SwiggyAI Product Manager interview preparation

The user is driving. Every design choice follows from that, and candidates who sketch a chat screen fail the question in the first minute.

Standard prioritisation frameworks miss the thing that makes AI ideas risky: nobody knows yet whether the model can do it reliably. The strong answer prices that uncertainty in.

Repeat items are predictable; meal plans are a nice demo. Start with replenishment, expose ordering to outside assistants with one confirmation, and keep household preferences inside your own app.

Matching free is tempting and often ruinous when every use costs money. The interviewer wants a segmented response that protects the customers you can keep, the margin you need, and the value only you deliver.

The assistant owns the user, the ranking and the payment rules. Ship a narrow app for discovery, keep the account and core workflow on surfaces you own, and measure incremental conversions with a holdout.

The first vocabulary word of AI product management. Tokens are the unit of cost, speed and memory, and a PM who can't reason in them can't price, budget or design an AI feature.

A question about fairness and unit economics hiding in a tokenizer. The interviewer wants the mechanism, the arithmetic, and options that do not leave non-English users with a worse product.

Voice adds two models and a much tighter latency budget to a text assistant. The interviewer wants the pipeline, the turn-taking problem, and the failure modes that text products never face.

A full-stack AI system design with scale, money, languages and angry customers. The interviewer wants tiers: cheap triage for everything, an agent where it pays, and humans where it matters, with the cost per day worked out.

Every AI product depends on services it does not control. The interviewer wants a degradation plan by feature, written and tested before the outage starts.

Launches fail on rate limits more often than on model quality. This question checks whether you can turn expected usage into tokens per minute, compare it with limits, and plan headroom.

Generation at scale where the model writes copy nobody reviews before it reaches millions of phones. The design is about templates, guardrails and cost, more than about the model.

Open schema access answers more questions and produces more wrong numbers that look right. Choose the scope, the permissions and the evidence each answer must show.

Money movement is where agent design stops being theoretical. The strong answer never lets the model be the control, and shows exactly where policy, approval and idempotency sit.

A fundamentals question with a trap: the model never touches your systems. Getting that right is what lets a PM reason about safety and control later.

Two problems hide in one complaint: the agent is slow, and waiting for it feels worse than it needs to. Strong answers attack both, and question whether every task should make the user wait at all.

The strongest first move costs nothing and involves no tooling: read the traces. What you do with the notes, and in what order, is the rest of the answer.

A translated English eval set can miss code-switching, transliteration and local support needs. Decide what to sample in each language and who can judge the replies.

A voice agent can fail at hearing, understanding, deciding or speaking. Evaluate each stage, then whole calls, segmented by language, accent and line quality.

An estimation question that tests commercial judgment. The inference bill is where the arithmetic starts; the number that decides the answer is somewhere else.

AI features are unusually good at producing engagement that is actually friction. The question tests whether you can tell the two apart in the data.

Batch pricing halves the bill on eligible work, and the real product question is what you can precompute before anyone asks for it.

India's Digital Personal Data Protection framework is now in force in phases. The interviewer wants the principles turned into product requirements, stated as of a date and checked with counsel.

Opinions about prompts are cheap. A small grid of prompts by models on fifty real examples turns a debate into a table, and the interviewer wants to see you build it.

Prototypes tested in English hide most of what goes wrong for users in other languages. The interviewer wants a prototype cycle that tests real speech and text from target users, with native evaluation.

Progressive constraints test whether you can adapt under pressure without breaking what works. Principal-level candidates handle each constraint with the right mechanism, verify each change, and explain trade-offs.

Companies that shipped MCP servers exposed reads widely and held back money-moving actions. Start with a few consolidated read tools, test descriptions against real tasks, and gate anything irreversible.

A common behavioural prompt with an AI twist: model capability itself is uncertain. A good answer turns ambiguity into small, time-boxed experiments with clear decisions at the end.

Recommend an approach to a CEO who needs a product decision. Explain what retrieval and fine-tuning each change, then connect that difference to freshness, reliability and cost.

A fundamentals question that comes up when a stakeholder notices the assistant answered differently yesterday. The good answer explains sampling in one minute and then turns it into product decisions.

Retrieval quality decides most RAG products, and embeddings are where it starts. The interviewer wants the intuition, the failure modes, and the fixes a PM would push for.

A larger context window changes what fits in a request. Decide whether to use it by checking corpus size, freshness, permissions and cost per successful query, including cache misses.

Fine-tuning is sometimes the best decision a team makes and often a costly detour. The interviewer wants the test that tells them apart, with numbers.

A vocabulary check on one of the most important model developments of recent years. The good answer explains the trade (accuracy for time and money) and gives a rule for when it pays.

Everyone knows models make things up. The interviewer wants to hear why, which kinds of hallucination exist, and a layered set of product defences, without promising to eliminate it.

A fluency question about the request path. The interviewer does not need the maths; they want to know you can connect each stage to latency, cost and design decisions.