This is a submission for Weekend Challenge: Generosity Edition.
What I Built
When I was younger, my family went through times when we needed help from local charities, food pantries, clothing programs, and things like that. I do not need to get into all the details, but I remember being surprised by how generous people could be when we really needed it.
That stuck with me, and it is a big part of why I made Sprinkle.
A lot of people have perfectly useful stuff they want to donate. Coats, food, hygiene products, electronics, household items, whatever. The annoying part is figuring out where to actually bring it.
Every organization accepts different things, their needs change, and the information is usually spread across a bunch of different pages.
So Sprinkle basically answers one question:
I have this stuff. Who nearby can actually use it?
You type in what you have in normal language and enter a ZIP code or city. Sprinkle finds nearby organizations, checks what they accept, looks for current needs, and matches your items with what it finds.
Each result also includes a verification label and the sources it used, so you can double-check everything before loading up the car and driving somewhere.
The whole idea is pretty simple: make it easier for useful things to end up somewhere they are actually needed.
Demo
You can try Sprinkle here:
Enter a location and something like:
Two clean winter coats, unopened shampoo, canned soup, and a working laptop.
Sprinkle shows what it is doing while it parses the items, searches for nearby organizations, researches their donation info, and builds the matches.
A brand-new search can take a little while because it is doing live research instead of just pulling results from a static directory.
Code
The source is on GitHub:
pinkpixel-dev
/
sprinkle
Find nearby organizations that can use your donations with Gemini-powered research and source-backed matches.
Sprinkle
Put a little good where it’s needed.
Sprinkle is a small web app that answers one question: I have this stuff, who nearby can actually use it?
You type what you want to donate in plain language, give it a ZIP code, and it goes looking. It finds local organizations, reads their donation pages, pulls out what they accept and what they refuse, checks whether they have a current needs list, and matches that against your items. Every claim comes back with a confidence label and the links it used, so you can check the work yourself.
Try it: sprinkle.pinkpixel.dev
Why this exists
Donating things is more annoying than it should be. Different places take different items, some only want certain things at certain times, and current needs are usually buried on a website, a Facebook post, or a wish list nobody links to. So people either drive around…
Sprinkle is licensed under Apache 2.0.
How I Built It
Sprinkle is built with React and TypeScript and runs through a single Cloudflare Worker.
The Worker handles the API, calls Gemini, streams progress back to the UI, and uses Cloudflare KV for caching and rate limiting. The Gemini API key stays on the server.
The research flow is split into four parts:
Parse:
gemini-3.5-flash-liteturns whatever someone typed into structured donation items with categories and conditions.Discover:
gemini-3.7-flashuses Google Search grounding to find nearby organizations that might accept those items.Research: Gemini uses Google Search plus URL context to read public donation pages and pull out things like accepted items, things they do not take, drop-off details, and current needs.
Match: Gemini compares the donated items with each organization’s policies, then TypeScript handles the final score and sorting.
I originally tried doing discovery and research in one call because it was cheaper, but the results were noticeably thinner and I got fewer useful sources.
Splitting it into two stages worked much better. Sprinkle can first figure out which organizations are worth looking into, then spend the research call actually reading the pages that matter.
The verification system was also really important to me because I did not want the app confidently telling someone to drive across town based on shaky information.
Results are labeled Confirmed, Likely, Call first, or Unknown.
If Gemini gives a confident answer but does not have a valid source URL to back it up, the Worker automatically knocks it down to Call first. The same thing happens when an organization’s donation info is vague or contradictory, even if the actual item match looks good.
The UI gets progress updates through server-sent events. Cold searches can take a bit, so instead of staring at a spinner, you can actually see whether Sprinkle is finding organizations, researching them, or building the final matches.
Discovery results are cached for five days, and organization research is cached for 36 hours.
I intentionally do not cache Unknown results, because if a lookup fails once, I would rather let it try again next time than treat that failure as permanent.
Privacy was pretty simple too.
Sprinkle does not need an account, email address, or exact home address. Donation descriptions are not stored, and Gemini requests use store: false.
The only things that persist are public research about organizations and a short-lived timestamp used for rate limiting.
One of my favorite parts of the project is how many different jobs Gemini is doing inside one pretty focused workflow.
It takes messy normal-language input, turns it into structured data, searches for current information, reads organization pages, compares donation policies, and explains the matches.
Then the TypeScript around it handles the boring-but-important stuff like hard limits, deterministic ranking, caching, rate limiting, and verification rules so the AI stays useful without getting to make every decision by itself.
Prize Categories
I am submitting Sprinkle for Best Use of Google AI.
Gemini handles the item parsing, grounded organization discovery, URL-based research, and semantic donation matching.
It is not really a chatbot bolted onto the side of the app. Gemini is the research engine behind the whole thing, helping answer the actual question Sprinkle was built for:
Where can this specific group of donated items do the most good nearby?