Document best practices
How to prepare and upload documents for the best possible analysis results.
The quality of your analysis depends heavily on the quality of your input. Here's what we've learned from thousands of analyzed procurements.
RFP preparation
Include everything relevant
The AI can only check requirements it knows about. If your RFP has technical specifications in a separate annex, upload that annex. If there's an evaluation methodology document, include it. The more complete the picture, the more thorough the check.
Documents to include:
- Main RFP document
- Technical specifications
- Contract terms and conditions
- Evaluation methodology and scoring tables
- Standard forms and templates
- Amendments and clarification answers
- Referenced standards (if practical)
Skip what's not relevant
On the flip side, don't upload 50 pages of general procurement legislation that applies to every procurement. The AI will dutifully read it all, use your credits, and clutter the analysis with generic observations. Focus on documents specific to this procurement.
Bid preparation
Name vendors clearly
When you create a bid, use the actual vendor name. You'll see this in comparisons, exports, and throughout the interface. "SIA TechnoGroup" is better than "Bid 3".
Include supporting materials
Upload everything the vendor submitted:
- Main technical proposal
- Financial offer
- CVs of proposed team members
- Certificates and licenses
- Reference project descriptions
- Subcontractor information
The AI picks up on details across all documents. A CV might confirm a qualification that the main proposal only mentions in passing. A certificate proves what the vendor claims.
One bid per vendor
Don't combine multiple vendors into one bid. Each vendor should have their own bid entry with their own set of documents.
File format tips
Best results: Native digital documents (PDFs created from Word, not scanned). The text is clean and structured, and parsing is fast and accurate.
Good results: Clear scans with readable text. Modern OCR handles these well, but complex tables and small fonts can be problematic.
Poor results: Blurry scans, photos of printed pages, handwritten documents. The AI struggles with these because the text extraction is unreliable.
Won't work: Password-protected files (remove the password first), corrupted files, DRM-protected documents.
Tables and spreadsheets
If the RFP or proposal contains important pricing tables or technical matrices in Excel, upload the Excel file directly rather than a PDF export. The system handles tabular data in spreadsheets better than tables rendered in PDF.
File naming
The AI sees file names and uses them for context when searching documents. Descriptive names help:
| Less helpful | More helpful |
|---|---|
| doc1.pdf | Technical_Specifications_v2.pdf |
| scan_001.pdf | Financial_Proposal_CompanyX.pdf |
| New Document.docx | Team_CVs_TechnoGroup.docx |
Document organization
For procurements with many files (20+), organizing them into folders helps you keep track. The AI reads everything regardless of folder structure, so this is purely for your own convenience.
A simple structure:
- RFP documents / Main / Annexes / Amendments
- Bid: CompanyA / Proposal / Financials / Supporting docs
- Bid: CompanyB / Proposal / Financials / Supporting docs
Common mistakes to avoid
Uploading the RFP as a bid document (or vice versa). The AI treats the RFP as "what's required" and bid documents as "what's offered". Mixing these up produces nonsensical results.
Starting analysis before parsing completes. If documents are still being parsed, the AI works with incomplete information. Always wait for all files to show "Completed" status.
Uploading duplicate files. If the same document appears twice, the AI processes it twice (using more credits) and might raise duplicate findings. Check your upload list for accidental duplicates.
Leaving old versions alongside new ones. If a vendor sent a revised proposal, remove the old version unless you specifically want both analyzed. Two versions of the same document can create contradictory findings.