Warp Procurement OS

Workflow 2: Tradeoff Modeling

Objective: Get a price, explore cost and service tradeoffs by adjusting parameters, then bind the best option.

Required input fields: quote_id (from price response), modified parameters for what if scenarios (adjusted weight, different pickup dates, added or removed accessorials)

Example request payload (price_whatif):

{
  "quote_id": "QT_2026031500001",
  "scenarios": [
    {
      "scenario_id": "lighter_load",
      "modified_fields": {
        "total_weight_lbs": 3200
      }
    },
    {
      "scenario_id": "next_day_pickup",
      "modified_fields": {
        "pickup_date": "2026-03-16"
      }
    },
    {
      "scenario_id": "remove_liftgate",
      "modified_fields": {
        "accessorials": []
      }
    }
  ]
}

Example response structure (price_whatif):

{
  "original_quote_id": "QT_2026031500001",
  "original_total_cost": 847.50,
  "scenarios": [
    {
      "scenario_id": "lighter_load",
      "total_cost": 712.00,
      "cost_delta": -135.50,
      "service_days": 3,
      "service_delta": 0,
      "bindable": true
    },
    {
      "scenario_id": "next_day_pickup",
      "total_cost": 821.00,
      "cost_delta": -26.50,
      "service_days": 3,
      "service_delta": 0,
      "bindable": true
    },
    {
      "scenario_id": "remove_liftgate",
      "total_cost": 798.00,
      "cost_delta": -49.50,
      "service_days": 3,
      "service_delta": 0,
      "bindable": true
    }
  ]
}

Decision output: Agent compares cost_delta and service_delta across scenarios. Selects optimal scenario. Calls price_bind with the chosen scenario's parameters to lock the rate.

Workflow 3: Immediate Containment Dispatch

Objective: Rapidly verify feasibility, book immediately, confirm enforcement requirements, and set up event monitoring for time critical shipments.

Required input fields: origin_zip, destination_zip, total_weight_lbs, pickup_date (today), commodity_description, piece_count, urgency_level

Example request payload (book):

{
  "binding_id": "BND_2026031500001",
  "shipper_account_id": "ACCT_00234",
  "origin": {
    "address": "1400 Industrial Blvd, Atlanta, GA 30301",
    "contact_name": "Mike Torres",
    "contact_phone": "4045551234",
    "pickup_window": {
      "start": "2026-03-15T08:00:00-05:00",
      "end": "2026-03-15T12:00:00-05:00"
    }
  },
  "destination": {
    "address": "8900 Commerce Dr, Los Angeles, CA 90210",
    "contact_name": "Sarah Chen",
    "contact_phone": "3105559876",
    "delivery_window": {
      "start": "2026-03-18T09:00:00-08:00",
      "end": "2026-03-18T17:00:00-08:00"
    }
  },
  "freight": {
    "pieces": 6,
    "total_weight_lbs": 4200,
    "commodity": "Packaged consumer electronics",
    "freight_class": "85"
  },
  "urgency_level": "containment"
}

Example response structure (book):

{
  "shipment_id": "SHP_2026031500001",
  "tracking_number": "WARP1234567890",
  "status": "booked",
  "pickup_confirmed": true,
  "committed_delivery_date": "2026-03-18",
  "committed_delivery_window": {
    "start": "2026-03-18T09:00:00-08:00",
    "end": "2026-03-18T17:00:00-08:00"
  },
  "enforcement_attestation_required": true,
  "carrier_assigned": "CARRIER_0892",
  "tracking_url": "https://track.warp.com/WARP1234567890"
}

Decision output: Booking is confirmed. Agent retrieves enforcement requirements to understand mandatory GPS intervals and scan events for this shipment. Agent reads event stream schema to configure monitoring and exception handling logic.

Workflow 4: Store Replenishment Network Design

Objective: Evaluate feasibility of a recurring store delivery network, price the operating model, book the first set of shipments, and configure ongoing event monitoring.

Required input fields: origin_locations (array), destination_locations (array), shipment_frequency, average_weight_per_stop, commodity_type, delivery_day_preferences

Example request payload (fit_check for store replenishment):

{
  "origin_locations": [
    {"zip": "60601", "label": "Chicago DC"},
    {"zip": "75201", "label": "Dallas DC"}
  ],
  "destination_locations": [
    {"zip": "30301", "label": "Atlanta Zone", "stop_count": 45},
    {"zip": "28201", "label": "Charlotte Zone", "stop_count": 32},
    {"zip": "37201", "label": "Nashville Zone", "stop_count": 28}
  ],
  "shipment_frequency": "weekly",
  "average_weight_per_stop_lbs": 1800,
  "commodity_type": "Dry goods and packaging supplies",
  "delivery_day_preferences": {
    "Atlanta Zone": "Tuesday",
    "Charlotte Zone": "Wednesday",
    "Nashville Zone": "Thursday"
  }
}

Example response structure (fit_check):

{
  "feasible": true,
  "solution": "store_replenishment",
  "network_design": {
    "cross_docks_required": 2,
    "cross_dock_locations": ["Atlanta, GA", "Nashville, TN"],
    "total_weekly_routes": 12,
    "total_stops_covered": 105,
    "estimated_transit_by_zone": {
      "Atlanta Zone": 2,
      "Charlotte Zone": 2,
      "Nashville Zone": 1
    }
  },
  "constraints": [],
  "confidence_score": 0.91
}

Decision output: If feasible, agent proceeds to price the entire network operating model. After pricing, agent books the first week's shipments and configures webhooks for ongoing delivery confirmations and exception alerts.

