Agentic AI Foundations — Half-Day Workshop (All Staff / Track 1)

About this session

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.

Learning Outcomes

By the end, participants can:

1. Explain what makes an AI system an agent (versus a chatbot) — and why that shift matters for their work.
2. Write a clear system prompt using the 4 pillars + persona to steer an agent.
3. Build a simple working agent on AgentSea using Document Analysis and the enhanced Document Builder (brand-compliant output).
4. Design an agent for their own workflow using the Agent Design Canvas — captured as a shareable one-pager.
5. Recognise the common agentic workflow patterns and where AgentSea is heading.

Agenda

Timings are adjustable; runs equally well as a morning or afternoon session. Full module descriptions follow below.

Module Detail

F0 · Welcome — from AI users to agent builders (10 min)

• Goals, AgentSea login, quick poll (“what task eats your week?”).
• Meet the shared use case: the Guideline Assistant — an agent that reads an internal staff guideline (e.g., leave, claims, IT & data-handling, procurement rules) and helps you understand it, answer a question grounded in it, and draft a compliant note. Every employee deals with guidelines, whatever their function.
• Pointer to the pre-read for anyone who wants the “how AI works” grounding.

F1 · From Chatbots to Agents (50 min) — agentic AI concept

• Why a chatbot hits a wall: it can draft and summarise, but it can’t fetch fresh data, reach a system, or take a multi-step action.
• The four ideas that turn an LLM into an agent: tool use (skills), step-by-step reasoning, reading documents/images, and the framework that runs the loop.
• Skills = what an agent can do: on AgentSea today that’s Document Analysis, Document Generation / Document Builder, and Outlook — the capabilities you give your agent (you’ll pick one in the build).
• The four phases: LLM → Assistant → Agent → Agentic System — increasing autonomy, with healthcare-admin examples.
• The leadership read: chatbots make people faster; agents take work off the plate. (Adapted from the reference “From Chatbots to Agents” explainer, re-skinned for healthcare + AgentSea.)

F2 · Prompting your agent (40 min) — prompt engineering

• The 4 pillars (Clear · Specific · Contextual · Constrained) and the persona technique — framed as writing an agent’s system prompt, not just one-off prompts.
• Structured output (summaries, tables, checklists) and simple guardrails (“only use the document,” “never invent data”).
• Short guided practice that produces the system prompt used in the next module.

F3 · Build the Guideline Assistant on AgentSea (60 min) ⭐ Guided demo + simple build

A light, guided build everyone completes together — the shared warm-up before designing their own agent. It also teaches the single most important idea: an agent grounded in your documents, not the open internet.

1. Give the agent its skill (Document Analysis) and a system prompt (role + rules: answer only from the provided document, cite the section, say “not covered” if it isn’t there) — starter template provided.
2. Upload a sample internal guideline (synthetic); ask it a question → a grounded answer that points to the relevant section.
3. Have it produce a brand-compliant briefing — a plain-language summary or staff response, formatted on a Synapxe template using AgentSea’s enhanced Document Builder.
4. Quick debrief: notice it answers from your document, flags what isn’t covered, and returns a polished, on-brand document — why a grounded agent beats a generic chatbot, and where a human still checks.

Deliberately simple and universal so a class of ~50 (and, at scale, thousands of staff) can complete it comfortably. The deeper, robust build — with verification and guardrails — lives in the optional Deep Dive.

F4 · Agent Design Canvas — your use case (50 min) ⭐ Working session

• 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, the steps, the skills needed, guardrails, and how they’d know it’s working.
• Output — a design one-pager: each participant captures their canvas as a simple Markdown file, which is then converted into a branded HTML one-pager — a polished, shareable design they take away and present in the showcase.
• Share a few aloud. This canvas is the ticket into the optional Use Case Deep Dive, where it gets refined, built properly, and prepared for implementation.

F5 · Wrap-up & what’s next (15 min)

• Key takeaways; recognise the common workflow patterns and where AgentSea is heading (document-library and knowledge-space connectors, multi-step workflows, and shareable skills — demonstrated as concepts, subject to platform readiness).
• The optional 0.5-day Use Case Deep Dive for those who want to mature their canvas; the champion network; feedback.