The industry pattern
Mid-sized planning firms track public tenders every day on TED and DÖE, Germany's central notice service. Their bid process has grown over the years. Typically, several staff spend two hours each per day on different steps: screening and sorting notices, writing bid documents, picking staff from the personnel database by competency, contacting partner firms.
That adds up to about 10 hours a day, more than one full-time role, spent on bidding instead of planning.
A filter that only searches for keywords doesn't know what a firm actually builds. So it returns lots of notices that don't fit, and a person has to sort them out again.
Architecture
The agent doesn't use a generic keyword filter; it works with the firm's own profile. For that, we index:
- Indexing references: the firm's references are tagged by practice area, contract size, project phase and regional distribution.
- Capturing competencies: staff competencies come from the personnel database: specialties, software knowledge, certifications, typical project sizes.
- Partner firms: regular partners are tagged by practice area, along with the track record of past collaboration.
- Target contract sizes: for each practice area, the firm sets the contract size below which a bid isn't worth pursuing.
The agent (Claude Sonnet) sorts incoming notices from TED and DÖE against this firm profile. Hits with a high rating go straight into automatic Word drafting. Hits with a medium rating land on a review list for a single bid manager. If a bid moves on to the next round, the same agent creates the presentation using the same criteria from the firm profile.
Compliance: the agent only does the groundwork. Self-declarations such as the ESPD (European Single Procurement Document) and running the procedure in a legally compliant way stay in the firm's existing workflow. VgV, GWB and HOAI risk remains entirely in the firm's hands.
Model calculation
The projection starts from the baseline the firm owner stated (10 staff hours/day on bid work) and is validated against the TED and DÖE notices the PoC processed:
- 10 staff hours/day → 30 minutes of review in bid work (factor of 20)
- Built into the architecture: once the sorting bottleneck is gone, the firm can handle more bids without adding staff.
- Built into the architecture: competency matching becomes more consistent because the agent uses an indexed staff database instead of manual assignment.
The time freed up goes back into actual planning work. More than one full-time role moves from bid work into planning, with the same people.
Methodology in detail
To keep the factor of 20 traceable, here is the math for a generic mid-market planning firm. It builds on the firm owner's baseline and the target processing time we validated in the fully built PoC.
Typical industry assumptions
- TED and DÖE volume, Germany: we assume 800–1,200 relevant notices per week across all practice areas. TED is the EU-wide platform; DÖE (Datenservice Öffentlicher Einkauf) bundles notices from German federal, state and local authorities.
- Hit rate after indexing the firm profile: typically 0.5–2 % of incoming notices are real matches for a specialized firm. The rest fits the practice area, but not the specific profile.
- Manual screening effort without pre-sorting: roughly 3 min per notice × 200 notices/day = 600 min/day = 10 staff hours/day (baseline stated by the firm owner).
- HOAI fee zones: specialized firms are mostly interested in contracts in the upper fee zones IV and V, where fee rates are higher.
- Procurement law: self-declarations such as the ESPD stay in the firm's existing workflow. The AI makes no procurement-law assessment. VgV, GWB and HOAI risk stays in the firm's hands.
The math
- Factor of 20: 600 min/day (baseline stated by the firm owner) / 30 min/day (target processing time validated in the PoC for reviewing the filtered top hits) = 20×. We measured the target time in the fully built PoC against real TED and DÖE notices; it is not modelled.
- In headcount terms: at 8 hours per working day, 10 staff hours equal roughly 1.25 full-time roles in bid work. Bid work earns no fees, planning does. Every hour that moves from bidding into planning becomes billable.
What moves the numbers
- In smaller firms (under 50 staff), the absolute number of hours saved shrinks. The factor stays, but the business case for the pilot looks different.
- In highly specialized firms (e.g. structural engineering only, HOAI zone V), typical TED volume allows even more selective filtering. The factor can rise to 30–40×, because the hit rate is below 1 % and manual screening is correspondingly less efficient.
The key takeaway
A tender AI that knows nothing about the firm can only return general hits. What matters is not the model but indexing the firm profile. Without that step, even a strong model like Claude Sonnet only returns average hits.
That is exactly what we built: a working PoC that indexes the firm profile and runs against live TED and DÖE notices. The full build was never commissioned, but the prototype runs. For the next firm, it is the starting point for a PoC sprint, not a concept on paper.