Works with the AI Agents you already use
decision scenario simulator
Manual spreadsheet modeling for business decisions is prone to error and lacks rigorous sensitivity testing.
$2.99
decision scenario simulator
Example session with this skill installed
Compare two shipping policies (Standard vs Express) for Q4. Objective is minimizing cost. Constraints: delivery < 5 days. Drivers: fuel price (low/high), volume. Fuel data in E1.
- Read your context and instructions
- Compiled the decision scenario simulator
The simulation compared "Standard Shipping" and "Express Shipping" against the cost minimization objective under two fuel price scenarios.
Decision Scenario Simulation — Logistics Dept, 2023-10-27
1. Scope, sources and assumptions
- Objective: Minimize total shipping cost while maintaining delivery < 5 days.
- Sources: E1 (Q4 Fuel Projections - Approved).
- Model Basis: Accounting Identity.
2. Scenario comparison
| Alternative | Scenario | Objective (Cost) | Feasible | Violated constraints |
|---|---|---|---|---|
| Standard | Base | 45,000 | True | None |
| Standard | High Fuel | 52,000 | True | None |
| Express | Base | 68,000 | True | None |
| Express | High Fuel | 74,000 | True | None |
Selection: Standard Shipping is the proposed alternative based on Lowest Cost.
3. Sensitivity and decision flips
| Driver | Alternative | Low | High | Swing | Rank |
|---|---|---|---|---|---|
| Fuel Price | Standard | 42,000 | 55,000 | 13,000 | 1 |
| Volume | Standard | 44,000 | 46,000 | 2,000 | 2 |
Decision Flip: No flip detected. Standard remains optimal even at High Fuel Price (+25%).
5. Assumptions ledger
| Driver | Role | Value/Range | Status | Source |
|---|---|---|---|---|
| Fuel Price | Input | [3.10, 4.20] | Validated | E1 |
| Volume | Input | 10,000 | Estimate | User |
7. Decision brief (draft)
The analysis proposes Standard Shipping as it meets the delivery constraint in all scenarios at a lower cost point.
- Observation 1: Express Shipping costs 51% more in the base scenario (Computed result).
Observation 2: If volume exceeds 15,000 units, the delivery constraint may be at risk (Analytical estimate — validation required).
Management decision required. This analysis supports, and does not replace, professional judgment and management's decision.
Next steps
- Validate the Q4 volume estimate with the sales team.
- Review the fuel price "High" threshold in E1.
- Confirm delivery lead times for Standard Shipping with the carrier.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual spreadsheet modeling for business decisions is prone to error and lacks rigorous sensitivity testing. This skill formalizes policy comparison by using an explicit driver model and a deterministic execution script to simulate outcomes across multiple scenarios.
What it does
- Multi-alternative comparison evaluates different policy options or business plans against a shared objective and set of constraints.
- Scenario simulation tests how alternatives perform under varying conditions, including best-case and worst-case envelopes.
- Sensitivity analysis performs one-at-a-time driver shocks to identify which variables have the largest impact on the outcome.
- Decision-flip detection pinpoint exactly where an uncertain driver value would cause a different alternative to become the optimal choice.
- Probabilistic modeling runs seeded Monte Carlo simulations to estimate the probability of meeting constraints and achieving objectives.
- Assumptions ledgering maintains a strict audit trail, separating validated facts from user estimates and cited evidence.
How it works
- Input mapping identifies the objective, constraints, drivers, and alternatives from your project data and registers sources as evidence.
- Model definition structures the logic into a
request.jsonfile following a strict schema, including causal basis and calculation steps. - Execution runs the deterministic
run.pyscript to perform all arithmetic, constraint checks, and rankings without manual intervention. - Validation checks the output status and warnings to ensure no unapproved data or personal records influenced the results.
- Brief generation produces a structured decision brief with tables for comparison, sensitivity, and the assumptions ledger.
Frameworks & tools
The core engine is a self-contained Python simulation script. It interfaces with JSON schemas for input/output validation and uses Markdown for structured reporting.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate arithmetic or fail to maintain consistent constraints across multiple "what-if" branches. This skill offloads all math to a deterministic script, ensures every conclusion is traceable to a specific source, and forces a disciplined distinction between facts and estimates.
Use cases
- Compare marketing budget allocations across different economic growth scenarios.
- Test the robustness of a supply chain strategy against volatile lead times.
- Identify the "flip point" for a build-vs-buy decision based on cost-per-unit uncertainty.
- Simulate the feasibility of a project timeline under various resource constraints.
Known limitations
This skill is for decision support only and does not replace human judgment. It excludes unapproved or personal data and cannot forecast time series or optimize continuous variables.
Does not support time-series forecasting or continuous optimization. Refuses personal-level records or unapproved data sources. Arithmetic is limited to the provided Python execution script.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 days ago