# LedgerOS: Case Study | Gr8r Studio

> LedgerOS: AI agents run the routine finance work, people make the calls. Invoices, expenses, payments, cash flow and risk in one workspace, where five AI agents handle the routine work and hold anything unusual for a person to decide.

Source: https://gr8rstudio.com/work/ledgeros

# LedgerOS: AI agents run the routine finance work, people make the calls.

Invoices, expenses, payments, cash flow and risk in one workspace, where five AI agents handle the routine work and hold anything unusual for a person to decide.

Built by Gr8r for its own portfolio. Not client work.

Client

LedgerOS

Project

Finance operations platform

Platforms

Web app, desktop and mobile

- [Product Design](https://gr8rstudio.com/services/product-design)
- [Product Engineering](https://gr8rstudio.com/services/product-engineering)
- [AI Workflow Automation](https://gr8rstudio.com/services/ai-workflow-automation)

[View live demo](https://ledger-os-v2.vercel.app/)[Discuss your workflow](https://gr8rstudio.com/contact)

The problem

## Let agents do the routine work without losing control.

A finance team chases late invoices, codes card spend, approves vendor payments and watches cash, often in separate tools. Automation only helps if the team can see what each agent did and stop anything that looks wrong. The product had to make agent work visible and keep every risky decision with a person.

- 1
### Routine work is spread out
Chasing invoices, coding card spend and approving payments happen in different tools, every day.
“What still needs a person today?”
- 2
### Automation you can't see
If an agent acts in the background, the team can't check its work or stop it.
“What did the agent just do?”
- 3
### Risky payments slip through
Changed bank details or an unusual amount look normal in a long payment run.
“Should this payment go out?”

Where the day starts: cash position, what needs attention and what the agents found.

Each agent shows what it watches, where it reads from and what it did, with a pause button.

Problem map

## Six themes behind the product.

We grouped the finance team's problems into themes first, then gave each one an area and an agent.

- ### Receivables

  - Late invoices chased by hand
  - Duplicates paid twice
  - Cash applied late
- ### Spend

  - Card spend coded by hand
  - Missing receipts
  - Policy checked after the fact
- ### Payments

  - Approvals pile up
  - No reason beside each payment
  - Runs hard to plan
- ### Cash

  - Forecast updated monthly
  - Threshold breaches spotted late
  - Accounts seen apart
- ### Risk

  - Bank detail changes missed
  - Unusual amounts look normal
  - No one owns the hold
- ### Trust in AI

  - What did the agent do?
  - Can I stop it?
  - Who decides?

Design hypotheses we built the product around, drawn from the product brief. Not interview data.

Information architecture

## Seven areas, five agents.

Finance work on one side of the sidebar, the agents that watch it on the other, as in the app.

LedgerOS

1. Finance

  - Overview
  - Invoices
  - Expenses
  - Cash Flow
  - Payments
  - Risk
  - Transactions
2. AI agents

  - Invoice Agent
  - Expense Agent
  - Flow Agent
  - Payment Agent
  - Risk Sentinel
3. Account

  - Settings
  - Help

The workflow

## From the agent's alert to a person's decision.

1. 1
Detect
An agent flags a duplicate invoice, an unusual expense or a risky payment.
2. 2
Explain
The alert shows the signals and the score behind it.
3. 3
Decide
A person approves, holds or reviews; policy handles the rest.
4. 4
Record
Every action lands in the ledger with the agent that handled it.

The product

## Built around the decisions, not the data.

Every area pairs the numbers with the agent that watches them, and puts what needs a person at the top.

1. Invoices
### Receivables, chased for you
Aging by bucket, the accounts running late, and what the Invoice Agent matched, held or reminded today.

  1. 1Receivables aging, by bucket
  2. 2The accounts running late, by amount
  3. 3The Invoice Agent explains today's work in a sentence
  4. 4Every action it took, with the time
2. Payments
### One approval queue
Payments above the auto-approval limit wait in one queue, each with the reason it matches a purchase order or schedule.

  1. 1One queue for everything above the limit
  2. 2Each payment says why it matches
  3. 3Approve the batch in one click
  4. 4Upcoming payment runs, by date
3. Risk
### Holds that explain themselves
Risk Sentinel scores every outgoing transaction and shows why it held one: changed bank details, an unusual amount, an off-hours submission.

  1. 1What the alert is, in plain words
  2. 2The risk score beside the amount
  3. 3The signals behind the score
  4. 4Protection rules you switch on or off
4. Cash flow
### Where cash is heading
A forecast against the operating threshold, scenarios, accounts and the payments that will move cash next.

  1. 1The forecast shaded beside actuals
  2. 2Headroom above the operating threshold
  3. 3The Flow Agent explains what moved the forecast
  4. 4Balances by account

Interaction

## A held payment, decided by a person.

One real path through the product, captured frame by frame.

