# GGTC Kyiv — 28 relevant opportunities for a think tank — out of 10,000+ pages processed

> 28 opportunities · 10,000+ pages

- **Client:** GGTC Kyiv — the Global Government Technology Centre, the world's second GovTech centre after Berlin
- **Website:** kyivgovtechcentre.org
- **Industry:** GovTech · digital transformation of government
- **Who uses it:** The centre's fundraising lead
- **Format:** Grant-scouting agent + a web interface for the team
- **Timeline:** First working result — under a week from kickoff

## The problem

One person was hunting for grants. More than 35 sources: grant platforms, embassy pages, sector newsletters, Telegram channels — and the whole round had to be repeated every week, because new calls appear all the time. Every call is 40+ pages of terms: budget, deadline, eligibility, consortium requirements. You have to read all of it to answer one question — does the organisation even qualify? Most of the time it doesn't.

## What it does

We built the centre Granty — an agent that does the round itself. On a schedule it reads every source, scores every opportunity against the centre's own criteria (focus, budget, deadline, eligibility, consortium) and surfaces a short list with a 1–10 score and a reason each grant made it. Sources and criteria live in the centre's own Google files: the fundraiser changes the rules herself, and the agent shows the diff before applying them. No developer needed for that.

- Covers 35+ sources: grant platforms, embassy pages, Telegram channels — and takes European calls from the official EU Funding & Tenders API rather than scraping
- Scores every opportunity against the centre's seven criteria and shows the breakdown — you can see why it got that score instead of «the AI said so»
- Criteria live in the client's own Google Doc: edit → the agent shows a diff → confirm. The previous version keeps running until the new one is approved
- Results land both in the interface and in a Google Sheet; «reviewed / rejected» triage happens right in the list
- Sources that failed to load don't vanish — the agent lists them separately for a human to check by hand

## Result

- **28 relevant out of 420** — One run: 35 sources covered, 420 opportunities read, 28 surfaced with an explanation.
- **Minutes for a full round of sources** — The same reading by hand — roughly 160 hours by our estimate, about a month.
- **<1 week to first result** — From kickoff to a working agent with live findings — four days.

## ← All cases

- [Minimal Studio](https://propellercrew.com/en/cases/minimal-studio) — A design studio saves 30+ hours a month — and is thinking about a 6-hour workday
- [Kartonky](https://propellercrew.com/en/cases/kartonky) — Launched in under an hour — 5M+ media reach in 3 days
- [Fulcrum](https://propellercrew.com/en/cases/fulcrum) — A complex WordPress site, now edited by an AI agent
- [Gearheart](https://propellercrew.com/en/cases/gearheart) — A website the team updates just by writing in Slack
- [Propeller Crew — our own outreach](https://propellercrew.com/en/cases/linkedin-outreach) — 17 people asked for a call in 4 weeks
- [Revby](https://propellercrew.com/en/cases/revby) — A cold list that comes alive: warm reasons to write instead of a static spreadsheet
- [Subtitler](https://propellercrew.com/en/cases/subtitler) — Drop in a vertical video — get back a Reels-ready cut with subtitles
- [Brandkit](https://propellercrew.com/en/cases/brandkit) — Give it your website — get your company's brandbook in minutes
- [Perry](https://propellercrew.com/en/cases/perry) — The personal assistant that keeps a company's operations in order
- [Webby](https://propellercrew.com/en/cases/webby) — The helper that runs a website from Slack — including this one

---

Source: https://propellercrew.com/en/cases/ggtc (HTML) · https://propellercrew.com/en/cases/ggtc.md (Markdown)
Contact: tim@propellercrew.com · https://t.me/timakozak · Call: https://calendar.notion.so/meet/timakozak/propeller-15min
Agent index: https://propellercrew.com/llms.txt · https://propellercrew.com/sitemap.xml