From Prompt to Prototype: 2-Day AI Bootcamp at Kementerian Komunikasi

On 17–18 September 2025, we ran a hands-on AI training at Kementerian Komunikasi Malaysia for ~50 officers—moving from fundamentals to real deliverables in just two days. Participants learned practical GenAI workflows with tools like ChatGPT, Gemini, Claude and Perplexity; created fast, on-brand assets with Canva AI; supercharged everyday documents with Google Workspace AI; and even built simple prototypes (API calls, a mini-chatbot, local LLMs with Ollama, and light orchestration using n8n/Flowise). The focus was impact and safety: accurate research, responsible use, and repeatable processes that slot straight into government work. Everyone left with ready-to-use prompts, templates, and a clear path to scale AI securely across their teams.

9/18/20252 min read

Dates: 17–18 September 2025
Location: Kementerian Komunikasi, Putrajaya
Participants: ~50 officers

We just wrapped a two‑day, hands‑on AI training with the Kementerian Komunikasi Malaysia and it was all about turning ideas into working outputs, fast. Over 17–18 September, about fifty participants moved from fundamentals to real deliverables: smarter research, cleaner drafts, on‑brand visuals, and even small working prototypes. No fluff — just repeatable workflows they can use the very next day.

What we covered

GenAI toolbelt for daily work — Practical prompting and research using leading models and platforms (ChatGPT, Gemini, Claude, Perplexity, and more) to draft memos, summarise long reads, compare sources, and structure briefs.
Google Workspace AI, end‑to‑end — Gmail, Docs, Sheets, Slides, Gemini, NotebookLM, and Google AI Studio: from inbox triage to policy notes, simple data analysis, and deck creation — all within the tools teams already use.
Canva AI for communications — Magic‑assisted design and content features (Design for me, Magic Write, image generation, and more) to ship on‑brand visuals and public‑facing assets quickly.
Prototyping drills — API basics, coding inside modern IDEs, a minimal feature calling an AI API, a small chatbot prototype on Replit, local LLMs with Ollama, and lightweight orchestration using n8n/Flowise.
Safety, governance, and rollout — Prompt hygiene, data handling, red‑teaming, evaluation, and a simple adoption plan that scales responsibly across units.

Why it matters for public‑sector teams

Speed with traceability — Faster turnarounds for briefs, responses, and talking points, while keeping sources and attributions in view.
Consistency at scale — Shared prompts, templates, and checklists to standardise outputs across different units.
Right‑sized innovation — Start with low‑risk wins in existing tools; expand to prototypes once workflows are stable and governed.

In‑room wins we loved

Turning a rough prompt into a well‑structured memo — with citations to verify every claim.
Converting briefing notes into a clean slide deck in minutes.
Summarising heavy inbox threads into action items and next steps.
Spinning up a tiny chatbot and testing a local model — enough to demystify “how it all works.”

What participants took home

Prompt packs & playbooks for day‑to‑day tasks (research, drafting, summarising, meeting notes, Q&A).
Templates for Docs/Slides/Sheets and design presets for quick comms.
Starter snippets for API calls and local‑model experiments.
A governance checklist to keep outputs accurate, secure, and compliant.

Want this for your team?

We tailor our two‑day, lab‑first programme to your workflows — policy, comms, or IT. If you’re ready to move from slides to working results, let’s talk. We’ll bring the prompts, labs, and guardrails; your team brings the problems that matter.