Generative & Agentic AI on AWS

AnyCompany Leader — Workshop

2 days · From prompt mastery to your first AI agent · No coding required

Workshop Journey

🎯

Day 1: Prompt Mastery & Smart Model Selection

Choose the right model, write better prompts, verify AI outputs. Ends with a Prompt Competition judged by AI.

🤖

Day 2: Agentic AI — From Concept to Your First Agent

Understand autonomous agents, then build one for your team's process in Claude Cowork. Ends with Agent Design Showcase.

Who Is This For?

👔

Finance Leadership

CFO Office, Heads of Finance CoE, Directors evaluating AI for their teams

👥

People Managers

Managers sponsoring AI adoption, deciding where to invest team time

💼

Finance Operations

Team members using Claude/Gemini daily who want to use AI more effectively

🚀

Anyone Curious

Anyone who wants to understand AI agents without needing to code

What You'll Take Home

📝

Prompt Template

Reusable template with persona, Chain-of-Thought, structured output

🤖

Working Agent Project

Claude Cowork project with steering rules, skill, and quality check

📊

Model Selection Guide

Decision framework: which model for which task + cost comparison

Governance Checklist

How to verify and trust AI outputs for finance use cases

📋

Agentic Cheat Sheet

One-page reference: steering → skills → hooks → MCP

🗺️

Agent Design Canvas

Strategic one-page plan for your next automation

Prerequisites

  • No coding experience required
  • Basic familiarity with AI chat tools (Claude, Gemini, or similar)
  • Bring a laptop with access to Claude
⚠️ Security Notice: Do not include any confidential information, personally identifiable information (PII), or sensitive data in your prompts. All sample data in this workshop is synthetic.

Day 1: Prompt Mastery & Smart Model Selection

Use AI better today — choose the right model, write better prompts, verify the output.

Topics Covered

• How LLMs work (next-token prediction)
• The creativity dial: Temperature, Top-k, Top-p
• Model selection: cost vs quality vs speed
• The 1-cent-or-1-dollar model choice
• When NOT to use AI (Python vs LLM)
• Governance: verifying AI outputs
• PII risks & Bedrock Guardrails
• Hallucination detection strategies
• The 4 pillars of effective prompts
• Chain-of-Thought & Self-Consistency
• Persona prompting & structured outputs
• RAG: grounding AI in your documents

⚡ Interactive Explainers — How AI Works Under the Hood

🏆 Day 1 Activities

🏆 Day 1 Exercises

Day 2: Agentic AI — From Concept to Your First Agent

Understand autonomous AI, then build one for your team's process.

Topics Covered

• Chatbots vs autonomous agents
• The agentic loop: Observe → Plan → Act → Reflect
• 4 levels of AI autonomy (L1–L4)
• 4 workflow patterns: Chaining, Parallelization, Routing, Orchestration
• The automation stack: Steering + Skills + Hooks + MCP
• Building agents in Claude Cowork
• Agent Design Canvas methodology
• Python vs LLM: when to use what

⚡ Interactive Explainers

🤖 Day 2 Activities

💡 What you'll take home from Day 2: A working agent project in Claude Cowork, an agentic workflow cheat sheet, and an Agent Design Canvas ready to share with your tech team.