What generative AI does | Introduction to Generative AI
Understand how generative AI works, write source-bounded prompts, validate outputs, evaluate grounded answers and design a responsible career-learning assistant.
Prerequisites: No prior AI experience required. Basic familiarity with reading short code examples is helpful; no paid API account is needed.
What generative AI does
Artificial intelligence is a broad field concerned with systems that perform tasks such as prediction, planning, perception and language processing. Generative AI is a family of approaches that creates new outputs, such as text, images or audio, using patterns learned from data. A generated answer is not a database lookup and does not, by itself, prove that the answer is correct. This distinction matters when choosing an application for a job-search product.
Consider three product requests. Sorting job applications by a known application date is an ordinary database operation. Predicting whether an application belongs to a category is a classification task. Drafting a polite follow-up message from candidate-provided facts is a generation task. A useful AI feature starts with a clear user need, an input contract and a reviewable output. Adding generation to a deterministic task may increase cost and uncertainty without improving the result.
Begin with a bounded use case. For example, ask a model to rewrite an existing skills summary without adding qualifications. The candidate supplies the source facts and approves the result. Define success before choosing a model: the rewrite should preserve every factual claim, omit unsupported details and remain within a length limit. Keep a straightforward non-AI alternative available when a deterministic template already solves the problem.
Worked example
Task: Rewrite the supplied profile summary in clear language.
Source facts: Two years of Java experience; based in Pune.
Constraints: Do not add employers, degrees, awards or additional skills.
Return: One paragraph of at most 60 words.
Try it yourself
Write one generation use case and one deterministic use case for a career website. For each, define the input, expected output and a failure that would matter to the user.
Check your understanding: explain why the example works, state one limitation, and record how you would test it.
1. Understand generative AI
2. Give clear instructions
3. Ground and evaluate answers
4. Build a responsible learning prototype