Two half-day sessions · Foundations for all staff, then an optional Use Case Deep Dive · No coding required · Built for hospital administration, finance & agency teams
The workshop is delivered as two half-day sessions. Foundations takes all staff from understanding what an agent is to building one. The optional Use Case Deep Dive is for those who want to mature their own idea into a working, verified assistant with a plan to implement.
How AI Works — short interactive explainers (tokenization, embeddings, inference) sent before Session 1. Not live workshop time.
All staff. From chatbots to agents → prompting → build the Guideline Assistant on AgentSea → design your own agent on the canvas.
Optional follow-up. Bring your canvas or a new problem → workflow patterns → robust build + verify → automation plan → implementation path.
Complete before Session 1. A short, progressive curriculum in healthcare context — each part takes ~10–15 min. This is the "how AI works" grounding so live time can focus on building.
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 — your starting point for AI-powered productivity. Built on Amazon Bedrock, it lets you deploy AI agents for your daily work. As you grow, you'll also explore Bedrock AgentCore, Strands Agents, and Kiro IDE — the AWS agentic AI stack that powers and extends what AgentSea offers.
Upload PDFs, Excel, or Word files — the agent reads, summarizes, and extracts key information
Create reports, letters, summaries, and brand-compliant documents from your instructions
Read and summarize emails, check calendars, and draft responses
A hands-on, half-day session that takes all staff from understanding what an AI agent is to building one. Everyone builds a shared, grounded assistant together — the Guideline Assistant — then designs an agent for their own work on the Agent Design Canvas, the springboard into the optional Use Case Deep Dive.
Half day — runs as a morning or afternoon session
Non-technical · healthcare administration context
Self-paced How AI Works before the session
By the end, participants can:
| Time | Module | Description |
|---|---|---|
| 09:00–09:10 | F0 · Welcome from AI users to agent builders | Goals, quick poll, and meet the shared use case (the Guideline Assistant) |
| 09:10–10:00 | F1 · From Chatbots to Agents | Why a chatbot hits a wall, the four ideas that make an agent, and the levels of autonomy |
| 10:00–10:40 | F2 · Prompting your agent | The 4 pillars + persona → writing a clear system prompt |
| 10:40–10:55 | Break | |
| 10:55–11:55 | F3 · Build the Guideline Assistant ⭐ | Guided build on AgentSea: ask an internal guideline → grounded answer → brand-compliant briefing (Document Builder) |
| 11:55–12:45 | F4 · Agent Design Canvas ⭐ your use case | Design an agent for your own workflow → a branded HTML one-pager; the bridge to the optional Deep Dive |
| 12:45–13:00 | F5 · Wrap-up & what's next | Key takeaways, the optional Use Case Deep Dive, and the champion network |
Timings are adjustable; runs equally well as a morning or afternoon session.
A light, guided build everyone completes together. Give the agent a skill (Document Analysis) and a system prompt (answer only from the document, cite the section, say "not covered" if it isn't there), ground it in a synthetic guideline, test a covered vs a deliberately uncovered question, then produce a brand-compliant briefing with Document Builder. Teaches the single most important idea: an agent grounded in your documents, not the open internet.
Open the F3 lab →Using the Guideline Assistant as the template, each participant designs an agent for a task in their own function (Finance, HR, Operations, Procurement, admin). The canvas captures purpose, steps, the skills needed, guardrails, and how they'd know it's working — captured as a Markdown file, then a branded HTML one-pager to take away. This canvas is the ticket into the Use Case Deep Dive.
Open the Canvas →Everything you'll open during the live session, in order.
Copy-paste starting points for F2–F4. Sharpen a vague ask into a powerful one, then shape it into a deployable system prompt.
A hands-on follow-up for staff who identified a promising use case and want to take it further. Where Foundations builds awareness and a first idea, this Deep Dive is about refining and implementing it — deeper agentic patterns, a robust agent design, a full build with verification, and a clear path to hand over to the DNA / IT team.
Half day — morning or afternoon
For a subset who want to mature a use case
Continue from Foundations, or bring a new problem
By the end, participants can:
| Time | Module | Description |
|---|---|---|
| 09:00–09:15 | D0 · Welcome bring your use case | Frame your use case — continue from your Foundations canvas or bring a new problem |
| 09:15–09:55 | D1 · Agentic workflow patterns | All four patterns (Chaining · Parallelisation · Routing · Orchestration) — matched to your use case |
| 09:55–10:35 | D2 · Build skills & instructions ⭐ | Hands-on: craft the system prompt and configure the skills your agent needs — guardrails, escalation, what NOT to do |
| 10:35–10:50 | Break | |
| 10:50–11:45 | D3 · Build & verify (capstone) ⭐ | Build a working assistant on AgentSea; the deliberate-error verification / trust-but-verify moment; iterate |
| 11:45–12:15 | D4 · Agentic Automation (design) | Concept + design: triggers, approval nodes, human-in-the-loop → produce an automation plan (Markdown) |
| 12:15–12:50 | D5 · Use-case refinement Agent Design Canvas | Full canvas: value / feasibility / risk, success metrics, and the path to implementation |
| 12:50–13:00 | D6 · Showcase & next steps | Share designs, implementation roadmap, and how to engage the DNA / IT team |
Timings are adjustable; runs equally well as a morning or afternoon session.
Anyone who prefers a ready-made starting point can adopt one of these instead of their own idea.
Procurement / Finance — extract terms, compare vendors, flag risks, recommend
Governance — check a document against a policy or circular, cite the clause
HR — apply the rules in a staff guideline to a request and draft the response
Finance — read the numbers, explain the variance, draft a memo
On current AgentSea (single agent + Document Analysis + Document Generation + system prompt):
The shift from an assistant you invoke to an agent that runs on a trigger or a schedule — the L1 → L2 → L3 autonomy ladder. Three questions frame any automation: What triggers it? · What runs? · Where does a human stay in the loop?
The Deep Dive is built around your use case, so most work happens on AgentSea and in your own documents. The canvas below anchors D2, D5, and the implementation plan.