Rizal

I've been thinking about a fundamental problem in ag finance that I think sometimes doesn't get talked much about.

When you insure a car, the insurance company knows everything. Make, model, year, mileage, accident history. They price your policy based on specifics.

But when you insure a farm? They treat the whole thing as one block. 1,000 acres = 1,000 acres. Doesn't matter if half those fields are thriving and half are struggling. Doesn't matter if the farmer claims 1,000 acres but only planted 600.

Same thing with lending. A bank writes a loan for a farm. The loan officer might visit 15% of that land. Takes some photos in what I like to call “truck window” inspection. Signs off. Then everyone just hopes it works out.

That's more of a guess instead of risk management.

When you can't measure risk accurately, you price in uncertainty. Banks charge higher rates. Insurance gets expensive. Farmers who are actually doing great work subsidize the ones who aren't.

But I found a company that is trying to solve this. They figured out how to do it at scale using satellites and AI.

Here's what they built.

Rizal uses daily satellite monitoring and AI to give agricultural lenders real-time visibility into every financed acre, turning farmland into transparent, trackable assets.

Let's start with the basic problem: ag lenders are flying blind.

When a bank finances farmland, they have almost no real-time visibility into what's actually happening in the fields. A loan is based on projections and plans, but conditions change fast. Drought hits. Pests show up. Markets shift. By the time anyone notices a problem, it's often too late to fix it.

Physical inspections are expensive and infrequent. A loan officer might visit once at planting, maybe once mid-season. That's it. Everything else is self-reported.

This creates massive information asymmetry. And in lending, information asymmetry equals risk. Risk equals higher costs. Higher costs mean fewer farmers can access credit.

Rizal is trying to flip this entire equation.

Their platform turns credit records and field data into a verified digital portfolio. Upload your loan documentation, map the financed acreage, and suddenly every field shows up on a centralized dashboard.

But here's where it gets interesting: they're not just mapping farms. They're monitoring every acre, every day, using satellite imagery.

Think about what that means. Instead of financing "John's 1,000-acre farm," lenders can now see John's northwest cornfield (performing well), his southeast soybean field (showing early drought stress), and his southern pasture (not planted at all this season).

The system tracks NDVI (crop health), biomass levels, soil moisture, and weather patterns. When something goes wrong - drought stress, pest damage, flooding - the AI flags it immediately.

For example: A wheat lender in their case studies noticed underperformance mid-season. Rizal's platform caught early nutrient stress. The lender sent a technician who confirmed the issue and recommended foliar fertilizer and irrigation adjustments. The crop recovered. The loan stayed current.

Without that monitoring? That stress would've compounded quietly until harvest revealed a 30% yield loss. By then, it's too late. The farmer's income drops. The loan payment gets missed.

So Rizal also gives lenders the ability to intervene before problems become disasters.

Their mobile app adds another layer. Farmers and field inspectors can upload geo-tagged photos and ground-truth data, even offline. This fills in the gaps satellite imagery can't catch and creates an auditable trail for every field visit.

The platform also builds what they call "Acre Credit Records" - essentially a credit history for farmland itself. What's been planted. What yielded. What repayment looked like. Over time, this data turns land into a transparent, financeable asset that unlocks better terms for farmers who perform well.

Here's a real example of how this changes lending:

A bank issued a $7 million loan tied to 12,500 acres. Before releasing the second tranche, they used Rizal to verify planting. The platform flagged 5,000 acres that weren't planted. The bank required geo-tagged proof before releasing funds.

They adjusted the loan to actual acreage. Avoided massive under-collateralization. And the loan repaid in full.

Another case:

Flood damage during growing season. Traditionally, this means delayed claims, farmer-insurer disputes, and weeks of back-and-forth. Rizal flagged the flooded fields in real-time. Farmers immediately alerted insurers with satellite evidence. Claims verified quickly. Payouts processed fast.

The cost savings are somewhat dramatic. Banks report 8x reduction in oversight costs by digitizing inspections and monitoring. No more sending loan officers on daylong field visits for routine checks. Physical inspections only happen when the platform flags something that needs eyes on the ground.

Rizal is monitoring over 270,000 paid acres and has supported more than $100 million in loans. They're seeing 15% reduction in early delinquencies because problems get caught and addressed before they snowball.

What Rizal is really selling isn't satellite data or AI models. It's certainty. They're removing the information gap that's made agricultural lending risky and expensive for everyone involved.

Deep dive into how banks are using satellite data to automate farm crediting, improve risk assessment, and align with environmental standards. Explains why this tech is finally affordable and mainstream. [8 min read]

Explains how radar satellites enable continuous monitoring regardless of weather or daylight. Great breakdown of why ground-based control isn't viable at scale and how satellite monitoring builds trust between lenders and farmers. [7min read]

Explores how satellite data quality and availability has improved dramatically, enabling precision agriculture applications that maximize yields and ward against disease. Shows the progression from traditional notebook farming to fully digitalized operations. [9 min read]

Two quick things:

- Enzo