Calculates the coverage rate for a tender, technology by technology, piece of evidence by piece of evidence.
Developed in Germany · Hosted in the EU or on-premises
Delivered together with
Sovereign hosting in Germany, single-tenant from the first user.
Legal, tax and compliance expertise for legally sound deployment.
Advisory and implementation for the public sector, starting with the AI readiness assessment.
The tender lists its requirements in tables, often spread across several annexes. Anyone who wants to know the coverage rate goes through it line by line and asks the relevant department about each technology area. By the time the answers are back, the table is circulating in three versions, and nobody knows which one counts.
With the three table versions gone, assessment effort falls by 55%, and the 23 open lines are in one place rather than spread across three email attachments.
The 55% reduction in assessment effort is this agent's headline figure. The number of requirements, the areas involved and the table versions describe a typical procedure in bid management; they are illustrative, not measured.
The agent reads the requirement tables from all the annexes and assigns every line to an area. It merges duplicate lines from different annexes.
Procedure AS-2026-118, 146 lines spread across 4 technology areasFor every line, the agent checks whether evidence is stored in the repository and calculates the coverage rate from that. The figure is recalculated from the dataset on every call.
123 of 146 lines evidenced, 23 without evidenceThe agent lists the lines without evidence by area and names the responsible unit. The list goes to the four departments with a field for their rationale.
deckungsgrad_as-2026-118.xlsx, 23 open lines, 4 recipientsIt shows the coverage rate and the open lines. Bid management and executive management decide whether the organisation bids.
For the 23 open lines, it names the technology area and the responsible department. The department says whether a reference can be supplied.
It calculates the coverage rate separately for each area and states the number of open lines for each. The bid manager reads from the procedure's scoring matrix whether one area carries more weight for the award than another.
Connected systems
Operations
A pilot typically runs on your own data within 4 to 6 weeks. The agent connects to your existing systems rather than running as a separate, parallel environment.
EU cloud, private cloud or on-premises. Processing is GDPR-compliant and models are never trained on your data. Details in the Trust Center.
It is based on experience from comparable projects and process benchmarks, not a commitment. We work out the realistic effect for your organisation during the assessment before the pilot.