Predictika · Parking garage quotes

An AI sales agent's parking garage quote, checked before it goes out

An AI sales agent prepares a quote for a GOLDBECK Parkhaus: the garage type, the levels and stalls, the stall and aisle geometry, the ramp, the facade and ventilation, the charging share and the roof and slab options. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of how those choices fit together and returns a verdict, every reason and the capacity it computed.

Scope: One GOLDBECK Parkhaus per quote (staff, neighborhood or Mobility Hub): levels and stalls, capacity against need, stall, aisle, height and ramp geometry, facade and ventilation, charging share, slab and roof options. See everything this validator covers

This validator models GOLDBECK Parkhaus quotes, not just the scenarios shown below.

  • Garage type and size — staff, neighborhood and Mobility Hub garages, from 1 to 8 levels and 40 to 400 stalls per level, with the stalls needed checked against the stalls provided.
  • Geometry — stall width, driving aisle, clear height and ramp slope against modeled limits.
  • Facade and ventilation — natural ventilation needs enough open facade, and a closed panel facade needs mechanical ventilation.
  • Charging — a Mobility Hub needs a minimum share of stalls prepared for charging.
  • Slab and roof options — a carbon-concrete slab on a tall structure and photovoltaic together with roof greening go to a person to confirm.
  • Stated total — the stall total the quote states against the total computed from the levels.

Any GOLDBECK Parkhaus quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: other GOLDBECK product lines (offices, halls, schools, housing), parking management and service. The validator produces no price build-up. GOLDBECK publishes no dimensions or limits for the Parkhaus, so every numeric limit here is modeled.

The AI sales agentBuilds the parking garage quote from the conversation with the customer and says it is ready.
Predictika validatorChecks every rule at once and returns the verdict, each finding, and the computed figures.

6 scenarios in 3 groups · each group runs from the agent’s first attempt to the outcome · click one to switch

What the agent proposes

The AI sales agent says

Illustrative agent statement. The validator receives the structured request below.

Proposing agent: AI sales agent (scripted)

Before sending, the agent must call Recorded run

Predictika validator


      
Waiting for the call.

Where rules-based CPQ gets it wrong

Click to expand

Our assessment of what a typical rules-based CPQ (product rules, price rules and validation rules, as in Salesforce CPQ) does with the same cases. It is a judgment about effort and reliability, not a claim that nothing can be built.

What the validator caughtTypical rules-based CPQPredictika
Capacity that must cover the stalls neededOnly with workarounds
The capacity is levels times stalls per level, so a separate calculation is needed before it can be compared with the stalls the customer needs.
The levels, stalls per level and stalls needed are fields of the request and are compared in the same pass.
Facade and ventilation that depend on each otherOnly with care
A closed panel facade rules out natural ventilation and natural ventilation needs enough open facade, so each is its own rule that reads another choice.
The facade, the ventilation and the open share are checked together on every call.
Geometry limits on stalls, aisle, height and rampOnly with care
Each limit is its own rule, and the rule list grows with every dimension that is added.
Each dimension is a field of the request and is checked against its limit on every call.
Options that need a person once they combineOnly with care
A slab above a certain height or two roof options together each need their own approval rule that reads several choices.
The slab, the levels and the roof options are checked together and approvals are listed with the blocks.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the quote is saved or a step is completed, so a rep often fixes one error and meets the next.
All findings come back together, whatever order the choices arrived in.

What this validator catches: findings from its test cases

Click to expand

Every rule is checked on every call, in any order the choices arrive; one problem never hides another. Blocking findings stop the quote; approval findings need a person to sign off; everything else is computed.

1A Mobility Hub needs at least 20 percent of stalls prepared for charging; the quote has 19 percent.
2The quote has 9 parking levels; this model supports 1 to 8.
3The quote has 39 stalls per level; this model supports 40 to 400.
4The customer needs 401 stalls; the quoted structure provides 400.
5The quote states 420 stalls in total; the quoted levels give 400.
6Stall width is 245 cm; the minimum in this model is 250 cm.
7Driving aisle is 540 cm; the minimum in this model is 550 cm.
8Clear height is 200 cm; the minimum in this model is 210 cm.
9Ramp slope is 16 percent; the maximum in this model is 15 percent.
10Natural ventilation needs at least 33 percent open facade; the quote has 30 percent.
11A closed panel facade needs mechanical ventilation.
12Carbon-concrete ceiling slabs on a structure of more than 5 levels need a structural engineer to confirm.
13Photovoltaic and roof greening are both on the roof deck; a person should confirm the roof layout.

Scenarios and results

Click to expand

The recorded result of the validator for each scenario on this page: the request the AI agent sent, the verdict, and every finding, in the order they appear above.

1. Facade, ramp and slab: A neighborhood garage with a closed facade, natural ventilation and a carbon-concrete slab

The agent's request. Please quote a neighborhood garage of 7 levels with 90 stalls per level, 630 stalls in total, for a customer who needs 600 stalls. Stalls are 250 cm wide, the driving aisle is 600 cm, the clear height is 220 cm and the ramp slope is 17 percent. The facade is closed panel with natural ventilation and 20 percent open facade, 10 percent of stalls are prepared for charging, and the slab is carbon-concrete. It is ready to send.

Verdict: Blocked.

