Operating model simulator
Generated 2026-07-14 19:11 · engine-backed interactive report · QA PASS · slider-formula max error 7.7 percentage points vs held-out engine runs
Plain-language legend - what the abbreviations mean (nothing here assumes prior knowledge)
How the operating model can evolve - pick a stage to explore it below
Each stage keeps the same work and the same facts - only the way of working changes. Arrows show the direction of travel. Green delta = better than today, red = worse.
What this stage looks like - the org chart and the process it runs
The three numbers that matter - they recolour live as you move the levers
Ramps the workload up and shows exactly where each KPI turns red. Watch the tiles.
KPI = Key Performance Indicator. Green = comfortable, amber = getting tight, red = breached. Each tile names the point where it turns red.
Tune the world - untick a lever to switch it off; every chart recomputes instantly
Drag a slider or type an exact number. Untick a lever's box to hold it at "no change" and take it out of play. Dots on the lever charts further down are real engine runs; values between them are estimates (QA-measured error quoted at the top).
The stages, at your current settings
Shaded band = the realistic best-to-worst spread across re-runs with different luck (P10 to P90); the line is the middle (P50). Level-adjusted to your sliders (approximation, QA-measured).
Which levers matter most
Each lever, one at a time
Green zone = above your target. Dashed red line = where you are now. Each chart ends with the takeaway in plain terms and the point where it breaches.
What could break this - the risk tree
The story, in plain English
Assumptions ledger
| Assumption | Status | Value |
|---|---|---|
| Arrival volumes, intraday and weekly shapes | asked / stated in spec | orgspec baseline |
| Handle times and rework rates per step | asked / stated in spec | orgspec steps |
| Agent throughput and error rate | user estimate | orgspec agent_pools |
| Capacity tile (busiest-team load) scales base utilisation by the load factor | stated-default (directional estimate) | dashboard |
| Agents process in parallel at fixed per-item time | stated-default (simplification) | engine |
| Human service may finish after shift end (overtime) | stated-default (simplification) | engine |
| Max one rework per step per item | stated-default (simplification) | engine |
| Costs accrue per rostered weekday FTE; agent items flat cost | stated-default | engine |
| Sliders combine via an engine-measured LOAD curve; stress levers via load equivalence | QA-validated approximation | max err 7.7 SLA pp |
| Trajectory band level-shifted from engine base runs | approximation | fan chart note |
Quality checks - every check, individually
Verdict: PASS - 49 individual checks: 42 green, 7 amber, 0 red. Green = comfortably inside tolerance, amber = inside but close, red blocks release. Slider-formula max error 7.7 SLA points at held-out engine validation runs.
| What was checked | Owning agent | Input | Method | Result observed | Threshold | |
|---|---|---|---|---|---|---|
| ● green | Replication count - baseline | Simulation Runner | engine configuration | count seeded replications of the base run | 10 replications, distinct seeds by construction | >= 5 replications |
| ● amber | Flow conservation - baseline | Calculation QA | engine completions (run r4242x10-91407796) vs orgspec arrival rates | Little's-law style: completed items must equal spec-implied arrivals | engine 11215 vs analytical 12026 (6.7% apart) | <= 10% |
| ● green | Capacity math - baseline / Intake (APAC) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 79% vs analytical 80% (diff 1%) | <= 18% |
| ● green | Capacity math - baseline / Repair (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 88% vs analytical 89% (diff 1%) | <= 18% |
| ● green | Capacity math - baseline / Investigations (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 94% vs analytical 95% (diff 1%) | <= 18% |
| ● green | Capacity math - baseline / Verification (AMER) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 78% vs analytical 80% (diff 1%) | <= 18% |
| ● green | Queueing law: load raises delay - baseline | Calculation QA | volume sweep turnaround (run r4242x10-91407796) | Operational Research (queueing theory): turnaround must rise, not fall, as offered load increases - Kingman / Pollaczek-Khinchine delay grows with utilisation | largest downward reversal 0% of peak turnaround | <= 25% |
