Ricardo Freire
All work

Ordines

An operations platform for accounting firms that I designed and built with AI agents. It runs in production at a real firm.

Type
Independent product
Role
Product designer & builder
Stack
React, Node, PostgreSQL, GCP
Period
2026 – ongoing
Ordines overview: overdue obligations and what is due this week
Problem

Nothing should expire without warning

A Brazilian accounting firm tracks hundreds of recurring tax obligations, and every client has its own calendar.

Deadlines depend on the tax regime, the business activity code (CNAE), the city and its holidays. Most firms run on a heavy accounting system plus spreadsheets and WhatsApp. A missed date means a fine for the client, and often a lost client for the firm.

Research

Benchmark first, then say no

I mapped two market leaders feature by feature, Omie G-Click and HubStrom, and later a third competitor screen by screen. Two decisions came out of it:

  • Don’t copy the complexity. G-Click has about 13 task statuses and its own rule language. A feature only gets in if it adds to the flow and stays invisible to anyone who doesn’t use it.
  • Protect what nobody else has. Matching activity code and regime to obligations automatically had no equivalent in the products I researched.
Three promises, in this order: nothing expires without warning, a view of the whole firm, nothing goes out wrong.

Ordines is a control layer on top of the firm’s accounting system. It checks and audits, and it doesn’t try to replace that system.

Alert center with ownerless count, alerts by origin, control coverage and a list of overdue items
The first promise in the product: one alert center for certificates, licenses, powers of attorney and documents. Every item has an owner, and it only leaves the list when the document is renewed. Demo data.
Design

From soft and organic to editorial

My first direction was warm and organic. I moved to an editorial direction for one reason: to make the information stand out. Sober colors and strong type, so deadlines, numbers and the next action are the first thing people see.

Obligations board in the shipped editorial design: shipped: editorial
Obligations board in the shipped editorial design: first direction: terra
First direction: TerraShipped: Editorial
The obligations board: the first concept and the shipped product. Demo data.
Decision 1

Every card tells one story

Problem
Dashboards full of charts made people interpret the data instead of acting on it.
Change
Each card follows the same structure: a small label, one big number and a sentence that says what to do. “Four obligations are overdue. The oldest has been stuck for a day. Resolve them first.”
Why
An accountant opening the tool at 8 a.m. needs the next action, not a chart to read.
Powers of attorney page explaining what depends on them and what still blocks
The same pattern on every page. The headline says what’s wrong, then why it matters: “without a valid power of attorney, Ordines is blind.” Demo data.

The design system (tokens, Inter Tight for numbers, components like SelectPill and DatePickerPill) is written down as rules the coding agents have to follow, such as “never a native select” and “drawers for editing”. That keeps the UI consistent even when an agent writes the code.

In production

Beyond tasks: licenses and the firm’s revenue

Once the task engine worked, the firm asked for two things it was tracking in spreadsheets: business licenses for client chains, and a view of its own client portfolio and fees.

Decision 2

A chain of stores is one view, not ten records

Problem
Fire department permits, health licenses and operating permits for every unit of a client chain lived in a spreadsheet with dates nobody owned.
Change
Each chain becomes one page: who has to file in the next 90 days, where the risk is by license type, and a grid of units × licenses colored by urgency. The client gets access too, so they can upload the renewed document.
Why
The question is never “when does this license expire?” but “who acts, and what is late?”
License network page with risk by owner, by license type and a units by licenses grid
Licenses for a client chain: risk by owner and license type, then each unit’s licenses by urgency. Demo data.
Decision 3

Charts that say what they mean

Problem
The partners’ fee spreadsheet had every number and no conclusions.
Change
Every chart opens with one sentence that reads it, like “a Lucro Real client pays on average 5.4× a Simples client”, plus insight cards above the charts and a table view under each one. Fee values are visible only to partners.
Why
Partners decide pricing and priorities. They need the conclusion, and the data to check it.
Portfolio dashboard with fee totals, insight cards and charts by tax regime, ABC curve and fee range
Portfolio dashboard, visible only to partners: totals, written insights, and charts that each start with a sentence. Demo data.
Activity matrix table with area, type, sphere, frequency, taxation and clients
The activity matrix defines which tasks the system can generate, by area, frequency and tax regime.
Mobile

Built for the phone first

Ordines was designed for the phone from the start, not adapted to it afterwards.

It installs from the browser to the home screen and opens full screen, without the browser around it. Navigation moves to a bar at the bottom, and dense screens like the portfolio panel reflow to fit.

  1. 01It opens in the phone’s browser
  2. 02One tap adds it to the home screen
  3. 03From there it opens full screen, like an app
  4. 04Conversations, client by client
  5. 05The portfolio panel, for partners only
Screens captured from the staging environment at phone width. Clients, people and amounts are fictional.
Safety

Design for actions you can’t undo

Decision 4

Automation starts switched off

Problem
Ordines queries government services with the client’s digital certificate and creates tasks automatically. One wrong switch can create hundreds of tasks or run billable queries.
Change
Every engine starts off, per firm and per client. Turning on the task engine for an area requires 100% coverage, a preview from the last 48 hours and typing the area’s name. Turning it off is instant and keeps existing tasks.
Why
In a business built on trust, one extra click costs far less than one wrong automatic action.
Decision 5

Processes drawn, not written

Problem
Each firm’s know-how lived in people’s heads and in long text instructions. Every analyst ran payroll a slightly different way.
Change
A custom SVG canvas to draw work instructions with steps, decisions, evidence, notes and links to other processes. Once published, each generated task keeps a frozen copy, so editing a process never changes work already in progress.
Why
A drawing is the language the team already used on whiteboards, and it turns into a task checklist automatically.
Work-instruction canvas showing a payroll process with three input paths, a review step and a yes/no decision
A real payroll process in the work-instruction builder: three ways the data arrives, one review, and a decision on whether adjustments are needed. Firm names replaced.
AI workflow

How I build with agents

Claude Code implements, Codex reviews, and I decide anything that can’t be undone.

1 · SpecEach feature starts as a written spec with acceptance criteria.
2 · BuildClaude Code implements and runs typecheck, tests and build.
3 · ReviewCodex reviews in read-only mode and returns Approved or Fix. Max two rounds.
4 · Human gateI approve every push, deploy, migration, secret and cost.
63AI review records in the repository
130+Automated test files
1Firm in production, on its own isolated cloud project

The agents work from shared context: a CLAUDE.md that acts as the source of truth, separate frontend and backend rules, a spec per feature and a dated decision log. When something breaks, the lesson goes into that context. After a cookie change broke login for a few minutes, every auth change now requires a Safari test and a check against production before release.

Outcome

In production, and still growing

Ordines has run in production at a real accounting firm since September 2026, with tasks and the Kanban board, client portfolios and fees, licenses and documents with expiry dates, and integrations with Brazil’s federal and state tax services.

What it shows: with AI in the loop, a designer can take a product from benchmark to production, as long as the judgment stays human.