Skip to main content

​
Overview

AMP is an AI assistant embedded into Scenario Builder. It has access to specialized tools that allow it to interact with your scenarios: analyzing inputs, debugging infeasible runs, and helping you edit scenario parameters.

​
Key Features

Contextual Analysis

AMP has direct access to your scenario’s configuration. It can sanity-check your data and provide reasoned analysis of your results.
Try asking: “Why is renewable curtailment high in the South?”

Infeasibility Analysis

When a model run fails or is deemed infeasible, AMP analyzes your inputs for logical conflicts and suggests specific solutions.
Try asking: “Why is this scenario infeasible?”

Documentation Retrieval

AMP has access to the full Scenario Builder documentation and can guide you through platform features and methodologies.
Try asking: “Where does Scenario Builder’s Japan dataset come from?”

Scenario Editing

AMP can help you turn high-level research questions into the specific data inputs needed to generate a scenario.
Try asking: “Help me model more aggressive learning rates for PV.”

​
User Guide

​
Setting Context

To get the best results, ensure AMP is looking at the right data. Load a scenario into context in one of two ways:
1

Load your scenario

Navigate to the specific Scenario page or Results page within your workspace.
2

Use @ mentions

From anywhere in the app, click the @ button in the chat bar to select a specific scenario from your project.

​
Managing Context

AMP’s performance may degrade if a single conversation becomes too long or if you switch between multiple different scenarios within one chat session.
Best Practice: Start a new chat session whenever you change topic or switch to a different scenario.

​
Limitations & Constraints

It is important to understand how AMP interacts with your data to interpret its answers correctly.
AMP’s general world knowledge is cut off as of January 2025. However, it can retrieve current data from your specific scenario context or the up-to-date Scenario Builder documentation.
Like all Large Language Models (LLMs), AMP can make mistakes with complex mental arithmetic.
  • Recommendation: Use AMP to set up the model inputs, and let Scenario Builder’s engine perform the calculation. Always verify precise numerical figures in the results table.
AMP sees your scenario data at reduced numerical precision (fewer decimal places) to save context space. For most analysis this is sufficient, but you may notice small rounding discrepancies compared to your raw data exports.
For performance reasons, AMP does not read every data point in hourly model results. Instead, it analyzes aggregated annual statistics and a sample of representative days.
AMP is not yet able to analyse or edit constraints using technology or node groups.
AI ReliabilityWe use advanced prompting and retrieval-augmented generation (RAG) to ground AMP in your data, but AI models can occasionally hallucinate.
  • Verification: Always verify critical model inputs and results in the Scenario Builder tables and charts.
  • Edits: Review proposed scenario edits before applying them to ensure they match your intent.
  • Advice: AMP provides modelling assistance, not financial or investment advice.

​
Usage Limits

AMP is subject to daily token usage limits. Users running heavy queries against very large scenarios may reach these limits. Please contact support@transitionzero.org if you require increased usage limits for enterprise projects.

​
Data Privacy & Security

We take the security of your proprietary modelling data seriously.
  • Data Isolation: Your scenario data is sent to the LLM (Google Vertex AI) only when you actively use the assistant with a scenario loaded.
  • No Training on User Data: Neither TransitionZero nor our LLM providers use your private scenario data or chat history to train public AI models.
  • Authentication: All AI requests are protected by your standard TransitionZero user session.
  • Cloud Security: The backend operates within a secure, enterprise-grade Google Cloud environment.
For more details, see the Data Privacy FAQs.