Agentic AI Foundations on AWS

AnyCompany Healthcare — Workshop

1 day · From AI fundamentals to designing your own agent · No coding required · Built for hospital administration, finance & agency teams

Workshop Journey

A single-day deep dive into AI agents — from understanding what AI can do, to designing your own agent for your daily workflows on the AgentSea platform.

🧠

Morning: Foundations

What is AI, how agents work, and why it matters for your daily tasks in hospital administration & finance

✏️

Midday: Prompt Mastery

Learn to communicate effectively with AI — the 4 pillars of great prompts, personas, and structured outputs

🤖

Afternoon: Design & Build

Design your own AI agent using the Agent Design Canvas — a system prompt ready to deploy on AgentSea

Who Is This For?

🏥

Hospital Administration

Administrative staff managing documents, correspondence, and operational workflows across agencies

💰

Finance Teams

Budget analysts, procurement officers, and finance staff handling reports, vendor assessments, and compliance

📋

Agency & Operations

Ministry and agency staff managing policies, meeting coordination, and cross-department communications

👥

HR & People Teams

HR professionals handling leave processing, onboarding documentation, and staff communications

What is AgentSea?

AgentSea is Synapxe's internal AI platform where you can deploy AI agents to help with your daily work. Think of it as your personal AI assistant that understands your role and follows your rules.

📄

Document Analysis

Upload PDFs, Excel, or Word files — the agent reads, summarizes, and extracts key information

✍️

Document Generation

Create reports, letters, summaries, and formatted documents from your instructions

📧

Outlook Integration

Read and summarize emails, check calendars, and draft responses

🚀 Coming in Phase 1B (August 2026): Custom skills marketplace, SharePoint integration, knowledge spaces, and the ability to create and share your own agent configurations with colleagues.

Topics Covered

• What is Generative AI — in plain language
• How AI "reads" and "writes" — tokens & context
• From chatbots to agents — what's different
• The Agent Loop: Observe → Plan → Act → Reflect
• Prompt engineering — the 4 pillars
• Persona technique for better AI responses
• AgentSea platform skills & capabilities
• Healthcare administration use cases
• Responsible AI — what AI should NOT do
• Data privacy & PDPA compliance
• Agent Design Canvas — design your own agent
• System prompts — the blueprint for your agent

🤖 Main Exercise: Agent Design Canvas

The centerpiece of this workshop — design an AI agent for a real workflow from your own team. No coding required.

🤖

Design Your AgentSea Agent

Pick a workflow from your team → design the agent → write the system prompt → submit for AI scoring on the leaderboard

Start Exercise →
⏱️
60 minutes
Team exercise
👥
Teams of 3-4
Collaborative design
🚫
No coding
Design thinking only
🏆
AI-scored
Live leaderboard

Prerequisites

  • No coding experience required — this is a conceptual and design-focused workshop
  • Curiosity about how AI can improve your team's workflows
  • Familiarity with your own team's daily processes (you'll design an agent for one of them)
  • Laptop with internet access and a modern browser
  • AgentSea platform access (provided during workshop)
⚠️ Data Privacy Notice: Do not include any confidential patient information, personally identifiable information (PII), or sensitive clinical data in any exercises. All sample data in this workshop is synthetic. Follow PDPA guidelines at all times.

Workshop Modules

The workshop follows a progressive structure — from understanding AI fundamentals to designing your own agent for deployment on AgentSea.

📽️ Presentation Slides

🧪 Interactive Explainers

📚 Module Breakdown

ModuleTopicDurationKey Concepts
M0Welcome & Setup15 minGoals, agenda, AgentSea login, ice-breaker
M1What is AI & How Agents Work45 minGenAI basics, tokens, context, agent loop, chatbot vs agent
M2Prompt Engineering for AgentSea60 min4 pillars, personas, structured output, negative constraints
M3AgentSea Skills & Use Cases45 minDocument analysis, generation, Outlook, healthcare workflows
M4Responsible AI & Governance30 minBoundaries, PDPA, verification, guardrails, healthcare considerations
M5Agent Design Canvas (Capstone)60 minPick workflow, design agent, write system prompt, AI scoring
M6Wrap-Up & Next Steps15 minTakeaways, Phase 1B preview, champion network, feedback

🧪 Exercises & Activities

🎬 Demos (Instructor-Led)

Hands-On Exercises

All exercises use the AgentSea platform — no coding, no IDE, just natural language prompts and the browser.

Exercise 1: Prompt Transformation

Take a vague, ineffective prompt and transform it into a powerful one using the 4 pillars.

❌ BEFORE — Vague prompt
Summarize this document for me.
✅ AFTER — Powerful prompt
You are a Senior Procurement Analyst with 10 years of experience in healthcare vendor assessment. Read the attached vendor proposal and produce: 1. A summary table with columns: Vendor Name, Service Offered, Contract Duration, Total Cost (SGD), Key Risks 2. A list of 3 strengths and 3 concerns about this vendor 3. A recommendation: PROCEED / REVIEW FURTHER / REJECT — with one-sentence justification Rules: - Only use information from the attached document — do not make assumptions - Flag any missing information as "NOT PROVIDED" - All costs in SGD - Keep the summary under 500 words

Exercise 2: Agent Design Canvas

The capstone exercise — design a complete AI agent for your team's workflow. Go to full exercise →

Exercise 3: System Prompt Writing

Convert your Agent Design Canvas into a deployable system prompt for AgentSea.

SYSTEM PROMPT TEMPLATE
You are [ROLE — use persona formula]. Your purpose is to [ONE SENTENCE — what this agent does]. ## What You Do When the user uploads [INPUT TYPE], you will: 1. [STEP 1 — what to extract/analyze] 2. [STEP 2 — what to produce/generate] 3. [STEP 3 — what format to output] ## Output Format [Describe the exact format: table, bullet points, report sections] ## Rules You MUST Follow - Only use information from the uploaded document(s) - If information is missing, state "NOT PROVIDED" — never guess - All monetary values in SGD - Keep responses under [WORD LIMIT] words - Use professional, clear language ## You Must NEVER - [NEGATIVE CONSTRAINT 1 — e.g., "provide medical advice"] - [NEGATIVE CONSTRAINT 2 — e.g., "share patient identifiable information"] - [NEGATIVE CONSTRAINT 3 — e.g., "approve amounts above $50,000 without flagging"] ## When to Escalate Say "⚠️ Please consult your supervisor" when: - [ESCALATION TRIGGER 1] - [ESCALATION TRIGGER 2] - You are unsure about the correct interpretation