1. Trigger A payment is held Risk Sentinel holds PAY-4821 at a score of 87 and lists the signals behind it.
2. Transition Review the evidence The panel shows the score, why it was flagged and the agent's advice, with Block and Release side by side.
3. Result The person decides Blocking confirms the payment won't be sent. Open alerts and the blocked total update at once.

Dark and light

## Built for both themes.

Dark by default, with a full light theme from the same tokens. Drag to compare.

Dark Light

Style guide

## Colour and type.

Read from the product's own design tokens: quiet greys for the ledger, colour only for status and money moving in or out.

Background

HEX #131313

\--background

Danger

HEX #F47F79

- Card
#1A1A1A
\--card
- Foreground
#EDEDED
\--foreground
- Muted
#8F8F8F
\--muted-foreground
- Inflow
#3987E5
\--inflow
- Outflow
#D95926
\--outflow
- Success
#46D68F
\--success

Geist

- Regular
- Medium

Every screen

## The full product, desktop and mobile.

Real screens from the live demo, with demo data.

- Invoices
- Expenses
- Payments
- Overview on mobile · AI operations and agents on mobile
- Cash flow
- Invoice Agent
- Risk

Engineering

## Agents you can see, pause and audit.

Five agents, for invoices, expenses, cash flow, payments and risk, each have a live status, a coverage figure, an activity log and a pause control. Every list shares search, filters and status tabs. Add the stack and integration details once your engineer confirms them.

- Five AI agents with live status
- Pause any agent at any time
- Risk scores with visible signals
- Protection rules you switch on or off

Outcomes

## Designed for finance teams that want help, not surprises.

What the product demonstrably does. Measured business results will be added only with evidence and approval.

- ### One view of the money
Cash, payables, receivables and spend on one screen.
- ### Every agent action on record
Each transaction shows the agent that handled it.
- ### People make the risky calls
Unusual payments are held with their reasons until someone decides.

## Bringing AI into a finance workflow?

Gr8r helps teams design AI workflows people can trust, and build them as working software.

[Discuss your workflow](https://gr8rstudio.com/contact)

## Next project

- [SaaSCRMCloseCRMA structured CRM for busy sales teams: tasks, deals, records and automation that reps can scan in seconds. Read the case study ](https://gr8rstudio.com/work/closecrm)
- [AISaaSSellerOSOne workspace for marketplace sellers: sales, stock, shipments and profit, with an AI briefing. Read the case study ](https://gr8rstudio.com/work/selleros)
- [SaaSProductivityTask Management AppOne workspace for projects, tasks, deadlines and updates, from each person's list to the company timeline. Read the case study ](https://gr8rstudio.com/work/task-management-app)
- [ProcurementOnboardingVelunoSupplier onboarding with parallel reviews, documents, renewals and a supplier portal in one workspace. Read the case study ](https://gr8rstudio.com/work/veluno)
- [AIAutomationRelayA workflow automation workspace where AI agents run the work and people approve the risky steps. Read the case study ](https://gr8rstudio.com/work/relay)
- [DronesLogisticsSortieMission control for autonomous delivery drones, with a live 3D map of every flight. Read the case study ](https://gr8rstudio.com/work/sortie)
- [LogisticsOperationsAxleA fleet command centre for live tracking, dispatch, safety, compliance and maintenance. Read the case study ](https://gr8rstudio.com/work/axle)
- [HealthcareSaaSCendaraHealthcare claim denials worked to resolution: documents, appeals, reviews and payer replies. Read the case study ](https://gr8rstudio.com/work/cendara)
- [3DLogisticsLoadlineA transport operations platform with 3D load planning, dispatch and live fleet tracking. Read the case study ](https://gr8rstudio.com/work/loadline)
- [WebsiteTravelContrailFlight search where every flight opens a 3D model of its aircraft, so you choose your seat inside the cabin. Read the case study ](https://gr8rstudio.com/work/contrail)
- [WebsiteLearningKnowspaceA zoomable canvas of surprising facts, explored by topic, search and a small daily goal. Read the case study ](https://gr8rstudio.com/work/knowspace)
- [WebsiteWellbeingHinterlandAn illustrated mental health publication: topics, essays, short practices and a clear route to support. Read the case study ](https://gr8rstudio.com/work/hinterland)
- [WebsiteAgencyAtlasA design agency website told as a gallery visit, with old master paintings reworked as dot prints. Read the case study ](https://gr8rstudio.com/work/atlas)
- [UX auditProcurementVeluno UX AuditOur own supplier onboarding product, audited like a client’s: 13 findings, 3 high, and what to leave alone. Read the case study ](https://gr8rstudio.com/work/veluno-ux-audit)
- [UX auditHealthcareCendara UX AuditOur own claims product, audited like a client's: 12 findings ranked by impact, from sideways tables to hidden logins. Read the case study ](https://gr8rstudio.com/work/cendara-ux-audit)

Ask Ali