| ● green | Surrogate fidelity - baseline @ {'volume_mult': 1.15, 'fte_mult': 1.15} | Visualizer | held-out engine run r4242x8-92386084 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 40.8% vs engine 41.6% (error 0.8 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - baseline @ {'volume_mult': 1.3, 'handle_mult': 1.15} | Visualizer | held-out engine run r4242x8-89119459 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 0.8% vs engine 1.0% (error 0.2 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - baseline @ {'volume_mult': 0.85, 'fte_mult': 0.85} | Visualizer | held-out engine run r4242x8-62696133 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 40.8% vs engine 40.4% (error 0.4 SLA points) | <= 8.0 SLA points |
| ● amber | Surrogate fidelity - baseline @ {'volume_mult': 1.15, 'error_mult': 1.5} | Visualizer | held-out engine run r4242x8-47853680 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 24.9% vs engine 18.5% (error 6.5 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - baseline @ {'volume_mult': 1.1, 'geo_outage_days': 3} | Visualizer | held-out engine run r4242x8-4329489 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 7.8% vs engine 9.3% (error 1.5 SLA points) | <= 8.0 SLA points |
| ● green | Replication count - two_hub | Simulation Runner | engine configuration | count seeded replications of the base run | 10 replications, distinct seeds by construction | >= 5 replications |
| ● amber | Flow conservation - two_hub | Calculation QA | engine completions (run r4242x10-91407796) vs orgspec arrival rates | Little's-law style: completed items must equal spec-implied arrivals | engine 11208 vs analytical 12026 (6.8% apart) | <= 10% |
| ● green | Capacity math - two_hub / Intake (APAC) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 79% vs analytical 80% (diff 1%) | <= 18% |
| ● green | Capacity math - two_hub / Repair (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 88% vs analytical 89% (diff 1%) | <= 18% |
| ● green | Capacity math - two_hub / Investigations (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 94% vs analytical 95% (diff 2%) | <= 18% |
| ● green | Capacity math - two_hub / Verification (moved to EMEA hub) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 58% vs analytical 59% (diff 1%) | <= 18% |
| ● green | Queueing law: load raises delay - two_hub | Calculation QA | volume sweep turnaround (run r4242x10-91407796) | Operational Research (queueing theory): turnaround must rise, not fall, as offered load increases - Kingman / Pollaczek-Khinchine delay grows with utilisation | largest downward reversal 0% of peak turnaround | <= 25% |
| ● green | Surrogate fidelity - two_hub @ {'volume_mult': 1.15, 'fte_mult': 1.15} | Visualizer | held-out engine run r4242x8-92386084 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 77.0% vs engine 77.0% (error 0.0 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - two_hub @ {'volume_mult': 1.3, 'handle_mult': 1.15} | Visualizer | held-out engine run r4242x8-89119459 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 1.1% vs engine 0.9% (error 0.2 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - two_hub @ {'volume_mult': 0.85, 'fte_mult': 0.85} | Visualizer | held-out engine run r4242x8-62696133 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 77.0% vs engine 76.8% (error 0.1 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - two_hub @ {'volume_mult': 1.15, 'error_mult': 1.5} | Visualizer | held-out engine run r4242x8-47853680 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 45.2% vs engine 41.8% (error 3.3 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - two_hub @ {'volume_mult': 1.1, 'geo_outage_days': 3} | Visualizer | held-out engine run r4242x8-4329489 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 14.0% vs engine 17.2% (error 3.2 SLA points) | <= 8.0 SLA points |
| ● green | Replication count - agent_intake | Simulation Runner | engine configuration | count seeded replications of the base run | 10 replications, distinct seeds by construction | >= 5 replications |
| ● amber | Flow conservation - agent_intake | Calculation QA | engine completions (run r4242x10-91407796) vs orgspec arrival rates | Little's-law style: completed items must equal spec-implied arrivals | engine 11415 vs analytical 12026 (5.1% apart) | <= 10% |
| ● green | Capacity math - agent_intake / Intake (APAC, exceptions) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 55% vs analytical 56% (diff 1%) | <= 18% |
| ● green | Capacity math - agent_intake / Repair (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 90% vs analytical 89% (diff 0%) | <= 18% |
| ● green | Capacity math - agent_intake / Investigations (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 95% vs analytical 95% (diff 0%) | <= 18% |
| ● green | Capacity math - agent_intake / Verification (AMER) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 79% vs analytical 80% (diff 0%) | <= 18% |
