Back to Prompt Library
planning

Initial Agent Setup and Tool Definition

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

Linked challenge: AI-Powered Enterprise Content Review Agent

Format
Text-first
Lines
1
Sections
1
Linked challenge
AI-Powered Enterprise Content Review Agent

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Using the OpenAI Agents SDK, define an agent named 'ContentReviewBot'. Create two custom tools: 'analyze_content(content_text: str, review_criteria: list[str]) -> dict' that simulates content analysis using Claude 4 Sonnet (you can mock this with a detailed response for now), and 'initiate_payment(content_id: str, amount: float) -> str' that simulates a Crossmint payment initiation. Define the agent's initial instructions to focus on content compliance and monetization inquiries. Provide the Python code snippet for agent and tool initialization.

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.