into quests, rejects weak proof, and only gives XP when the work is real.
MeDo took it from prompt war to deployed product.
#BuiltWithMeDo