Omnichannel post-sale agent · WhatsApp, Instagram, web chat, email
A retailer with physical stores and nationwide e-commerce. We built a unified post-sale agent across four channels (WhatsApp, web chat, Instagram DM, email) that handles exchanges, returns, tracking questions and reviews — all connected to the ERP, the WMS and the customer's history.
Omnichannel retailer (client under NDA)
Post-sale was the bottleneck: thousands of tickets a month, replies that took hours and falling satisfaction. The team couldn't keep up and turnover was high. Every ticket meant searching three different systems (the store platform, WMS, ERP) to answer something as trivial as 'where's my order?' The retailer's response times lagged what online shoppers in Mexico expect.
Stack and deliverable
A unified agent with four entry points: WhatsApp Business, web chat, Instagram DM and email. It identifies the customer by email or phone and loads their full history (orders, past returns, communications). It resolves first-tier requests with no human involved: tracking, order status, exchange policy, FAQs. For exchanges and returns it triggers the formal flow: it generates a prepaid shipping label, schedules the pickup and issues store credit or a refund based on policy and purchase date. It routes complex cases (defective items, formal complaints, consumer-protection (PROFECO) risk) to the right person with an executive summary and context already assembled.
What changed in the operation
What we learned
At first the agent stumbled on the last mile: emotional complaints, escalation, compensation. The fix wasn't a better model — it was better escalation. When the agent detects a frustrated tone or sensitive words (formal complaint, PROFECO, lawsuit, lawyer) it escalates immediately with an executive summary. People don't get angry at an agent; they get angry when you don't hand them to a human when they ask.
How it was built
Technology: WhatsApp Business · Instagram Graph API · E-commerce platform · WMS · ERP
Delivery: Staged delivery through to production
FAQ · this case
How did this Retail · Omnichannel e-commerce project make it to production?
Staged delivery through to production: design, build, testing with real data and launch. By the end, the client's team was running the agent in production, with observability dashboards and guardrails already configured. Stabilization is part of the delivery.
What tech stack was used in this Retail · Omnichannel e-commerce case?
WhatsApp Business · Instagram Graph API · E-commerce platform · WMS · ERP. Each piece was chosen to fit the client's existing systems — no forced migrations, integrating through official APIs wherever they were available.
How are results tracked?
Before the project starts, we agree on an operational baseline with the client, and during stabilization it's reviewed on the operations dashboard. Because of the NDA, we don't publish this client's figures. In the diagnostic we define what to measure in your case.
Can this be replicated at another company in Retail · Omnichannel e-commerce?
The pattern is replicable; the specific implementation depends on the current stack, operating volume and internal rules. The Studio diagnostic identifies which pieces apply to your context and estimates the return for your case.
Who runs the agent after the project?
The client's team. Studio hands over the agent running and trains the team on monitoring, prompt adjustments and exception handling. Stabilization support is included for the first few months; after that, an optional monthly retainer is available.
What happens if the AI model changes or gets more expensive?
We don't depend on a single provider. If a model changes or gets more expensive, we move the agent to another one without rebuilding it.
Facing similar challenges in Retail · Omnichannel e-commerce?
A Studio diagnostic with an architect. We identify which processes to automate first and estimate the return for your case.
No cost · No commitment