CRM + WhatsApp agent + back-office automation
An optical manufacturer with a network of stores. We built a lightweight CRM, a WhatsApp sales agent that responds around the clock, and automation for the weekly store close.
Optical manufacturer with a store network
The company ran on spreadsheets and ad-hoc WhatsApp. Each store reported sales by hand, the weekly close ate up days of work, and follow-up on social media leads fell through the cracks. Leadership had no real-time visibility and no way to react quickly to operational bottlenecks.
Stack and deliverable
Three pieces: a lightweight CRM with views by store and product; a WhatsApp Business sales agent that qualifies leads from Facebook and Instagram, books an in-store appointment and notifies the salesperson; and automation for the weekly close: per-store data collection, validation, reconciliation against inventory and an executive report for leadership.
What changed in the operation
What we learned
The bottleneck wasn't a lack of data but a lack of orchestration. The company already had the information — it just lived in silos. The value came more from connecting what already existed than from adding new tools.
How it was built
Technology: Lightweight CRM · WhatsApp Business Cloud API · Integration with your systems
Delivery: Staged delivery through to production
FAQ · this case
How did this Optical · Manufacturing 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 Optical · Manufacturing case?
Lightweight CRM · WhatsApp Business Cloud API · Integration with your systems. 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. We don't publish client figures on this site. In the diagnostic we define what to measure in your case.
Can this be replicated at another company in Optical · Manufacturing?
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 Optical · Manufacturing?
A Studio diagnostic with an architect. We identify which processes to automate first and estimate the return for your case.
No cost · No commitment