AI at Scale — The Automation Builder
A hands-on day for people ready to turn effort into leverage. Build the automations and agents that scale your output — a reusable agent, a workflow with a human approval gate, a live connection to real data — and harden it against the inputs that break real systems. The outcome is leverage; AI is just the tool.
Workshop17 · V&A Waterfront, Cape Town · Hybrid · max 13 participants · always live, never recorded · 09:00–16:00 · Level 2 of the Proven Path Professional Certificate ·
You learned to use AI. Now learn to build with it.
If "AI at Work" is about getting comfortable with prompts, this course is about moving from chat to agents and workflows — production-grade systems with roles, tools, memory, human approval gates, and the three checks (factuality, safety, cost) that decide whether they actually ship.
The advanced individual contributor
You're already prompting daily. You want to stop re-typing prompts and start shipping reusable agents — with the discipline of role, tools, memory and loop.
The operations / ops-tech owner
You spot the same repetitive workflow five times a week. You want to wire it to a trigger, hand it to one or two agents, and put a human gate where reversibility ends.
The team lead who'll roll it out
You'll leave with a Monday-morning team workflow — three agents, one shared memory, one digest, one human gate — that survives adversarial inputs.
Recommended first: AI at Work (Level 1) or equivalent experience — plus one licensed AI product (Claude Pro / Copilot for M365 / Gemini Advanced / Notion AI / NotebookLM). It's a recommendation, not a hard gate: come if you're already comfortable prompting. The trainer demoes every exercise in Claude live; students follow their own tool's path.
Working builds you leave holding — not slides you'll never open.
Running case: Karoo Logistics — Sam Naidoo (now Operations Director) needs AI automations the team uses every week. You build them, on your own tools.
- A reusable agent — Role · Tools · Memory · Loop. A weekly KPI digest, same agent each week, fresh inputs every time.
- A workflow with a human approval gate — complaint triage that classifies, drafts, holds, then sends only when a person says go.
- A live link from agent to real data — surface the few emails that need a reply from the many that don't. Native / no-code / MCP integration patterns covered.
- A stress-tested, production-aware version — survives adversarial inputs (missing data, non-English emails, prompt injection). The 3 production checks (Factuality · Safety · Cost) applied.
- A reference card — agent anatomy, workflow anatomy, integration patterns, the production-check list.
- A Proven Path certificate of completion — PPA-AIS-001, issued after a 10-question knowledge check (7/10 to pass). Level 2 of the Proven Path Professional Certificate.
Want to go further? Multi-agent orchestration, shared memory across agents and a full production capstone are covered in an extended build engagement delivered one-to-one or in-house via Proven Path Strategy — quoted to your context.
Agenda — from prompts to a hardened, working build
One focused day takes you from one-off prompts to a reusable agent, a workflow with a human gate, a live data connection, and a hardened, production-aware version. Lunch is BYO during the 45-minute break — V&A Waterfront cafés 5 minutes away. Deeper multi-agent orchestration is available as an extended build via Proven Path Strategy.
| Time | Block |
|---|---|
| One day — build, connect, harden (09:00–16:00) | |
| 09:00 – 09:15 | Welcome · check-in · Karoo running case |
| 09:15 – 09:45 | Theory 1–2. The agent spectrum + anatomy of an agent — Role · Tools · Memory · Loop |
| 09:45 – 10:45 | Exercise 1. Build a weekly KPI digest — your first reusable agent |
| 10:45 – 11:00 | Short break |
| 11:00 – 11:20 | Theory 3. Workflow anatomy — Trigger · Input · AI step · Action · Human gate |
| 11:20 – 12:20 | Exercise 2. Complaint triage with a human approval gate |
| 12:20 – 13:05 | BYO lunch (45 min) |
| 13:05 – 13:25 | Theory 4. Tool integration patterns — native · no-code · MCP |
| 13:25 – 14:25 | Exercise 3. Connect your agent to real data — surface what needs a reply |
| 14:25 – 14:40 | Short break |
| 14:40 – 15:05 | Theory 5. The 3 production checks — Factuality · Safety · Cost — plus where multi-agent goes next |
| 15:05 – 15:45 | Exercise 4. Stress-test and harden your build against adversarial inputs |
| 15:45 – 15:55 | Final test — 10 questions, 7/10 to pass |
| 15:55 – 16:00 | Reflection · certificates · close · your next step |
Bring one licensed tool. The trainer is on Claude — same exercise, your path.
Every exercise has a tool-agnostic scenario + five tool-specific step-by-steps. The trainer demoes every step in Claude live; when a student's path stalls we triage against the Claude reference.
Anthropic Claude (Pro / Teams)
Projects + Cowork mode (file system access). Long-context drafting, agent loops, code. The trainer's fallback for every exercise.
Microsoft Copilot for M365
Copilot Studio for agents inside the tenant; native Outlook / Word / Excel / Teams actions. Best when work stays inside M365.
Google Gemini Advanced / Gems
Custom Gems + Gmail / Docs side-panels + light AppSheet automation. Best when work lives in Google Workspace.
Notion AI / Business
AI Buttons, AI auto-fill DB properties, DB relations as the agent surface. Your team workspace becomes the agent surface.
Google NotebookLM
Source-grounded notebooks; "Briefing doc" custom output as the workflow output. Best when answers must cite your own documents.
Open-source & MCP intro
Theory beat 4 covers Model Context Protocol — the new standard for agents calling your tools — and where no-code (Make / Zapier / n8n / Power Automate) fits.
From R2,200 TTC per seat.
≈ €250 / $250 per seat — indicative, divided at R20 = €1 / $1.
One full day (09:00–16:00), materials, certificate. Book early, pay less — the price rises as the date nears. Lunch and refreshments are BYO during the 45-minute break (cafés inside the V&A Waterfront, 5 minutes from the venue). Hybrid — in-person or online · Always live, never recorded.
What's included
- One full day of training (09:00–16:00)
- Lunch and refreshments not provided — BYO (cafés 5 minutes away)
- Student exercise pack + Karoo Data Pack + adversarial inputs
- Laminated reference card (agent + workflow anatomy, orchestration patterns)
- 10-MCQ knowledge check + PPA-AIS-001 certificate
- Email follow-up access for two weeks after the course
Group & in-house
Group of 4+: 10% off the standard rate. In-house: contact us for a quote — same curriculum, your office, your team.
International participants & non-Rand payments welcome — we'll send specific invoicing instructions on request.