Lots
Configuring multi-lot procurement structure for per-lot bid analysis and comparison.
Lots split a procurement into separate packages or line items. Each lot has its own requirements, estimated value, and delivery terms. Vendors can bid on some or all of them. When lots are configured, the AI analyzes each bid at the lot level — tracking participation, offered prices, quantities, and compliance per lot.
When to use lots
Use lots when your RFP explicitly defines them. This is standard in EU and Baltic public procurement, where directives allow (and sometimes require) dividing contracts into lots.
Common examples:
- Office supplies: Lot 1 (furniture), Lot 2 (electronics), Lot 3 (stationery)
- IT services: Lot 1 (hardware maintenance), Lot 2 (software development), Lot 3 (helpdesk)
- Construction: Lot 1 (demolition), Lot 2 (structural work), Lot 3 (finishing)
Don't create artificial lot structures for a procurement that doesn't define them — it won't help and may confuse the analysis.
Setting up lots
Click Lots in the sidebar workflow. You have two options:
Auto-extract from RFP
Click Extract from RFP to have the AI read your procurement documents and identify lots automatically. The extraction agent:
- Reads the full RFP structure to find lot definitions, tables, and annexes
- Extracts lot numbers, names, descriptions, CPV codes, estimated values, quantities, units, and delivery timelines
- Validates that lot numbers match what's actually in the RFP (it won't fabricate lots)
- Detects framework agreements and catalog-based procurements where no lot structure exists — in those cases, it reports that no lots were found
You'll see real-time progress as the agent works. Once complete, review the extracted lots and edit any details that need correction.
Manual setup
Click Add manually to create lots one by one. For each lot, you can specify:
| Field | Required | Description |
|---|---|---|
| Number | Yes | The lot number as defined in the RFP (1, 2, 3...) |
| Name | Yes | A short label for the lot |
| Description | No | What this lot covers |
| CPV code | No | Common Procurement Vocabulary code, if specified |
| Estimated value | No | The RFP's estimated value for this lot |
| Currency | No | EUR, USD, etc. |
| Quantity | No | Number of units, if applicable |
| Unit | No | Unit of measurement (pieces, hours, kg...) |
| Delivery days | No | Required delivery timeline |
Set up lots before running analysis. The AI uses them during analysis to track per-lot participation and compliance. If you add lots after analysis, you'll need to re-run it.
Editing and removing lots
You can edit or delete lots at any time from the Lots view. Click Clear all to remove all lots and start over (or re-extract). Changes only affect future analyses — existing results stay as they were.
How lots affect analysis
When lots are configured, the analysis agent works differently:
-
Participation detection — the AI identifies which lots each vendor is bidding on. Some vendors bid on everything, others on a subset. The system tracks participation status per lot: compliant, partial, non-compliant, or not participating.
-
Per-lot compliance — findings can be tagged to specific lots. A vendor might be fully compliant on Lot 1 but have critical issues on Lot 3.
-
Price and quantity extraction — the AI extracts offered prices, quantities, and delivery timelines for each lot the vendor participates in. It verifies calculations (unit price times quantity equals total) and flags discrepancies.
-
Compliance scoring — each lot participation gets a compliance score and a recommended/not-recommended status.
Comparing lots across vendors
The Compare & Export view includes a Lots tab that shows a matrix:
- Rows: your procurement lots (number, name, estimated value)
- Columns: each vendor/bid
- Cells: offered price, compliance status (color-coded), and a recommendation indicator
This makes it easy to see at a glance which vendor offers the best terms per lot and where compliance issues exist.
Lots with evaluation criteria
When you have both lots and evaluation criteria configured, the analysis becomes very structured:
- For each vendor, for each lot they bid on, for each criterion — you get a specific value
- The comparison shows this as a multi-dimensional matrix
- You can see exactly where each vendor is strong or weak, per lot and per criterion
This is the most detailed analysis the platform can produce. It takes more time and credits, but for large multi-lot procurements with multiple vendors, it's the most effective approach.
Tips
- Match the RFP exactly. Use the same lot numbers and names as your RFP. The AI uses these to match bid content to the right lot.
- Include estimated values when known. This helps the AI flag bids that are significantly above or below expectations.
- Review extracted lots before analysis. Auto-extraction is accurate but not infallible — a quick review ensures nothing was missed or misinterpreted.