Skip to content

Processing Questions

Once you have created a tender, the next step is to upload your question file. Tendrex parses the file, auto-classifies columns and metadata, and queues questions for AI answer generation.

  • Excel (.xlsx) - each row is treated as a separate question. Tendrex auto-detects the question column based on header names and content. Multi-sheet workbooks are supported — you choose which sheet to process.
  • Word (.docx) - questions are parsed from the document structure (headings, numbered lists, or tables).
  1. Open your tender.
  2. Click Upload Questions.
  3. Select your question file.
  4. Multi-sheet Excel files: If the workbook contains multiple sheets, Tendrex shows a sheet picker. Select the sheet containing your questions. You can switch sheets later to process a different sheet from the same file.
  5. Tendrex displays a preview of the parsed questions with auto-detected column mappings. Review and adjust if needed.
  6. Click Process to start AI answer generation.

For Excel files, Tendrex automatically identifies and classifies columns:

Column TypeDescription
QuestionThe main question text
SectionThe section or category (e.g. Quality, Social Value, Technical)
ReferenceThe question reference number (e.g. “3.1.2”)
Max ScoreThe maximum marks available
WeightingThe percentage weighting for scoring (e.g. “10%”, “15”)
Word LimitAny word count constraints (e.g. “500 words”, “1,000”)
ContextAdditional context or guidance
MetadataOther columns (scoring type, evaluation criteria, etc.)

You can manually override the auto-detection before processing.

Beyond column classification, Tendrex uses AI to extract and enrich question metadata:

  • Section identification - categorises questions by topic (Quality, Social Value, Technical, Commercial, etc.)
  • Question number parsing - extracts structured reference numbers
  • Word limit detection - identifies word count constraints from the question text
  • Scoring type classification - determines if a question is scored, pass/fail, or information only
  • Guidance notes extraction - pulls out buyer guidance on what they expect in the response

After clicking Process, you can monitor progress on the tender page:

  • A progress bar shows how many questions have been processed.
  • Each question shows its status: Queued, Processing, or Complete.
  • Processing typically takes 5-15 seconds per question, depending on complexity and the size of your knowledge base.

When generating each answer, the AI follows a priority chain:

  1. Canonical store - checks your library of approved, canonical answers first
  2. Historical responses - looks at answers from previous tenders
  3. RAG chunks - retrieves relevant passages from your uploaded source documents
  4. AI fallback - generates from scratch when no strong source material exists

Rejected answers are also stored and fed back into prompts so the AI avoids repeating the same mistakes.

When you export a tender’s answers to Excel, the spreadsheet includes the following columns:

ColumnDescription
#Question number
SectionThe question section or category
QuestionThe question text
AnswerThe approved answer text
Weighting %The scoring weighting percentage
Word LimitAny word count constraints
ConfidenceThe AI confidence level (High/Medium/Low)
SourcesSource document citations

Column values from the original spreadsheet take priority. AI extraction fills any gaps for section, question number, scoring type, and guidance notes.

If you upload additional source documents after processing, you can re-process individual questions or the entire tender to generate updated answers using the new material.