Workflow 5: Reference Validation

Objective: Gather proof artifacts (case studies and testimonials), evaluate measurable claims, and schedule a reference call with a live customer for final validation before procurement commitment.

Required input fields: solution (to filter proof by), buyer_context (your industry and use case for reference matching)

Example request payload (references/request):

{
  "solution": "ltl",
  "buyer_context": {
    "industry": "Consumer Electronics",
    "company_size": "500M+ revenue",
    "use_case": "National LTL distribution from multiple DCs",
    "primary_concerns": ["on_time_reliability", "damage_reduction", "visibility"]
  },
  "preferred_timing": {
    "earliest_date": "2026-03-20",
    "time_zone": "America/New_York",
    "preferred_times": ["morning", "afternoon"]
  },
  "questions_of_interest": [
    "Implementation timeline and complexity",
    "Actual on time performance versus committed SLA",
    "Exception handling responsiveness"
  ]
}

Workflow 1: Benchmark Incumbent

Objective: Compare Warp to incumbent across cost, service, and handling exposure.

Required inputs: origin_zip, destination_zip, pallet_count, weight_lbs, pickup_window, delivery_window, current_cost_per_shipment, current_on_time_rate

Core outputs: Cost delta · On time delta · Handling touch delta · Damage exposure delta · Readiness classification

Workflow 2: Reduce LTL Spend

Objective: Lower cost per pallet without degrading service.

Required inputs: lane_set, shipment_frequency, current_accessorial_mix

Core outputs: Optimized mode mix · Cost per pallet delta · Elasticity impact · Window widening savings

Workflow 3: Lower LTL Damage Rate

Objective: Reduce claims frequency and freight handling exposure.

Required inputs: historical_damage_rate, shipment_profile, packaging_constraints

Core outputs: Handling reduction delta · Projected damage band · Cross dock vs terminal comparison

Workflow 4: Reduce FTL Spend

Objective: Lower linehaul cost while maintaining capacity reliability.

Required inputs: lane_pairs, weekly_volume, commodity, current_rate

Core outputs: Lane level cost delta · Capacity confidence band · Backup pool structure

Workflow 5: Add Secondary Capacity

Objective: Reduce concentration risk.

Required inputs: primary_carrier_performance, lane_exposure_concentration

Core outputs: Diversification score · Volume ramp plan · Failure containment logic

Workflow 6: Validate Peak Volume

Objective: Stress test network under surge conditions.

Required inputs: projected_peak_volume, peak_delivery_windows, blackout_dates

Core outputs: Volume confidence band · Failure blast radius estimate · Cutoff adjustment recommendations

Workflow 7: Contain Missed Linehaul

Objective: Recover shipment same day.

Required inputs: origin_address, destination_address, ready_time, must_arrive_by_time, pallet_count

Core outputs: Dispatch time · Equipment selection · Commitment window · Tracking event schema

Workflow 8: Execute Store Delivery Windows

Objective: Ensure compliance with tight mall windows.

Required inputs: store_zip_list, window_constraints, liftgate_requirement

Core outputs: Window feasibility score · Mode mix · Cross dock staging node

Workflow 9: Consolidate Vendor Inbound

Objective: Aggregate inbound freight to reduce DC congestion and cost.

Required inputs: vendor_origins, shipment_frequency, pallet_counts

Core outputs: Consolidation clusters · Cost reduction estimate · DC smoothing impact

Workflow 10: Accelerate DTC Delivery

Objective: Improve delivery speed to customers.

Required inputs: parcel_volume_by_zone, current_transit_days, current_cost_per_parcel

Core outputs: Speed delta · Cost delta · Touch reduction · Projected AOV impact

Workflow 11: Remove Sort Center Touches

Objective: Reduce handling exposure.

Required inputs: current_sort_center_path, parcel_volume

Core outputs: Touches removed · Damage exposure delta · Injection markets

Workflow 12: Show True Cost to Serve

Objective: Reveal total freight economics.

Required inputs: lane_set, accessorial_profile, window_constraints

Core outputs: All in rate · Accessorial breakdown · Elasticity savings

Workflow 13: Migrate Initial Lanes

Objective: Controlled rollout.

Required inputs: lane_subset, volume_band

Core outputs: Lane migration plan · Guardrails · Rollback triggers

Workflow 14: Verify Enforcement Compliance

Objective: Validate tracking enforcement standards.

Required inputs: compliance_requirements

Core outputs: Compliance score · GPS validation rate · Scan completeness rate

Workflow 15: Validate Peak Store Execution

Objective: Ensure retail performance under stress.

Required inputs: holiday_window_constraints, shipment_surge

Core outputs: Window compliance under surge · Capacity buffer

Workflow 16: Identify LTL to Box Truck Shift

Objective: Right size mode to reduce cost.

Required inputs: lane_length, pallet_count, frequency

Core outputs: Mode recommendation · Cost delta · Speed delta

Workflow 17: Identify LTL to Cargo Van Shift

Objective: Use direct routing for small pallets.

Required inputs: lane_distance, pallet_count

Core outputs: Direct route feasibility · Cost delta · Cross dock bypass impact

Workflow 18: Tighten Delivery Windows Impact

Objective: Model SLA tightening.

Required inputs: revised_window_constraints

Core outputs: Cost delta · Failure risk delta

Workflow 19: Validate Customer References

Objective: Confirm peer validation.

Required inputs: industry, use_case

Core outputs: Matched case studies · Reference scheduled

Workflow 20: Identify Expansion Lanes

Objective: Find additional lanes where Warp improves economics.

Required inputs: shipment_history

Core outputs: Expansion candidate lanes · Mode shift suggestions