Predictika · Crawler excavator quotes

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

An AI sales agent prepares a quote for a 22-ton class crawler excavator with a boom, an arm, track shoes and a bucket. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the machine's published configuration tables and returns a verdict, every reason and the figures it computed.

Scope: HX220A L crawler excavator quotes: variants, booms, arms, track shoes and buckets. See everything this validator covers

This validator models HX220A L crawler excavator quotes, not just the scenarios shown below.

  • Variants and track shoes — the HX220A L, HX220A L HW and HX220A LR, and which 600, 700, 800 and 900 mm triple grouser shoes or 700 mm double grouser shoe each one is listed with; the overall width the shoes give is compared with a transport width limit on the quote.
  • Booms and arms — the 5.70 m mono boom with 2.0, 2.4, 2.9 or 3.5 m arms, the 5.87 m 2-piece boom with 2.0, 2.4 or 2.9 m arms and the 8.5 m long reach boom with the 6.2 m arm; the maximum digging depth for each combination is computed and compared with the figure the quote states.
  • Buckets — the twelve buckets of the bucket selection guide; for the mono boom and the long reach boom the quote's material density is checked against the density each bucket and arm is recommended for, and combinations the guide marks as not recommended are sent for approval.

Any HX220A L quote that touches these tables is in scope — not only the scenarios pictured here. Not covered: prices (HD Hyundai Construction Equipment does not publish list prices, so this validator produces no price build-up or line-item quote), bucket recommendations for the 2-piece boom (the guide's column headings for it are inconsistent), lifting capacity tables, optional equipment and other HD Hyundai machines. The bucket guide is a recommendation, so a mismatch needs approval rather than being blocked.

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

7 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
Arms listed only for certain boomsOnly with care
A product rule per boom and arm. It works, but every new boom or arm is another set of rules to maintain.		The boom and the arm are in one request and every combination is checked together.
Track shoes listed only for certain variantsOnly with care
A rule per variant and shoe; the width a shoe gives and the customer's transport limit sit on different lines and need their own comparison.		Variant, shoes, width and the transport limit travel together and are checked on every call.
A 12-bucket by arm density tableOnly with workarounds
Forty-eight cells, each with its own density limit, have to be kept as rules or a lookup table and compared with a material density entered elsewhere; a "not recommended" cell is a different outcome again.		The table is part of the model; the bucket, arm and material density are compared on every call and the three outcomes (fine, outside the density, not recommended) are returned.
A stated digging depth that must match the boom and armOnly with care
A stated figure is a free-entry field; a rule can compare it with a computed depth, but someone has to write and maintain that comparison for every boom and arm.		The stated figure travels with the quote and is compared with the computed depth on every call.
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.

    
1The brochure lists the 5.70 m mono boom with 2.0, 2.4, 2.9 and 3.5 m arms, the 5.87 m 2-piece boom with 2.0, 2.4 and 2.9 m arms and the 8.5 m long reach boom with the 6.2 m arm only; the selected arm is not listed for the selected boom.
2The quote handles material of 1,900 kg/m3, but the bucket selection guide recommends this bucket and arm for material of 1,800 kg/m3 or less; a person should confirm the choice.
3The quote states a maximum digging depth of 6,900 mm, but the brochure gives 6,500 mm for the selected boom and arm.
4The quote states a maximum digging depth of 6,400 mm, but the brochure gives 6,500 mm for the selected boom and arm.
5The brochure lists the HX220A L with 600, 700, 800 and 900 mm triple grouser shoes, the HX220A L HW with those and a 700 mm double grouser shoe, and the HX220A LR with 800 mm shoes only; the selected shoe is not listed for the selected variant.
6With the selected track shoes the machine is 3,190 mm wide, which is wider than the 3,100 mm transport width limit on the quote.
7The quote handles material of 2,101 kg/m3, but the bucket selection guide recommends this bucket and arm for material of 2,100 kg/m3 or less; a person should confirm the choice.
8The quote handles material of 1,501 kg/m3, but the bucket selection guide recommends this bucket and arm for material of 1,500 kg/m3 or less; a person should confirm the choice.
9The bucket selection guide marks the selected bucket as not recommended for the selected boom and arm; a person should confirm the choice.
10The quote handles material of 1,201 kg/m3, but the bucket selection guide recommends this bucket and arm for material of 1,200 kg/m3 or less; a person should confirm the choice.

  

  

    
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. 2-piece boom order: A 2-piece boom order with a 3.5 m arm and 900 mm shoes under a 3,100 mm limit

    
The agent's request. Please quote an HX220A L excavator with the 5.87 m 2-piece boom and 3.5 m arm, 900 mm triple grouser shoes and the 0.92 m3 bucket, for material of 1,800 kg/m3. The machine has to stay within a 3,100 mm transport width. The quote states a maximum digging depth of 7,090 mm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Arm is not listed for this boom. The brochure lists the 5.70 m mono boom with 2.0, 2.4, 2.9 and 3.5 m arms, the 5.87 m 2-piece boom with 2.0, 2.4 and 2.9 m arms and the 8.5 m long reach boom with the 6.2 m arm only; the selected arm is not listed for the selected boom.
    • 
      
  • Machine is wider than the transport limit. With the selected track shoes the machine is 3,290 mm wide, which is wider than the 3,100 mm transport width limit on the quote.
    • 
    

