← Back to Qonto builds Claude-powered agents that run payroll 5x faster and cut invoice creation time 3x

Source proof for Qonto builds Claude-powered agents that run payroll 5x faster and cut invoice creation time 3x

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

13 fields supported

Title

Qonto builds Claude-powered agents that run payroll 5x faster and cut invoice creation time 3x

derived · high
…agents drafting every invoice and the customer confirming before it's sent Runs payroll 5X quicker: agents prepare every pay slip, the customer approves before anything sends, an…

Description

Qonto, a European business banking platform serving over 600,000 businesses across eight markets, built AI agents on Claude Opus 4.5/Sonnet/Haiku via Amazon Bedrock that prepare bulk payroll transfers, draft client invoices from a CSV, and answer cash-flow questions, with the customer always giving final approval before money moves. Since launching six weeks after the November 2025 project start, the agents send bank transfers 2x faster, cut invoice creation time 3x, run payroll 5x quicker, and have processed customer-approved transfers as large as €100,000.

derived · high
…;s AI agents drafting them and the customer confirming before they're sent More than 600,000 businesses across eight European markets run their banking and bookkeeping on Qonto . In late 2025, its 15-person AI Lab built agents into the app to take over the r…

Company

Qonto

classification · high
…ere Ask questions about this page Copy as markdown Case study | Claude Platform How Qonto delegates financial admin for small businesses with Claude on Amazon Bedrock Industry: Financial services Company size: Medium Product: Claude Platform Part…

Industry

Financial Services

classification · high
…to delegates financial admin for small businesses with Claude on Amazon Bedrock Industry: Financial services Company size: Medium Product: Claude Platform Partner: AWS Location: EMEA 2X fa…

Problem

Qonto customers spend on average up to 8 hours every month on financial admin tasks: manually running payroll transfers one pay slip at a time and re-keying client invoices one at a time from a CRM or spreadsheet, work that became a bigger pain as transaction volume grew, while cash flow lived in hand-built spreadsheets with account data going unused for decisions.

derived · high
…ce team behind them, and financial admin has become a hidden tax on their time: they spend on average up to 8 hours every month on financial admin tasks. "They are not finance experts and they don't want to be," said Sophie Corn…

Solution

Qonto's 15-person AI Lab built agents into the app, routing each step by complexity to the right model on latency, performance and cost: complex missions run on Claude Opus 4.5 and Sonnet while simpler steps go to smaller models including Haiku, accessed through Amazon Bedrock with GDPR and EU AI Act compliance handled at the provider level, with an operator agent handling high-frequency tasks like payroll and invoicing end to end and an analyst agent answering questions about past and present transactions.

derived · high
…ght European markets run their banking and bookkeeping on Qonto . In late 2025, its 15-person AI Lab built agents into the app to take over the repetitive parts of that work: preparing payroll transfers, dr…

Technology

Claude Opus 4.5, Claude Sonnet, Claude Haiku, Amazon Bedrock, Model Context Protocol

classification · high
…ight model on latency, performance, and cost. The agents' complex missions run on Claude Opus 4.5 and Sonnet, while simpler steps go to smaller models, including Haiku. Access runs through Amazon Bedrock, with GDPR and EU AI Act compliance handled…

Deployment model

cloud

classification · high
…Opus 4.5 and Sonnet, while simpler steps go to smaller models, including Haiku. Access runs through Amazon Bedrock, with GDPR and EU AI Act compliance handled at the provider level. Claude also stood out for how well it integrates with Amazon Bedrock, from stru…

Deployment options

cloud

classification · high
…Opus 4.5 and Sonnet, while simpler steps go to smaller models, including Haiku. Access runs through Amazon Bedrock, with GDPR and EU AI Act compliance handled at the provider level. Claude also stood out for how well it integrates with Amazon Bedrock, from stru…

Headline outcome

derived · high
…agents drafting every invoice and the customer confirming before it's sent Runs payroll 5X quicker: agents prepare every pay slip, the customer approves before anything sends, an…

Business value

Bank transfers now send 2x faster with no manual beneficiary search, amount entry or reference copying; client invoice creation takes 3x less time; payroll runs 5x quicker, turning a 15-to-20-slip run into one bulk transfer; customers have delegated transfers as large as €100,000; and one customer generated over 500 monthly invoices in a single batch.

derived · high
…numbers. The agents' most complex work runs on Claude. With Claude, Qonto: Sends bank transfers 2X faster, with no manual beneficiary search, amount entry, or reference copying, then waits for the customer's final approval before the money moves Cuts…

AI capabilities

Agentic AI, Large Language Models

classification · high
…ght European markets run their banking and bookkeeping on Qonto . In late 2025, its 15-person AI Lab built agents into the app to take over the repetitive parts of that work: preparing payroll transfers, drafting invoices, answering questions about the…

Use case type

Workflow automation

classification · high
…ight. Each goal became an agent that lives in the Qonto app and runs on Claude. The operator agent takes the high-frequency work, routing each request to a specialized agent scoped to that task, which handles it end to end. A customer running payroll drags 15 or 20 pay slips into Qonto; the agent prepa…
Capture details
Captured
23 Sept 2026, 05:31 UTC
Extractor
fetch-strip@1
Snapshot hash
d780beac8da5d0a18e960da32f744398e6233e92590eb40e9751e3ee8fa33b5f