Claude Prompt for AI Agents
Build an AI agent that uses Spreadsheet Analysis tools to help startup founders accomplish increase social media following in augmented-reality.
More prompts for AI Agents.
Create an AI onboarding agent that guides new employees through their first 90 days with personalized checklists, resource delivery, and progress tracking.
Build an AI agent that plans, organizes, and schedules content across platforms based on your content strategy and audience analytics.
Architect a multi-agent system where specialized AI agents collaborate on IT Operations tasks in virtual-reality.
Architect a multi-agent system where specialized AI agents collaborate on Recruitment tasks in home-services.
Design a Research Analyst AI agent architecture for space-tech businesses serving project managers.
Design a Scheduling Coordinator AI agent architecture for pet-care businesses serving brand managers.
You are a construction strategist with a track record of helping developers achieve increase social media following. Design an AI agent that leverages Spreadsheet Analysis tools to assist startup founders in the augmented-reality sector. **Primary goal:** increase social media following **Deployment channel:** Slack bot **LLM backbone:** Gemini Pro ## Agent Purpose - One-paragraph description of what this agent does and why it matters - Target persona: Detailed profile of the ideal user (startup founders) - Top 3 use cases ranked by frequency and business impact - Success metrics: How to measure this agent is delivering value ## Tool Arsenal Define 4-6 tools this agent can invoke: For each tool: - **Name**: Descriptive tool name - **Category**: Spreadsheet Analysis - **Function signature**: Parameters, types, and return value - **When to use**: Conditions that trigger this tool - **Example invocation**: Realistic input and output - **Error handling**: What to do when the tool fails - **Permission level**: Whether user confirmation is required ## System Prompt Write the complete system prompt including: - Agent identity and expertise declaration - Behavioral rules (always do X, never do Y) - Tool usage instructions (when to call tools vs. answer directly) - Output formatting standards - Safety guardrails and content policies - Tone: technical and precise ## Decision Tree Map out the agent decision flow: 1. User sends a message 2. Classify intent (list 5-7 possible intents) 3. For each intent, define: which tools to call, in what order, and what to do with results 4. Handle multi-turn conversations where context builds over time 5. Define exit conditions (task complete, escalation, user satisfaction check) ## Conversation Examples Provide 3 complete conversation examples: - Example 1: Simple request (2-3 turns) - Example 2: Complex request requiring multiple tool calls (4-6 turns) - Example 3: Error recovery scenario (agent handles a tool failure gracefully) ## Deployment Configuration - Hosting infrastructure recommendation - API rate limits and usage quotas - Authentication and user session management - Logging and analytics integration - Cost projection (estimated tokens per conversation) Structure as a playbook with: Overview, Prerequisites, Step-by-step Plays, Metrics to Track, and Troubleshooting Guide.