How it runs today
- 01The documents arrive as a PDF bundle, sometimes with hundreds of items.
- 02Someone skims them and decides whether costing is worth it.
- 03If it is costed, items are matched by hand against your own range of services.
Use case
Tenders
Reviewing tenders is expensive, and most of them lead nowhere. Which is exactly why the pre-selection is worth more than the costing itself.
Highest value per individual case
The difference
The same process, once as it is today and once with us.
- 01Documents
- 02Review
- 03Matching
A person does itThe system does it
How it would run with us
- 01The bundle is read out in full, even at hundreds of items.
- 02The item list is held against your range of services, with exclusion and eligibility criteria alongside.
- 03You get an assessment with reasons and decide whether to take part.
What it gets you
- A tender document is read through, even at three hundred line items.
- The decision whether to bid takes a day instead of a week.
- No tender is missed because nobody had time that week.
Where it does not fit
Where an award turns on references and relationships, an evaluation helps little - there it is not the document that decides.
More specific
What this looks like in your sector
The process is sector-independent, the fit is not. These pages show the systems, the formats and the rules that actually apply there.
Construction & building services
In public procurement, the pre-selection decides the return, not the costing. Every hour spent on a tender you were going to lose anyway is missing from the one you could have won.
ViewMechanical engineering
In mechanical engineering the exclusion criterion sits in running text, not in a line item. Skim the document and you find it reliably too late.
ViewProfessional services
In professional services the formalities decide participation and the concept decides the award. The pre-selection therefore has to check both.
ViewFrequently asked
How long does implementation take?
5 to 8 weeks - the most demanding of the eight cases. Building it is usually the shorter half - the time goes into access, coordination and test cases.
What do we have to provide?
Your range of services in structured form - a list is enough, it only has to be complete. Ten to twenty past tenders together with the decision you took at the time. A contact in costing for the questions of the first weeks. Nothing more is needed to start.
How will we know it works?
From verifiable criteria agreed before the build: Across 20 real tenders the "cost it / drop it" recommendation agrees with yours in at least 85 %. The item list is read out in full - verified by spot check against the PDF. No bid is submitted without a person looking at it.
Does the AI decide on its own?
The evaluation runs independently; the decision to take part is made by a person. A tender wrongly dropped is never seen again.
When is this not worth it?
Where an award turns on references and relationships, an evaluation helps little - there it is not the document that decides.
Which sectors does this suit?
In our experience particularly Construction & building services, Mechanical engineering, Professional services. The process itself is sector-independent, though - what matters is whether it repeats.
Let us start with a conversation.
You tell us where your time goes. We put it in writing: what is worth automating, and roughly what that costs.
