GenAI: Capabilities, Limits & Use Cases

Where generative AI shines, where it fails (hallucinations and friends), and how to pick the right use case.

9 min read

What generative AI is great at

Key points

  • Text generation & summarization — drafts, reports, meeting notes.
  • Chatbots & virtual assistants — customer support, internal helpdesks.
  • Code generation — writing, explaining, and reviewing code.
  • Translation & rewriting — tone changes, simplification, localization.
  • Search & question answering — especially when combined with company data (RAG).
  • Image/audio/video generation — marketing assets, product mockups.
  • Extraction & classification — pulling structured facts from messy text.

The limitations you MUST know

LimitationWhat it meansMitigation
HallucinationThe model confidently generates false or fabricated informationRAG with trusted sources, human review, guardrails
NondeterminismThe same prompt can produce different outputs each timeLower temperature; don't expect exact repeatability
Knowledge cutoffThe model only knows what existed in its training dataRAG or tools to supply current information
Bias & toxicityModels can reproduce biases present in training dataCurated data, guardrails, evaluation, human oversight
Prompt sensitivitySmall wording changes can change results significantlyPrompt engineering and testing
Cost & latencyBig models are slower and pricier per callPick the smallest model that meets the need
Exam tip

Hallucination is the single most-tested limitation. If a scenario says the chatbot "invented an answer" or "cited a nonexistent policy," the fix is almost always RAG grounded in company data, plus human oversight for high-stakes decisions.

Choosing GenAI (or not)

Generative AI suits open-ended, language-heavy tasks with human review. It's the *wrong* tool when you need deterministic, auditable answers (use rules), precise numeric prediction (use classic ML — e.g., forecasting demand is Amazon Forecast territory, not an LLM), or when errors are unacceptable without review. Judge success with both technical quality and business metrics: cost per interaction, deflection rate, user satisfaction, revenue impact.

Knowledge check
Question 1 of 4

An LLM-powered support bot confidently tells a customer about a refund policy that does not exist. What is this failure called?