--- title: "Tenders at planning firms: 30 minutes instead of 10 hours" description: "Planning firm use case study: KL works through how an agent tuned to the firm's profile can cut the effort of bid work by a factor of 20." canonical_url: "https://kevinludwig.com/en/case-studies/planungsbuero-ausschreibungs-pipeline" last_updated: "2026-03-15" --- [All case studies](https://kevinludwig.com/en/case-studies) Use case, Planning firm, 2026 # Tenders at planning firms: 30 minutes of review instead of 10 hours of bid work a day How an agent that knows the firm's profile can cut up to ten staff hours of daily bid work down to thirty minutes of review, without generic tender AI. A use case study built on conversations with planning firms and our production-ready prototype. [Auf Deutsch lesen](https://kevinludwig.com/de/case-studies/planungsbuero-ausschreibungs-pipeline) Potential effect 20× Less time on bid work (projected from the figures in our conversations) - Industry Planning firms (architecture and engineering services) from about 10 employees that regularly bid on public tenders - Scope Fully built prototype; projection based on the figures planning firms gave us in our conversations - Technologies used Claude Sonnet, Next.js, Postgres, procurement portals (EU and Germany) ## Starting point At planning firms, several people often work on tenders every day: they screen notices on the procurement portals, sort them, write bid documents, pick the right people by competency and contact partner firms. Filtering by keywords alone returns hit lists that match thousands of firms at once and none of them really. ## What we built The agent doesn't rely on a generic keyword filter; it works with the firm's own profile: its references, its staff's competencies, its regular partner firms and the target contract sizes it has set for each practice area. Claude Sonnet sorts incoming notices against this profile, drafts the first bid from the tender documents and, if the bid moves on, the presentation. 30 minutes, and you know whether it fits your workflow. [Book a first call](https://kevinludwig.com/en/kontakt#termin) ## Focus - ### Tuned to your firm profile A tender AI that doesn't know your firm can only return general hits. We index your reference list, your staff's skills, your regular partner firms and the contract sizes that make economic sense for you. The results then show what your firm can actually deliver, not what fits ten thousand other firms just as well. - ### From screening to bid presentation The agent does the groundwork of the bid workflow: it filters notices from the procurement portals, sorts them, drafts the first bid from the tender documents, finds matching staff in your personnel database and suggests partner firms. If a bid is shortlisted, the same agent creates the presentation on the same principle. - ### Compliance stays in your firm We don't build AI that makes procurement-law judgments. The agent only does the groundwork: screening, sorting, drafting, matching staff by competency. The legally compliant finalization (self-declarations such as the ESPD, procedural compliance) stays in your existing workflow. VgV, GWB and HOAI risk stays in your hands. ## Why tender AI needs to know your firm profile. Tender software has been around for years. What's been missing is tender AI that understands what your firm stands for. We heard this again and again in our conversations with planning firms: a plain keyword filter doesn't know the firm profile. It returns a hit list that fits thousands of firms at once and none of them really well, and bid managers end up sorting through the notices themselves again. So we tune the agent to the firm's own profile: references, staff competencies, regular partner firms and target contract sizes per practice area. Projected, up to 10 staff hours of bid work per day become 30 minutes of review, a factor of 20. We built this approach as a working prototype: reference list and staff database indexed, the classification run against live notices, the pre-selection matched to the firm's own services. The prototype works, and it is the starting point for your firm. The fair concern Another tender filter that throws out everything above €5 million without ever checking whether your firm profile actually fits. ## Your tender agent in 10 working days. In the 10-day pilot, the agent runs with your firm profile against live notices. Your bid team checks the hits before you decide on the full build. [All about the 10-day pilot](https://kevinludwig.com/en/leistungen/pilot) - ### Your firm profile, indexed References, staff competencies, partner firms and target contract sizes, taken from the lists you already have. - ### A pre-sorted hit list Live notices from the procurement portals, sorted against your profile, with the reason for each hit. - ### A first bid Drafted from the tender documents for a matching hit, for your team to review. If connecting your portals takes more work, the bid moves into the full build. - ### Decision paper with your numbers How much review time your team needed, how good the hits were, and what the full build would take. ## What we need from you - Your reference list as it exists today, in any format - An overview of your staff and their specialties - Your regular partner firms and the minimum contract size per practice area - One person from bid work who rates the hits and makes the call ## What you can rely on. - ### Day-7 commitment If the version on day 7 doesn't meet one of the checkpoints agreed in writing, we show you a new version within five working days until all are met, provided access and data are available as agreed. - ### Fixed amount Before the start you get a fixed amount for the scope agreed in writing. We only charge more if you commission additional work. Third-party costs, such as hosting or AI, are listed separately in the offer. For businesses only. The written offer sets out the details, and your statutory rights remain in place. ## What we heard in our conversations In at least five conversations with planning firms, the same topic came up: bid work eats time nobody can bill for. The process has grown over the years and looks almost the same everywhere. Several people share the steps: screening and sorting notices on the procurement portals, writing bid documents, picking staff by competency, contacting partner firms. Depending on firm size, the owners named anything from several hours to **a good 10 hours a day. At the upper end, that's more than one full-time role spent on bidding instead of planning.