SagepilotBonkers Corner

How Bonkers Corner runs the full buyer journey in chat

The Gen-Z streetwear brand runs the complete buyer lifecycle on an AI employee: guided product discovery from the live catalogue, sizing advice, ready-to-checkout carts, orders placed end to end in chat, and post-purchase operations from tracking to returns, across WhatsApp, Instagram, and web chat, in English, Hindi, Hinglish, and other major Indian languages.

Challenge

A fast-moving streetwear catalogue and an audience that shops in DMs: open-ended 'show me oversized tees' messages, sizing doubt driving exchanges, and a constant stream of order, payment, return, and exchange queries landing on the support team.

Solution

An AI employee across WhatsApp, Instagram, and web chat that runs the whole journey: guided discovery from the live catalogue, sizing advice, the best applicable offer, ready-to-checkout carts, full order placement in chat, and post-purchase operations from tracking to returns, with identity checks and policy guardrails throughout.

Results

  • Open-ended DMs turned into guided, assisted purchases
  • Orders placed end to end in chat, from selection to payment
  • 24/7 first-line coverage across chat, social, and web, with humans on exceptions only

Streetwear that lives in the DMs

Bonkers Corner sells streetwear to an audience that practically lives on Instagram: oversized tees, pop-culture drops, and collections that move fast. That audience doesn't browse a website politely and file a support ticket. It DMs. Every drop produces a wave of 'link?', 'what size should I get?', and 'where's my order?' across Instagram, WhatsApp, and the website chat.

Answering those messages is only the surface of the work. Behind them sits a full retail operation: promotions with rules, prepaid benefits, cancellations with cutoffs, return and exchange windows, store-credit wallets, and a network of physical stores that can take returns in person.

From 'show me oversized tees' to a ready cart

The AI employee turns open-ended messages like 'I need something casual' into a guided shopping experience. It searches the live catalogue by category, style, colour, fit, occasion, budget, or pop-culture preference, filters out anything unavailable, and showcases four to five suitable options visually, with current prices and links, in whichever language the customer is speaking.

Sizing doubt is handled before it becomes an exchange: the agent considers the specific product, the customer's usual size, and their preferred fit, explains the difference between oversized, regular, slim, and wide-leg, shares the size chart, and suggests sizing up or down where it makes sense.

Once purchase intent is clear, it identifies the most beneficial publicly available promotion for that cart and that customer, explains prepaid benefits, and then builds a ready-to-checkout cart with the right items and quantities, so the customer gets a direct checkout path instead of hunting for the products again. Campaign attribution is included, so every assisted sale is measurable.

The whole order, placed in chat

For customers who don't want to leave the conversation at all, the agent runs the entire order in chat: confirming products, variants, sizes, and quantities, checking availability, recognising returning customers, collecting delivery details, applying an eligible discount, calculating the total with shipping, and then presenting payment options, a payment link for prepaid or a confirmed cash-on-delivery order, with the order number delivered in the same thread.

The customer stays in one conversation from 'show me tees' to an order confirmation, without ever opening the website.

When verified customer information is already available on the channel, the agent recognises the customer proactively and reviews their recent orders before they've finished explaining, so returning customers never start from zero.

After the order: operations, not just answers

Post-purchase, the agent does the work a support team would. It tracks orders and translates courier states into plain language a customer can act on. It verifies identity and handles eligible cash-on-delivery cancellations directly, routing prepaid cancellations for review. It manages address and contact-detail changes on orders that haven't progressed too far, updating every operational record and confirming only after the change has actually gone through.

Returns and exchanges start with real eligibility checks, delivery status, window, category exclusions, condition, before anyone is sent into a flow, with online and in-store options presented equally, including help finding the nearest Bonkers Corner store. Damaged, incorrect, and missing-item reports run through a specialised claims flow that asks for the unboxing video, distinguishes a genuinely missing item from a split shipment still in transit, and routes valid claims for review with a complete summary. Payment issues, failed payments, money deducted with no order, possible duplicate charges, are checked against whether an order was actually created before any next step is promised.

  • Order tracking, cancellations, and address changes handled end to end
  • Return and exchange eligibility enforced before a request is raised
  • Refund status and Bonkers Corner Wallet balance answered on demand
  • Partial cancellations attempted safely, never at the cost of the whole order

Guardrails a retail brand can trust

The whole lifecycle runs inside hard controls: identity verification before any order change, live stock validation before recommendations, no unsupported discounts or policy exceptions, no promised delivery dates, no exposed internal jargon, and confirmation only after an action has actually completed. If removing items from a multi-item order can't be done safely, the agent stops and routes the case rather than risk cancelling products the customer wanted to keep.

The agent also knows what isn't its lane. Conversations that belong to the influencer team stay with the influencer team, collaboration and career enquiries are routed to the right channel and closed cleanly, and when a case genuinely needs a human, it's escalated during support hours with a structured summary: who the customer is, what they need, what's been checked, and why it needs a person. Outside support hours, it sets honest expectations instead of promising callbacks that haven't been arranged.

Pre-purchase · Guided discovery

From 'show me tees' to a ready cart

Open-ended messages become a guided shopping experience. The agent searches the live catalogue by style, fit, occasion, budget, or pop-culture preference, filters out anything unavailable, shows four to five picks with prices and links, advises on sizing, applies the best public offer, and hands back a ready-to-checkout cart.

Need something oversized for a concert. Budget around ₹1,500?
Say less. Here are in-stock picks under ₹1,500, and going by your usual M, I’d take L in these for the proper oversized drop.
  • Live catalogue searched, out-of-stock filtered
  • Best public offer and prepaid benefit applied

Ready-to-checkout cart created

Open-ended DM to ready cart, no human needed
Commerce · Orders in chat

The whole order, placed in the thread

Customers who don't want to leave the conversation don't have to. The agent confirms variants and quantities, checks stock, recognises returning customers, collects delivery details, applies an eligible discount, and closes with a payment link or a confirmed cash-on-delivery order, order number included.

Order placed entirely in chat
  • Sizes and quantities confirmed, stock checked
  • Returning customer recognised, address confirmed
  • Total calculated, payment link sent for prepaid
  • Order number shared on confirmation
Selection to order confirmation, one thread
Post-purchase · Operations

Returns and exchanges, checked before promised

Tracking, cancellations, address changes, returns, and exchanges run against real eligibility: identity verified first, windows and category exclusions checked before a flow starts, and online and in-store options presented equally, including the nearest Bonkers Corner store.

“Wrong size, can I exchange?” · identity verified
  • Delivery date and exchange window checked
  • Size swap guided, price difference explained
  • Nearest store offered for in-person exchange
Eligibility enforced before the flow, not after
Customers

More stories

Join the brands that run their customer experience on Sagepilot

Live in about 48 hours, across every channel your customers use.