Why I stopped trading and started tendering with AI

Описание и применение

Автор заменил торговые боты на AI‑систему для анализа и ответа на тендеры, что повысило количество заявок, коэффициент выигрыша и снизило затраты.

Задача

Traditional tendering is manual, time‑consuming, and error‑prone, making it infeasible for small businesses to respond to many tenders.

Результат

The AI pipeline increased bid volume, improved win rate, reduced manual costs, and provided scalability for tender responses.

Рабочий процесс

• Parse tender documents with OCR (PyTesseract, pdfminer.six)
• Chunk and summarize text
• Use a fine‑tuned Llama 2 7B for requirement extraction
• Embed requirements and query Pinecone for matching capabilities
• Generate compliant tender response with LLM prompts
• Cross‑check response against original requirements for compliance

Доказательства

Traditional methods relied on manual reading and tagging - a process slow and expensive.

Источник

I fine‑tuned a model (currently a quantized Llama 2 7B, deployed locally for cost and control) on a dataset of tender documents and manually labeled requirements.

Источник

We can now analyze and respond to significantly more tenders.

Источник