** Another thing almost every firm mentioned: they had already tried keyword filters and tender tools. Those don't know which projects fit a firm, so they return 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: 1. **Indexing references:** the firm's references are tagged by practice area, contract size, project phase and regional distribution. 2. **Capturing competencies:** staff competencies come from the personnel database: specialties, software knowledge, certifications, typical project sizes. 3. **Partner firms:** regular partners are tagged by practice area, along with the track record of past collaboration. 4. **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 the procurement portals against this firm profile. For hits with a high rating, it drafts the first bid straight from the tender documents. 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 upper end of the figures planning firms gave us (10 staff hours/day on bid work) and is validated against the notices the prototype 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**, **with the same people**. ## What we take from it 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 prototype that indexes the firm profile and runs against live notices. For your firm, it is the starting point for a 10-day pilot, not a concept on paper. Methodology in detail: assumptions and math To keep the factor of 20 traceable, here is the math for a generic planning firm. It builds on the figures from our conversations with planning firms and the target processing time we validated in the fully built prototype. ### Typical industry assumptions - **Volume on the procurement portals (EU and Germany):** we assume 800–1,200 relevant notices per week across all practice areas. - **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** (upper end of the figures from our conversations). - **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 (upper end from our conversations) / 30 min/day (target processing time validated in the prototype for reviewing the filtered top hits) = **20×**. We measured the target time in the fully built prototype against real 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 - Smaller firms save fewer hours in absolute terms; the factor stays similar. - In highly specialized firms (e.g. structural engineering only, HOAI zone V), filtering can be even more selective. The factor can rise to **30–40×**, because the hit rate is below 1 % and manual screening is correspondingly less efficient. ## Compliance We don't build AI that makes procurement-law judgments. The agent only does the groundwork: screening, sorting, drafting, matching staff by competency. The legally compliant finalization (self-declarations such as the ESPD, procedural compliance) stays in your existing workflow, with your legal counsel where needed. That keeps VgV, GWB and HOAI risk entirely in your hands. We host in EU regions, sign the DPA before the project starts and can run the system on your own servers if your firm's data protection concept requires it. ## FAQ Which tender platforms do you integrate with? By default, the main procurement portals of the EU and the German federal government, which together bring most of the notices relevant to planning firms in Germany into one place. We connect further tender portals if your firm pursues tenders from those sources. We check the specific integration on day one of the 10-day pilot. How is this different from generic tender tools? A tool that doesn't know your firm can only filter public notices by keywords. The result is lots of hits that don't fit: too small, too large, wrong practice area, no matching competencies. We take a different approach. In the 10-day pilot, we index your reference list, your staff competencies, your regular partner firms and your target contract sizes. The agent sorts incoming notices against this firm profile and returns a short, filtered hit list instead of an unsorted stream. How quickly do we see results? The 10-day pilot takes ten working days: the agent sorts live notices from the procurement portals, matched against your firm profile. In the full build, automatic drafting and competency matching from the staff database follow within a few weeks. Bid managers see the effect from the first round of notices after launch. Projected, the daily effort drops from up to 10 staff hours to 30 minutes of review, a factor of 20. Who keeps the system tuned to our firm profile? If you like, we do it for the first six months: once a month we tune the prompts based on your feedback on the hits. After that, we hand the tools over to your bid team: an interface for tagging references, a way to maintain skills in the staff database and a versioned prompt editor. If you like, we stay on as your point of contact under a maintenance contract. For ongoing strategic guidance, there's our Fractional CTO offer. How large does our firm need to be for this system? The system makes sense from about 10 employees, if your firm bids on public tenders regularly. Smaller firms save fewer hours in absolute terms; the factor stays similar. From about 150 employees, the effect gets particularly large: a projected 1.5–2.5 full-time roles freed up in bid work, which move into actual planning work instead of being cut. ## The same for your company? The fastest way to find out is a 10-day pilot on your own data. - [10-Day Pilot First version usually within days, on your real data](https://kevinludwig.com/en/leistungen/pilot) - [Product Build If the pilot convinces you: in use within weeks](https://kevinludwig.com/en/leistungen/umsetzung) ## Let's talk. Tell us what it's about and Kevin Ludwig gives you a first assessment of whether and how it can be built. > “You can simply rely on him.” Judith Hickel, Gloria Kollektiv e.V. 5.0 from 8 Google reviews As of October 6, 2026. We don't verify whether reviews come from clients. [Book a first call](https://kevinludwig.com/en/kontakt#termin) [Or write to us, one sentence is enough.](https://kevinludwig.com/en/kontakt?anliegen=idea#anliegen) On working days we usually reply within 24 hours.