Works with the AI Agents you already use
decision tree and expected value analyst
Decision tree analysis with expected monetary value computation.
$2.99
decision tree and expected value analyst
Example session with this skill installed
Perform a decision tree analysis for a new product launch. Option A has a 60% chance of $500k and 40% of $100k. Option B has a 50% chance of $400k and 50% of $200k. Cost of launch is $50k.
- Read your context and instructions
- Compiled the decision tree
Analysis of the product launch decision tree is complete. I have calculated the Expected Monetary Value (EMV) for both options using backward induction, factoring in the $50,000 initial investment cost.
Decision Tree Analysis Results
| Metric | Value |
|---|---|
| Optimal EMV | $290,000.00 |
| Recommended Alternative | Option A (High Variance/High Return) |
| Optimal Path | Root > Option A > High Demand Outcome |
| Tree Depth | 2 |
| Alternatives Analyzed | 2 |
| Status | Completed |
Calculation Trace
| Node ID | Description | Probability | Value | EMV Contribution |
|---|---|---|---|---|
opt_a_high | Option A: High Success | 0.60 | $500,000 | $300,000 |
opt_a_low | Option A: Low Success | 0.40 | $100,000 | $40,000 |
| opt_a_total | Gross EMV (A) | - | - | $340,000 |
opt_b_high | Option B: High Success | 0.50 | $400,000 | $200,000 |
opt_b_low | Option B: Low Success | 0.50 | $200,000 | $100,000 |
| opt_b_total | Gross EMV (B) | - | - | $300,000 |
Analytical estimate — validation required: The results above are based on the provided 60/40 and 50/50 probability splits.
Management decision required: While Option A yields a higher EMV of $290,000 (after $50k cost) compared to Option B's $250,000, Option A carries a lower floor ($50,000 net). Final selection must align with organizational risk tolerance.
Next steps
- Validate the probability estimates (0.60 vs 0.50) with the marketing department.
- Review the $50,000 launch cost for potential overruns which may flip the optimal choice.
- Approve the recommended path for Option A if the organization is risk-neutral.
Connects securely to your tools. The creator never sees your data.
About this skill
Business decisions involving uncertainty often rely on gut feeling or flawed manual spreadsheets. This skill formalizes the process by constructing decision trees and executing backward induction to find the path of highest value.
What it does
- Expected Monetary Value (EMV) computation calculates the weighted average of all possible outcomes for every branch.
- Optimal path identification traces the sequence of decisions and outcomes that maximize potential returns.
- Alternative flagging highlights dispreferred options that fall below the optimal EMV.
- Node analysis evaluates both decision nodes (choices) and chance nodes (probabilistic events) systematically.
- Validation marking flags analytical estimates and information gaps where organizational data is missing.
How it works
- Define the tree structure by providing a JSON object containing decision nodes and chance nodes with their associated probabilities and payoffs.
- Execute the analysis script using the provided Python driver to process the tree logic and calculate values.
- Review the calculation trace to verify the deterministic formulas and rounding conventions used for each node.
- Identify the recommendation based on the highest EMV while reviewing dispreferred alternatives and warnings.
Frameworks & tools
The core logic is driven by a Python 3 CLI engine (scripts/run.py). It utilizes a schema-driven approach for inputs and outputs, ensuring strict data validation and deterministic decimal arithmetic for financial precision.
Why this beats prompting it yourself
Prompting an LLM to calculate EMV often results in "hallucinated math" or inconsistent rounding across complex branches. This skill offloads the heavy lifting to a specialized execution script, ensuring the math is always deterministic and the pathing logic follows standard operations research methods.
Use cases
- Evaluate capital investment options by weighing project costs against market success probabilities.
- Analyze litigation strategies by comparing settlement offers to expected trial outcomes.
- Optimize product launch timings based on seasonal demand forecasts and competitor response scenarios.
- Quantify risk exposure in supply chain transitions with multiple failure points.
Known limitations
Does not support stochastic programming with pre-uncertainty recourse or complex network optimization. Probabilities must be manually provided or clarified via prompts if missing from the source.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Requires structured JSON input for tree nodes. No support for stochastic programming or network flow optimization. Computations are deterministic based on provided probabilities.
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 buying a skill.
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