| The rules are clear and stable (tax rate, opening hours) | Plain code, no AI | Cheapest, testable and explainable. Use AI only where rules break down. | What AI, machine learning, deep learning and generative AI are |
|---|
| Predict a number from a table (price, delivery time, demand) | Regression (gradient boosting first) | Tables of business data are where classic ML is strongest. | Regression: predicting a number |
|---|
| Pick a category from a table or short text (churn, fraud, spam, intent) | Classification | Needs labelled history; choose the metric from the cost of each mistake. | Classification: picking a category |
|---|
| No labels; find groups or unusual cases | Clustering or anomaly detection | Segments customers or flags fraud and faults for review. | Unsupervised learning: groups, compression and anomalies |
|---|
| Predict future values over time | Time-series forecasting | Split by time; beat a seasonal baseline. | Time-series forecasting |
|---|
| Suggest items to users | Recommender system | Collaborative filtering plus content features for new items. | Recommender systems |
|---|
| Images, audio or video | Deep learning with a pretrained model | Transfer learning needs far less data than training from scratch. | Computer vision: classification, detection and segmentation, Speech and audio: recognition and text-to-speech |
|---|
| Write, summarise, translate or extract from text | An LLM with a good prompt and structured output | Start with a hosted or local model; validate every output. | Calling an LLM from your application, Prompt engineering that works in production |
|---|
| Answer questions from your own documents | RAG | Keeps answers current and cited; no retraining. | RAG: answering from your own documents, Advanced RAG: chunking, hybrid search, re-ranking and evaluation |
|---|
| Take actions in other systems (refunds, bookings, tickets) | Agent with tools and human approval | Least privilege and approval in code. | Tools and agents with human approval |
|---|
| A specific style, format or narrow skill the prompt cannot reach | Fine-tuning (for example LoRA) | Only after prompting and RAG are measured and fall short. | Fine-tuning: SFT, LoRA, QLoRA and preference tuning |
|---|
| Data must never leave the building | A local model | Small quantised models run on laptops and servers you control. | Running language models on your own machine |
|---|
| Learn by trial and error from a simulator (control, scheduling) | Reinforcement learning | Rarely the first choice in business; needs a safe simulator. | Reinforcement learning |
|---|