1 day · From AI fundamentals to designing your own agent · No coding required · Built for hospital administration, finance & agency teams
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.
What is AI, how agents work, and why it matters for your daily tasks in hospital administration & finance
Learn to communicate effectively with AI — the 4 pillars of great prompts, personas, and structured outputs
Design your own AI agent using the Agent Design Canvas — a system prompt ready to deploy on AgentSea
Administrative staff managing documents, correspondence, and operational workflows across agencies
Budget analysts, procurement officers, and finance staff handling reports, vendor assessments, and compliance
Ministry and agency staff managing policies, meeting coordination, and cross-department communications
HR professionals handling leave processing, onboarding documentation, and staff communications
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.
Upload PDFs, Excel, or Word files — the agent reads, summarizes, and extracts key information
Create reports, letters, summaries, and formatted documents from your instructions
Read and summarize emails, check calendars, and draft responses
The centerpiece of this workshop — design an AI agent for a real workflow from your own team. No coding required.
Pick a workflow from your team → design the agent → write the system prompt → submit for AI scoring on the leaderboard
The workshop follows a progressive structure — from understanding AI fundamentals to designing your own agent for deployment on AgentSea.
| Module | Topic | Duration | Key Concepts |
|---|---|---|---|
| M0 | Welcome & Setup | 15 min | Goals, agenda, AgentSea login, ice-breaker |
| M1 | What is AI & How Agents Work | 45 min | GenAI basics, tokens, context, agent loop, chatbot vs agent |
| M2 | Prompt Engineering for AgentSea | 60 min | 4 pillars, personas, structured output, negative constraints |
| M3 | AgentSea Skills & Use Cases | 45 min | Document analysis, generation, Outlook, healthcare workflows |
| M4 | Responsible AI & Governance | 30 min | Boundaries, PDPA, verification, guardrails, healthcare considerations |
| M5 | Agent Design Canvas (Capstone) | 60 min | Pick workflow, design agent, write system prompt, AI scoring |
| M6 | Wrap-Up & Next Steps | 15 min | Takeaways, Phase 1B preview, champion network, feedback |
All exercises use the AgentSea platform — no coding, no IDE, just natural language prompts and the browser.
Take a vague, ineffective prompt and transform it into a powerful one using the 4 pillars.
The capstone exercise — design a complete AI agent for your team's workflow. Go to full exercise →
Convert your Agent Design Canvas into a deployable system prompt for AgentSea.