Generative AI for Problem Solving

Building software that diagnoses problems and proposes fixes is central to the work of Dr. Alfred Ang, a full-stack AI developer, Agentic AI solution architect and corporate trainer who is Chief Technology Officer of Tertiary Infotech Academy Pte Ltd in Singapore, the organisation behind Tertiary Courses. Several of Dr. Ang's projects turn generative AI into a structured analysis partner. An inventory audit and forecasting agent built on n8n uses a local large language model through Ollama to read stock levels, flag anomalies and forecast replenishment needs. A guided SIPOC and process-map builder for Lean Six Sigma helps users map suppliers, inputs, process steps, outputs and customers, tag pain points and generate swimlane diagrams and hand-off tables automatically. An ERP prototype built on Next.js and Postgres routes purchase orders through human-in-the-loop approvals, matches invoices three ways and triggers low-stock replenishment, showing how AI suggestions and human judgement can share a decision. Dr. Ang also built a coaching simulator that helps teams redesign jobs around accountable AI-agent ownership, and a stock-analysis dashboard with a Telegram AI agent for market questions. These projects belong to a public GitHub portfolio of more than 300 repositories spanning front end, back end, databases, cloud deployment and native mobile apps. Together they give Dr. Ang practical experience of where generative AI sharpens analysis and where people must still own the decision. Each of these builds required Dr. Ang to define the problem precisely, test candidate solutions against real data and measure whether the fix actually improved results, which is the same discipline this course teaches. Dr. Ang is also a certified Lean Six Sigma Black Belt and a PMP-certified project manager, so structured problem solving runs through every activity, and as a Distinguished Toastmaster with many public speaking awards he helps learners present their ideas and recommendations with confidence.

Generative AI for Problem Solving draws on that experience to give participants a disciplined, repeatable method rather than ad hoc prompting. The first topic shows learners how to use generative AI to identify performance gaps and dig for root causes, structuring prompts around data, symptoms and context so the AI supports techniques such as five whys and cause-and-effect analysis instead of jumping straight to answers. The second topic moves to developing corrective plans, where participants generate alternative solutions, compare them against cost, risk and feasibility, and ask the AI to challenge assumptions before a recommendation is made. The final topic covers selecting a solution, planning its implementation and defining measures that show whether it actually worked. Dr. Ang teaches through realistic workplace scenarios and live demonstrations, often referring to the approval steps and audit trails built into real projects to explain why a human should remain accountable for the final call. Learners practise writing evaluation criteria, checking AI output for bias and missing evidence, and documenting their reasoning so decisions can be reviewed later. The emphasis throughout is on practical tools that managers, analysts and team leaders can use the following week, not on technical theory. Participants leave with prompt templates, a structured problem-solving workflow and a clearer sense of good judgement with AI. Exercises use cases familiar to participants, such as rising customer complaints, missed delivery targets or slow internal approvals, so the method transfers directly to their own teams and departments. Dr. Ang's projects can be explored at https://github.com/alfredang.