Tender Relevance Scorer – AI Bid/No-Bid for EU Tenders
Pricing
from $20.00 / 1,000 results
Tender Relevance Scorer – AI Bid/No-Bid for EU Tenders
Describe what you sell (keywords, CPV codes, countries, budget) and get public tenders from TED (EU), BOAMP (France) and BZP (Poland) ranked 0-100 by fit, with plain-language reasons. Rules + AI. Can also score any tender dataset.
Pricing
from $20.00 / 1,000 results
Rating
0.0
(0)
Developer
Nebulosa Data
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
an hour ago
Last modified
Categories
Share
Describe what your company sells (keywords, CPV codes, countries, budget) and this actor returns current public tenders from TED, BOAMP and Polish BZP ranked 0–100 by how well they fit, each with a plain-language reason. It turns hundreds of notices into a short bid/no-bid list; it can also score any tender dataset you already have.
Stop reading hundreds of tender notices by hand. Describe what your company sells (keywords, CPV codes, countries, budget) and this actor pulls fresh public tenders from TED (Tenders Electronic Daily, all EU/EEA), BOAMP (France) and BZP / e-Zamówienia (Poland), then ranks every notice 0–100 by fit, with plain-language reasons you can check.
Built for SMEs, bid managers, tender consultants and B2G sales teams who want a short list, not a firehose.
How the score works
Each notice gets a transparent rule score that always works, with no AI needed:
| Signal | Points |
|---|---|
| Your keywords in the title / description | up to 40 |
| CPV code: exact match / shared prefix | up to 30 |
| Buyer country in your list | 10 |
| Estimated value inside your budget | 10 |
| Time left before the deadline | up to 10 |
| Exclude keyword found | −40 |
When AI scoring is on, the best candidates also go to TypeSafe Jev, a decision model that returns a calibrated relevance score and a bid probability. The final score is 40% rules and 60% AI, and the output shows both, so you can always see why a notice ranks where it does.
Output (one row per notice, best first)
{"rank": 1, "score": 95, "verdict": "strong fit","reasons": ["AI relevance 100/100 (confidence 100%)", "Keyword in title: catering, comedor escolar", "CPV match 55524000 (profile 55520000)", "23 days to deadline"],"source": "TED", "title": "Spain – School catering services – Servicio de comedor escolar","buyerName": "…", "country": "ESP", "cpvCodes": ["55524000"], "estimatedValue": 1080000, "currency": "EUR","deadline": "2026-11-12", "ruleScore": 95, "aiRelevance": 100, "aiBidProbability": 0.81, "url": "https://ted.europa.eu/…"}
Example input
{"buyerDescription": "Spanish catering company running school and hospital canteens.","keywords": ["catering", "comedor escolar", "restauration scolaire", "żywienie"],"cpvCodes": ["55520000", "555"],"countries": ["ESP", "FRA", "POL"],"budgetMax": 5000000,"sources": ["TED", "BOAMP", "BZP"],"daysBack": 14,"minScore": 50}
Already have tender data? Set datasetId to the dataset of any tender scraper (for example our EU Tenders Scraper (TED), BOAMP Scraper or Przetargi BZP Scraper) and the actor scores those notices instead of searching.
Daily bid/no-bid alerts
Schedule the actor daily with daysBack: 1 and minScore: 60, then connect Slack, email, Google Sheets, Make, Zapier or n8n. You get only the tenders worth a look.
Use cases
- Bid managers getting a short, ranked list instead of hundreds of raw notices.
- IT, consulting, construction SMEs screening EU tenders every morning.
- Tender consultants running one task per client profile.
Pricing
$20 per 1,000 scored notices saved (pay-per-event, from 4 Nov 2026), plus a tiny per-run start fee. Notices below your minScore are not saved and not charged.
FAQ
Which countries? TED covers above-threshold tenders from all 27 EU countries plus EEA. BOAMP adds French national tenders and BZP adds Polish ones.
Is the data official? Yes. It comes from the official public APIs: TED API v3 (Publications Office of the EU), BOAMP open data (DILA, Licence Ouverte) and e-Zamówienia (UZP). Personal e-mails and phone numbers in descriptions are removed.
Can I trust the AI? Every row shows the rule-based reasons and the AI confidence. With AI switched off, the ranking is fully deterministic.
More questions
How is relevance computed? AI relevance to your description + keyword hits in title/description + days to deadline. Every row has human-readable reasons.
Which sources? TED (EU) and BZP (Poland) live APIs.
Can I turn AI off? Yes, set useAi: false for keyword-only scoring.
Pairs with
Reports from Revunda
Need the results as a ready dataset or a one-off report instead of running the actor? See Revunda Data (ES, RU) for prices and sample outputs.
More questions (FAQ)
How do I find relevant public tenders for my company?
Enter your offer as keywords and CPV codes, choose countries and a budget range, and sort the output by score.
Can it score tenders from another scraper?
Yes. Pass a dataset ID with tender rows and the actor scores those instead of fetching new ones.
Is the score a guarantee of winning?
No. It ranks fit with your description so you read the best notices first; eligibility and bid decisions are yours.