Case study · Automation

A bot that reads the world's tender sites every morning

Public tenders are spread across dozens of official sites, each with its own search. We built a bot that reads them every day, keeps only official tenders, scores each one against what the firm can actually bid for, and posts the shortlist to the team.

The client

Our own firm. Finding the right public tenders by hand took hours a week and still missed many. It is our own work, so we can show it in full.

What needed to change

Hours a week spent searching tender sites one by one.
Tenders found too late to bid.
No consistent way to judge which tenders were worth reading.

What we built

No.PartWhat it means in practice

01SourcesSAM.gov, the World Bank, UNGM, EU TED, UK and Canadian government portals, the Asian Infrastructure Investment Bank, the Islamic Development Bank and more.

02Official tenders onlyNews articles and second-hand listings are ignored; only the issuing body's own notice counts.

03ScoringEach tender scored against the firm's size, turnover and language, with minimum requirements and bid security shown.

04Daily reportA report page and a message to the team's chat channel each morning, listing only what changed.

How it runs now

The bot runs every morning on our own server. The team reads a short list instead of searching.

Built with: Python, Public tender APIs and feeds, Linux VPS, Scheduled jobs, Discord.

More case studies

Free tools

Free SEO checkerSee how Google, ChatGPT and Copilot read your website. 20 checks, a score and a fix for each, in 20 seconds.Check my website →llms.txt generatorDraft the file AI assistants read to understand your site, from your own sitemap, in under a minute.Make my llms.txt →

Book a meeting

Free 30-minute call