| ● green | Queueing law: load raises delay - agent_intake | Calculation QA | volume sweep turnaround (run r4242x10-91407796) | Operational Research (queueing theory): turnaround must rise, not fall, as offered load increases - Kingman / Pollaczek-Khinchine delay grows with utilisation | largest downward reversal 0% of peak turnaround | <= 25% |
| ● green | Surrogate fidelity - agent_intake @ {'volume_mult': 1.15, 'fte_mult': 1.15} | Visualizer | held-out engine run r4242x8-92386084 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 67.6% vs engine 68.1% (error 0.5 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - agent_intake @ {'volume_mult': 1.3, 'handle_mult': 1.15} | Visualizer | held-out engine run r4242x8-89119459 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 2.0% vs engine 2.0% (error 0.0 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - agent_intake @ {'volume_mult': 0.85, 'fte_mult': 0.85} | Visualizer | held-out engine run r4242x8-62696133 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 67.6% vs engine 67.1% (error 0.5 SLA points) | <= 8.0 SLA points |
| ● amber | Surrogate fidelity - agent_intake @ {'volume_mult': 1.15, 'error_mult': 1.5} | Visualizer | held-out engine run r4242x8-47853680 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 43.8% vs engine 36.5% (error 7.3 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - agent_intake @ {'volume_mult': 1.1, 'geo_outage_days': 3} | Visualizer | held-out engine run r4242x8-4329489 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 43.5% vs engine 41.4% (error 2.0 SLA points) | <= 8.0 SLA points |
| ● green | Replication count - ai_verify | Simulation Runner | engine configuration | count seeded replications of the base run | 10 replications, distinct seeds by construction | >= 5 replications |
| ● amber | Flow conservation - ai_verify | Calculation QA | engine completions (run r4242x10-91407796) vs orgspec arrival rates | Little's-law style: completed items must equal spec-implied arrivals | engine 11212 vs analytical 12026 (6.8% apart) | <= 10% |
| ● green | Capacity math - ai_verify / Intake (APAC) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 79% vs analytical 80% (diff 1%) | <= 18% |
| ● green | Capacity math - ai_verify / Repair (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 88% vs analytical 89% (diff 1%) | <= 18% |
| ● green | Capacity math - ai_verify / Investigations (EMEA) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 94% vs analytical 95% (diff 1%) | <= 18% |
| ● green | Capacity math - ai_verify / Verification exceptions desk (AMER) | Calculation QA | engine utilization (run r4242x10-91407796) vs orgspec demand math | independent re-derivation: demand hours / supply hours from the spec | engine 12% vs analytical 12% (diff 0%) | <= 18% |
| ● green | Queueing law: load raises delay - ai_verify | Calculation QA | volume sweep turnaround (run r4242x10-91407796) | Operational Research (queueing theory): turnaround must rise, not fall, as offered load increases - Kingman / Pollaczek-Khinchine delay grows with utilisation | largest downward reversal 0% of peak turnaround | <= 25% |
| ● green | Surrogate fidelity - ai_verify @ {'volume_mult': 1.15, 'fte_mult': 1.15} | Visualizer | held-out engine run r4242x8-92386084 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 75.1% vs engine 75.2% (error 0.1 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - ai_verify @ {'volume_mult': 1.3, 'handle_mult': 1.15} | Visualizer | held-out engine run r4242x8-89119459 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 1.1% vs engine 0.9% (error 0.1 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - ai_verify @ {'volume_mult': 0.85, 'fte_mult': 0.85} | Visualizer | held-out engine run r4242x8-62696133 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 75.1% vs engine 75.2% (error 0.1 SLA points) | <= 8.0 SLA points |
| ● green | Surrogate fidelity - ai_verify @ {'volume_mult': 1.15, 'error_mult': 1.5} | Visualizer | held-out engine run r4242x8-47853680 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 36.7% vs engine 36.5% (error 0.2 SLA points) | <= 8.0 SLA points |
| ● amber | Surrogate fidelity - ai_verify @ {'volume_mult': 1.1, 'geo_outage_days': 3} | Visualizer | held-out engine run r4242x8-4329489 (never used to fit the surrogate) | dashboard slider formula (load equivalence) vs a real engine run at the same settings | slider formula 61.4% vs engine 69.2% (error 7.7 SLA points) | <= 8.0 SLA points |
| ● green | Data hygiene scrub | Calculation QA | every .md/.yaml/.html file in the repo | regex scan for PII patterns (emails, phone numbers) and a blocklist of real institution names | no findings | zero findings |
Settings used for this export
- prints the report exactly as tuned (choose "Save as PDF").