Back to Prompt Library
planning

Multi-Step Analysis and Reporting Logic

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: AI-Powered Productivity Agent for Enterprise Cost Optimization

Format
Text-first
Lines
5
Sections
1
Linked challenge
AI-Powered Productivity Agent for Enterprise Cost Optimization

Prompt source

Original prompt text with formatting preserved for inspection.

5 lines
1 sections
No variables
3 checklist items
Outline the Mastra AI agent's internal logic for performing a multi-step cost analysis. This should involve:
1. Using the `rag_retriever` to gather background information.
2. Using `phi3_analyzer` to process simulated raw data and identify patterns/inefficiencies.
3. Synthesizing these findings into a concise report.
Provide pseudo-code or a detailed flow diagram within the Mastra AI agent's `onMessage` or `plan` method to illustrate this process, demonstrating how the agent would chain tool calls and internal reasoning.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.