MOTHERSHIP

[work] aquaculture

MAS Aqua.

High-stakes aquaculture ops, made manageable.

MAS Aqua is one of Andhra Pradesh's leading shrimp seed hatcheries: a real technical business run by seasoned operators, over nothing but phone calls and memory. We embedded, extracted the tribal knowledge, and encoded it into a typed operating system with portals, atomic capacity, payment-linked orders, dispatch intelligence, and an agent layer on the same endpoints.

4 portals86 endpoints18 tables219 commits
typed hatchery os

[01] operating reality

The business ran through humans.

Calls, WhatsApp, memory, bank checks, and production Sheets.

Start with respect: MAS is not a company that needed rescuing. It is veterans managing biology, logistics, and money simultaneously, every day. A farmer does not place an order; he calls someone he knows by name. A distributor buys bulk capacity first and names his farmers later. Accounts confirms payments by checking the bank. Dispatch splits by flights and trucks, because the real world is split.

What they were carrying is the tax every traditional manufacturer pays: dynamic data shifting with every invoice, every call, every swing in production volatility. Every step a human. Every handoff a place where the day can go wrong.

[02] the paradigms

We made the failure modes structurally impossible.

Seeds are not SKUs. They are perishable production capacity.

Capacity is booked atomically at the database level: two buyers, one remaining slot, the database decides and exactly one wins. Overselling stops being a discipline problem and becomes an impossibility. Orders confirm themselves when money moves, with advances and partial balances tracked cumulatively across transactions. Dispatch knows the difference between a flight and a truck, because they are different operations with different economics.

The production floor kept its Google Sheets. We made them a live output of the source of truth: workflow untouched, data finally trustworthy. And every action in the system carries who did it, because when livestock and lakhs move daily, the audit trail is how veterans trust a new system.

[03] operator surfaces

Every actor got the interface they needed.

Telugu farmers. Gujarat distributors. Local AP distributors. Admin. Flight dispatch. Truck dispatch.

Farmers got Telugu self-service. Gujarat distributors got the two-phase bulk-order and farmer-allocation flow that exists in no software product on earth, because nobody who builds software has sat in that office. Local distributors got the same logic in Telugu with truck delivery. Admin got a single command center: live capacity, payments, reallocations, and audit trails, one screen instead of five phone calls.

THE REST OF THE ORGANIZATION · EVERY ROLE, ASSISTEDhumans decide · agents chase, remind, reconcile

Distributors

self-serve portals, bulk now · allocate later
Collections agent nudges the late, spares the loyal

Admin team

one dashboard: orders, payments, capacity
Capacity agent frees expiring holds in time

Dispatch coordinators

flights + trucks, separate PIN-gated views
Dispatch agent WhatsApps what's missing for tomorrow

Production floor

still reads Google Sheets, workflow unchanged
auto-synced from the source of truth, manual entry gone

Field sales

farmer relationships, on the ground
Win-back agent routes leads: orders every 6 weeks, overdue

[04] agent layer

Build the surface for humans. Wrap it for agents.

The dashboard is one client of the 86 endpoints. Agents are another.

The pattern is the same one we run everywhere: the visual surface for operators first, then that same tool wrapped as an agent surface, so agents traverse the exact actions the operators do. A company brain in WhatsApp answers the CEO from live state: what is blocking a delivery date, whose payment is pending, where cash stands.

Autonomous workers handle the routine: collections that knows which buyer always pays late but always pays, capacity protection that nudges pending orders before a hold expires, dispatch resolution that flags tomorrow's missing flight details. And telephone agents answer farmers in Telugu, check capacity, book the order, and confirm on WhatsApp, for the farmers who will never open a browser.

Eagle Eye — command deck
CAPACITY · NEXT 7 DAYS
PAYMENTS3 late · 1 to nudge
DISPATCH · TOMORROW2 flights · 1 truck
What's blocking Feb 15?
Feb 15 · delivery capacity92% booked
ND-1042distributor · PENDINGNudge
ND-1047distributor · PENDINGNudge
LF-0981farmer · expires in 4hLet expire
live from the same system the portals write to
Nudge both distributors.
✓ Reminders sent on WhatsApp. Follow-up scheduled in 24h. Both actions logged to the audit trail.
answers are live interface, not text · every button hits the same 86 endpoints
The CEO's command deckask, see, act · one surface, on any screen

ONE SYSTEM

86 endpoints · 18 tables
atomic capacity booking
payment-linked confirmation
dispatch: flights + trucks
Google Sheets kept in sync
audit on every action
the tribal knowledge, encoded

AGENTS · NIGHT AND DAY

  • Eagle Eye answers the CEO
  • Collections knows who to nudge
  • Capacity frees expiring holds
  • Dispatch chases missing flights
  • Win-back spots lapsed farmers
  • Voice AI takes farmer calls
MAS Aqua · voice line — live call · Telugu
నేను next week ki 50,000 seeds కావాలి. 25 PPTI need 50,000 seeds next week, 25 PPT
సరే. Feb 12 available. book చేయమంటారా?Feb 12 is available. Shall I book it?
అవునుyes
✓ Booked
50,000 seeds · 25 PPT · Feb 12
capacity locked, atomically
payment link sent on WhatsApp
no human picked up the phone
50 of these calls can happen at once
The farmer's phoneorders in Telugu, over a normal call

[05] the outcome

A high-stress business, made manageable.

219 commits. 86 endpoints. 18 tables. Four portals. One company brain.

4portals
86API endpoints
18tables
219commits
36pages
100%actions attributed

Orders that take minutes instead of hours of phone tag. Double-selling that is architecturally impossible. A CEO who asks his phone instead of asking around the office. The operators keep the judgment, the relationships, and the craft. The system carries everything else.

The architecture ports. Poultry, textiles, dairy, agri-inputs, construction materials: every traditional manufacturer running on phone calls and one person's memory is sitting on the same gap MAS was.

[next] explore

Adjacent capabilities.

Powered by Eagle Eye, Workforce, and The Engine.