How Mercos cut 70% of accounts payable work with invoice automation

The automation: What we built together

They started with AP, the biggest source of manual work.

Mercos didn't want another tool to manage. They wanted to build their own AP automation tool, something flexible, fast, and finance-led.

So they used Abstra to build one core flow for invoice processing.

Here's how it works:

Some invoices (NFs), even when posted automatically, require manual completion. For example, occasional expenses (where no standard is registered in the allocation table) and cost splits (which depend on specific criteria).

• 📥 Input: Incoming invoices (PDFs) received via Gmail
• 🤖 Abstra automates:
  • Extracting attachments
  • Validating if the file is an actual invoice
  • Extracting fields like Tax ID, amount, and issue date
  • Launching data into Granatum ERP
  • Sending alerts via Slack
• 📤 Output: Clean, structured invoice data and documents, automatically synced with ERP and ready for AP review

That's it. This end-to-end workflow is a real example of automated invoice entry in action. Jonattan built and tested everything himself, no devs needed.

"This wasn't plug-and-play. It was thoughtful design. And it worked."

It took just under 2 months to get from idea to production. That included prototyping, validation, and migrating the full flow into production using Abstra.

AI played a key role throughout this flow. Abstra uses AI models to read and extract invoice data like Tax ID, value, and issue date, removing the need for templated OCR or manual mapping. But more than that, AI also supports the finance team during development.

Jonattan used Abstra's hybrid builder, which combines natural language prompts, drag-and-drop logic, and Python, to write and test code faster, without being a developer. That means faster prototypes, fewer bugs, and a better feedback loop.

Why it worked: Finance-led, not IT-led

This wasn't a dev-heavy rollout. Jonattan built and tested the AP workflows himself.

What really made this click was the combination of flexibility (Python) and guidance (AI). With Abstra's AI-powered interface, the team could generate and adjust code, ask for help in natural language, and iterate quickly, all without relying on engineering. It turned finance analysts into builders.

That shift in capability is what unlocked the team's ability to build and maintain automations on their own. And it's a big reason why this worked, not just as a workflow improvement, but as an operating model change.

Only one integration point, Gmail configuration, required light support from IT and Google Workspace partners. Everything else was built and maintained internally.

Plus, it wasn't just the tool. It was the mindset:

• They experimented early
• They weren't afraid to ship v1
• They gave analysts the tools to build

Abstra gave them the structure to test, tweak, and deploy quickly.

"Even with little Python programming knowledge, I can lead this thanks to my background and Abstra's support. That's a game changer."

A smarter model for scaling finance

The finance team at Mercos isn't trying to build a robot army. They're building something more powerful: a team that owns its automation.

They've proven that invoice automation software can do more than save time, it can change how a team works. And with Abstra, they've done it without extra headcount, IT dependencies, or compromise.

"We're turning the finance team into a product team. One that builds, tests, and scales ops without depending on anyone."

Carlos has a clear vision. ERP is the system of record. But intelligence, that should live in the finance team. His plan is to eliminate all manual data entry in AP by the end of the year, then expand automation across the finance stack.