Hernan Corporation · Food & Beverage Manufacturing / Agriculture & Cold Chain Logistics · Malaysia · Claude Platform / API + agentic workflows

A durian doesn’t wait for a spreadsheet. From the moment a Musang King fruit is graded at the receiving dock to the moment it leaves, still cold, for one of eighteen export markets, every handoff that slows down is quality the fruit doesn’t get back.

Hernan Corporation Sdn Bhd is a Malaysian exporter of frozen and fresh durians and durian-based products, and one of the country’s leading names in durian cold-chain logistics. Its operations run through a chain of time-critical stages — sales, pre-shipment documentation, grading and receiving, pre-cooling, final packaging, driver assignment, inspection, loading and delivery — each historically coordinated by a different team, with photos, forms and status updates passed hand to hand as the fruit made its way from dock to container.

The challenge

Hernan’s problem was never demand. It was keeping a high-volume, time-sensitive, perishable-goods operation coordinated across every one of those handoffs, for a product whose grade and value are set by hours, not days. Manual photo handling and data entry, order verification, quality grading, driver assignment, inspections, loading confirmation, delivery handoffs, rejection logging and management reporting all created room for delay, inventory discrepancies and limited escalation oversight — risk that compounds when a shipment is racing an export cut-off against a quality grade that won’t hold.

The approach

Deployed under Anthropic’s Claude Partner Network in Malaysia — documented internally as the Hernan AI field deployment engagement — the build put a single agent, @Hernan Operation Assistant, inside the group chats each team already used to coordinate. The interface each team touched didn’t change; what happened behind it did.

A Sales team member uploads a completed order file and tags the agent, which asks clarifying questions where needed and creates the Sales Order automatically, notifying Pre-Shipment, Sales, Loading and Management the moment it’s done. Pre-Shipment attaches the shipping documents in the same chat; Sales verifies them with a click. At three points further down the chain — Grading & Receiving, Pre-Cooling and Final Packaging — a staff member simply photographs the fruit and tags the agent, which reads the image with Claude’s vision capabilities, asks any follow-up questions, and turns the photo into a structured inventory entry by durian grade and weight, notifying the next team in line.

Loading, inspection and delivery run on the same pattern with forms instead of photos: a driver-assignment form, an inspection form with an approval checkbox, a loading-completion checkbox, and a delivery link the driver completes on arrival — each one firing automated notifications to every team that needs to know. Two ad-hoc modules sit on top of the standard flow: a rejection form available at Pre-Cooling and Final Packaging for quality or operational issues, and an escalation channel that alerts automatically on inventory discrepancies, rejections and departure cut-off timing, plus a standing reminder sent to every operational group an hour before a shipment’s scheduled departure.

Management sits above all of it with a live feed of AI-generated operational insight in its own group chat — completion rates, delivery volume in box counts, and rejection and inventory breakdowns by durian grade, weight and rejection reason — generated as a byproduct of the same workflow, without anyone compiling a report.

The results

• All nine stages of the standard workflow — Sales, Pre-Shipment, Grading & Receiving, Pre-Cooling, Final Packaging, Driver Assignment, Inspection, Loading and Delivery — run end-to-end through the same chat-based agent.
• Vision-based inventory capture at three checkpoints (Grading & Receiving, Pre-Cooling, Final Packaging) replaces manual data entry with a photo and a tag.
• Automated multi-party notifications fire at every stage completion, keeping Sales, Pre-Shipment, Loading, Delivery and Management in sync without anyone chasing status.
• Two ad-hoc modules layered on the standard flow: a rejection form at Pre-Cooling and Final Packaging, and an escalation channel covering inventory discrepancies, rejections and departure cut-offs, plus a one-hour pre-departure reminder to every operational group.
• Management gets standing, AI-generated visibility into completion rates, delivery volume and rejection/inventory breakdowns by grade, weight and reason — without pulling a report.

What it unlocked

The strategic point isn’t that Hernan replaced paperwork with a chatbot. It’s that a business whose product loses value by the hour now has a live, stage-by-stage record of every order — from the sales desk to the delivery truck — without adding headcount to keep pace with eighteen export markets. Because the same chat groups each team already used to coordinate are what capture the data, adoption didn’t require training staff onto a new system; it asks them to do what they were already doing — upload a photo, reply to a message — and lets the agent handle the data entry, grading breakdown and escalation judgment behind it.

“Our durians don’t wait for paperwork, and now our systems don’t either. Claude lets our teams turn a photo into a verified inventory record and an order into a tracked shipment, in the same chat group they were already using — that’s the kind of speed a perishable export business has to run on to serve eighteen markets at once.”

— Datuk Anna Teo, Founder & Group CEO, Hernan Corporation