Examples
Examples
Try the starting example
- Tasks: name, minimum days, mode days, maximum days, prerequisites joined by | or none, quantile group
- A,1,2,3,none,independent B,2,3,4,A,independent
- Simulation trials: 20–10000
- 2000
- Unsigned 32-bit seed
- 42
- Project start date
- 2026-10-20
- Deadline date
- 2026-10-26
- Trials finishing by deadline (%)
- 95.8
- Median project duration (days)
- 5.014571
- 90th-percentile project duration (days)
- 5.74373
- 90th-percentile finish date
- 2026-10-26
- Monte Carlo standard error of completion proportion (percentage points)
- 0.448531
- Difference between half-run mean durations (days)
- 0.02833
Try another scenario
- Tasks: name, minimum days, mode days, maximum days, prerequisites joined by | or none, quantile group
- A,1,2,3,none,independent B,2,3,4,none,independent
- Simulation trials: 20–10000
- 2000
- Unsigned 32-bit seed
- 42
- Project start date
- 2026-10-20
- Deadline date
- 2026-10-23
- Trials finishing by deadline (%)
- 49.5
- Median project duration (days)
- 3.005454
- 90th-percentile project duration (days)
- 3.559044
- 90th-percentile finish date
- 2026-10-24
- Monte Carlo standard error of completion proportion (percentage points)
- 1.117978
- Difference between half-run mean durations (days)
- 0.00606
Calculation method
Calculation method
Trials finishing by deadline (%)
Sample task durations and compute each finish=max(parent finishes)+duration; compare total duration with deadline−start.
Median project duration (days)
Nearest-rank empirical median of critical-path completion durations.
90th-percentile project duration (days)
Nearest-rank empirical 90th percentile.
90th-percentile finish date
Start date + ceiling of the 90th-percentile elapsed duration, on a continuous calendar-day model.
Monte Carlo standard error of completion proportion (percentage points)
sqrt(p×(1−p)/trials)×100, a sampling diagnostic conditional on the model.
Difference between half-run mean durations (days)
Absolute difference between two half-run mean durations.
Symbols and units
- a
- Tasks: name, minimum days, mode days, maximum days, prerequisites joined by | or none, quantile group
- b
- Simulation trials: 20–10000
- c
- Unsigned 32-bit seed
- d
- Project start date
- e
- Deadline date
Use the units shown. A list keeps the order in which you enter its values. The symbol ^ means “raised to the power of”.
Assumptions & limits
Assumptions & limits
- A finite DAG of triangular task durations, with elapsed calendar days and unlimited resources. Shared quantile groups model only perfect positive quantile dependence. It does not infer working days, staffing, real delay probabilities or reliable completion guarantees.
Are these inputs private?
These calculations run in your browser. A shared link contains the values you choose to share. Only questions submitted to the separate AI finder are sent to OpenAI.
Further reading
NIST: triangular-input Monte Carlo example ↗
Background reading; this does not imply endorsement or independent review of SumFizz.