ChatGPT AI Guide: Compare Kurta-Set Component Size Options

By TryBuy Editorial

ChatGPT can turn separate kurta and pyjama fit notes into a component-option matrix. The matrix should reveal whether the offered configuration meets your requirements, which detail needs confirmation and whether a separate outfit deserves comparison. It cannot authorise a custom size pairing that the seller has not offered or decide physical fit from a familiar letter label.

Prepare two independent input records

For the top, supply the exact garment and selected size, relevant chart labels and your own reference-garment notes. Do the same for the bottom in a second record. State whether each figure describes a garment or a body, and keep flat widths separate from circumferences. Put missing measurements into an unknown list rather than asking the model to complete a neat table from typical sizing.

Add the confirmed purchase configuration: fixed set, selectable components or not stated. If it is not stated, preserve that uncertainty. Include any owned bottom you are genuinely willing to use as a separate option. Do not treat a catalogue photograph of two matching pieces as proof of custom pairing, waistband construction or an inclusion that the written record does not establish.

Copy the matrix prompt

Organise my kurta-top and bottom records into a feasibility matrix. Keep garment identity, selected options, measurement definitions and source IDs intact. Compare only like-for-like measurements. Show top suitability, bottom suitability, confirmed purchase configuration, decisive unknown and next action for each scenario. Do not translate M into a measurement, assume all sets allow separate sizes or recommend altering a new garment without a separate decision. Distinguish my own fit observations from seller-confirmed features. Finish with questions, not a purchase recommendation, when a hard requirement remains unresolved.

Request separate rows for the offered set and any alternative you explicitly supplied. The model should not silently add a third product, a new size or a purchase arrangement merely to produce a complete-looking solution.

Filled fictional example

Imagine your labelled top reference aligns with the information supplied for one option, but the bottom record needed for that option is missing. A second scenario uses a kurta-only listing with trousers you already own. These are fictional records. The matrix can mark the set’s bottom as unresolved and the separate scenario as requiring an actual combined try-on; it cannot declare the set unsuitable solely because one field is blank.

A useful output identifies the missing bottom measurement and asks whether separate component selection is available. If the seller confirms fixed pairing, that answer changes the configuration column. It does not change your original top or bottom observations. Keeping those layers separate prevents a purchasing limitation from being mistaken for a fit diagnosis.

Revise one layer at a time

• “Highlight every conclusion that depends on an unconfirmed set configuration.”
• “Rebuild the matrix using this confirmed seller answer, without changing my original measurements.”
• “Create one concise question for the bottom record; remove general advice that does not resolve this decision.”

If a revision introduces an assumed waistband type or a universal size equivalence, return to the source records. Better wording cannot compensate for information that was never supplied.

Check the output against the garments

Verify the identity of every top and bottom in the matrix. Confirm that an owned piece is not presented as included in a purchase. Check any arithmetic separately and keep your own try-on outcome distinct from the model’s comparison. The final action may be ask, compare a different configuration or stop; the workflow does not need to end with a sale.

Read the original practical guide for the practical component-fit process and consult the men’s kurtas collection for current configurations. Save the matrix with its exact source records and date. Its purpose is to make a complex set decision easier to inspect, while leaving seller permissions, current availability and physical fit with the sources that can actually establish them.

For general instructions and follow-up techniques, see official OpenAI prompting guidance.