  • Ramp too steep. Ramp slope is 17 percent; the maximum in this model is 15 percent.
  • Natural ventilation needs open facade. Natural ventilation needs at least 33 percent open facade; the quote has 20 percent.
  • Closed facade needs mechanical ventilation. A closed panel facade needs mechanical ventilation.
  • Carbon-concrete slab on tall structure. Carbon-concrete ceiling slabs on a structure of more than 5 levels need a structural engineer to confirm.

2. Facade, ramp and slab: The agent resubmits after fixing the errors

The agent's request. Please quote a neighborhood garage of 7 levels with 90 stalls per level, 630 stalls in total, for a customer who needs 600 stalls. Stalls are 250 cm wide, the driving aisle is 600 cm, the clear height is 220 cm and the ramp slope is 12 percent. The facade is open wave with natural ventilation and 40 percent open facade, 10 percent of stalls are prepared for charging, and the slab is carbon-concrete. It is ready to send.

Verdict: Needs approval.

  • Carbon-concrete slab on tall structure. Carbon-concrete ceiling slabs on a structure of more than 5 levels need a structural engineer to confirm.
  • Capacity summary. 7 levels of 90 stalls, 630 stalls in total.

3. Capacity, aisle and charging: A Mobility Hub for a customer who needs 640 stalls

The agent's request. Please quote a Mobility Hub of 5 levels with 120 stalls per level, 600 stalls in total, for a customer who needs 640 stalls. Stalls are 250 cm wide, the driving aisle is 520 cm, the clear height is 220 cm and the ramp slope is 14 percent. The facade is open wood with natural ventilation and 40 percent open facade, 10 percent of stalls are prepared for charging, and the slab is standard. It is ready to send.

Verdict: Blocked.

  • Stalls needed exceed capacity. The customer needs 640 stalls; the quoted structure provides 600.
  • Driving aisle too narrow. Driving aisle is 520 cm; the minimum in this model is 550 cm.
  • Mobility Hub needs charging share. A Mobility Hub needs at least 20 percent of stalls prepared for charging; the quote has 10 percent.

4. Capacity, aisle and charging: The agent resubmits after fixing the errors

The agent's request. Please quote a Mobility Hub of 6 levels with 120 stalls per level, 720 stalls in total, for a customer who needs 640 stalls. Stalls are 250 cm wide, the driving aisle is 600 cm, the clear height is 220 cm and the ramp slope is 14 percent. The facade is open wood with natural ventilation and 40 percent open facade, 25 percent of stalls are prepared for charging, and the slab is standard. It is ready to send.

Verdict: Allowed.

  • Capacity summary. 6 levels of 120 stalls, 720 stalls in total.

5. Roof deck options: A staff garage with photovoltaic and roof greening together

The agent's request. Please quote a staff garage of 4 levels with 100 stalls per level, 400 stalls in total, for a customer who needs 380 stalls. Stalls are 250 cm wide, the driving aisle is 600 cm, the clear height is 220 cm and the ramp slope is 12 percent. The facade is open wood with natural ventilation and 40 percent open facade, 10 percent of stalls are prepared for charging, and the slab is standard, with integrated photovoltaic and roof greening. It is ready to send.

Verdict: Needs approval.

  • Photovoltaic and roof greening together. Photovoltaic and roof greening are both on the roof deck; a person should confirm the roof layout.
  • Capacity summary. 4 levels of 100 stalls, 400 stalls in total.

6. Roof deck options: The agent resubmits after fixing the errors

The agent's request. Please quote a staff garage of 4 levels with 100 stalls per level, 400 stalls in total, for a customer who needs 380 stalls. Stalls are 250 cm wide, the driving aisle is 600 cm, the clear height is 220 cm and the ramp slope is 12 percent. The facade is open wood with natural ventilation and 40 percent open facade, 10 percent of stalls are prepared for charging, and the slab is standard, with integrated photovoltaic. It is ready to send.

Verdict: Allowed.

  • Capacity summary. 4 levels of 100 stalls, 400 stalls in total.

Narration transcript

Click to expand

The text of the narrated walkthrough, step by step.

  1. Welcome to a demo of Predictika's Validator. An AI sales agent prepares a quote for a GOLDBECK Parkhaus: the garage type, the levels and stalls, the stall and aisle geometry, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of how those choices fit together and returns a verdict, every reason and the capacity it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote a neighborhood garage of 7 levels with 90 stalls per level, 630 stalls in total, for a customer who needs 600 stalls. Stalls are 250 cm wide, the driving aisle is 600 cm, the clear height is 220 cm and the ramp slope is 17 percent. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with three findings and one approval, all in one answer. Ramp slope is 17 percent; the maximum in this model is 15 percent. Natural ventilation needs at least 33 percent open facade; the quote has 20 percent. A closed panel facade needs mechanical ventilation.
  6. The validator returned three blocking findings and one approval in one answer. A check that reads one field at a time would pass most of this; it shows only when the choices in the quote are checked against each other.
  7. What this shows: for facade and ventilation that depend on each other, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the ramp slope to 12 percent, the facade to open wave and the open facade to 40 percent.
  10. It calls the validator again.
  11. Not blocked, but held for a person.
  12. The three blocking findings are cleared; one approval remains for a person: carbon-concrete slab on tall structure.
  13. Four problems caught in one call, fixed in one pass, and the corrected quote now goes to a person for approval. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.