    
2. 2-piece boom order: The agent resubmits after fixing the errors

    
The agent's request. Please quote an HX220A L excavator with the 5.87 m 2-piece boom and 2.9 m arm, 700 mm triple grouser shoes and the 0.92 m3 bucket, for material of 1,800 kg/m3. The machine has to stay within a 3,100 mm transport width. The quote states a maximum digging depth of 6,400 mm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Machine summary. Maximum digging depth 6,400 mm; overall width with the selected track shoes 3,090 mm.
    • 
    

    
3. Rock bucket on a mono boom: A mono boom order with the 3.5 m arm and the 1.23 m3 rock bucket

    
The agent's request. Please quote an HX220A L HW excavator with the 5.70 m mono boom and 3.5 m arm, 700 mm triple grouser shoes and the 1.23 m3 rock-heavy duty bucket, for material of 1,800 kg/m3. The machine has to stay within a 3,200 mm transport width. The quote states a maximum digging depth of 6,500 mm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated digging depth differs from the brochure. The quote states a maximum digging depth of 6,500 mm, but the brochure gives 7,090 mm for the selected boom and arm.
    • 
      
  • Bucket not recommended for this boom and arm. The bucket selection guide marks the selected bucket as not recommended for the selected boom and arm; a person should confirm the choice.
    • 
    

    
4. Rock bucket on a mono boom: The agent resubmits after fixing the errors

    
The agent's request. Please quote an HX220A L HW excavator with the 5.70 m mono boom and 2.9 m arm, 700 mm triple grouser shoes and the 1.23 m3 rock-heavy duty bucket, for material of 1,800 kg/m3. The machine has to stay within a 3,200 mm transport width. The quote states a maximum digging depth of 6,500 mm. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Material is denser than the bucket recommendation. The quote handles material of 1,800 kg/m3, but the bucket selection guide recommends this bucket and arm for material of 1,500 kg/m3 or less; a person should confirm the choice.
    • 
      
  • Machine summary. Maximum digging depth 6,500 mm; overall width with the selected track shoes 3,090 mm.
    • 
    

    
5. Rock bucket on a mono boom: The agent resubmits after fixing the errors

    
The agent's request. Please quote an HX220A L HW excavator with the 5.70 m mono boom and 2.9 m arm, 700 mm triple grouser shoes and the 0.87 m3 rock-heavy duty bucket, for material of 1,800 kg/m3. The machine has to stay within a 3,200 mm transport width. The quote states a maximum digging depth of 6,500 mm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Machine summary. Maximum digging depth 6,500 mm; overall width with the selected track shoes 3,090 mm.
    • 
    

    
6. Long reach boom: A long reach order with 600 mm shoes and a standard bucket

    
The agent's request. Please quote an HX220A LR excavator with the 8.5 m long reach boom and 6.2 m arm, 600 mm triple grouser shoes and the 0.92 m3 bucket, for material of 1,600 kg/m3. The machine has to stay within a 3,300 mm transport width. The quote states a maximum digging depth of 11,455 mm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Track shoe is not listed for this variant. The brochure lists the HX220A L with 600, 700, 800 and 900 mm triple grouser shoes, the HX220A L HW with those and a 700 mm double grouser shoe, and the HX220A LR with 800 mm shoes only; the selected shoe is not listed for the selected variant.
    • 
      
  • Bucket not recommended for this boom and arm. The bucket selection guide marks the selected bucket as not recommended for the selected boom and arm; a person should confirm the choice.
    • 
    

    
7. Long reach boom: The agent resubmits after fixing the errors

    
The agent's request. Please quote an HX220A LR excavator with the 8.5 m long reach boom and 6.2 m arm, 800 mm triple grouser shoes and the 0.51 m3 long reach bucket, for material of 1,600 kg/m3. The machine has to stay within a 3,300 mm transport width. The quote states a maximum digging depth of 11,455 mm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Machine summary. Maximum digging depth 11,455 mm; overall width with the selected track shoes 3,190 mm.
    • 
    

  

  

    
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 22-ton class crawler excavator with a boom, an arm, track shoes and a bucket. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the machine's published configuration tables and returns a verdict, every reason and the figures it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote an HX220A L excavator with the 5.87 m 2-piece boom and 3.5 m arm, 900 mm triple grouser shoes and the 0.92 m3 bucket. The machine has to stay within a 3,100 mm transport width. The rest of the request is on screen. The quote states a maximum digging depth of 7,090 mm.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with two findings, all in one answer. The brochure lists the 5.70 m mono boom with 2.0, 2.4, 2.9 and 3.5 m arms, the 5.87 m 2-piece boom with 2.0, 2.4 and 2.9 m arms and the 8.5 m long reach boom with the 6.2 m arm only; the selected arm is not listed for the selected boom. With the selected track shoes the machine is 3,290 mm wide, which is wider than the 3,100 mm transport width limit on the quote.
    6. 
      
  6. The validator returned two blocking findings 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. 
      
  7. What this shows: for arms listed only for certain booms, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the arm to 2.9 m, the track shoes to 700 mm triple grouser and the stated maximum digging depth to 6,400 mm.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. Both earlier findings are cleared, and the validator's figure matches the quote.
    13. 
      
  13. Two problems caught in one call, fixed in one pass, and a clean quote. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.
    14.