What challenges did FloQast face before AI implementation?

Accounting teams face complex, manual reconciliation and audit processes at scale. Teams need accurate matching across bank statements and ERP data, plus controlled generation of audit annotations and rules.

Source

Scaled productionEvidence: Medium50/100

FloQast builds an AI-powered accounting transformation solution with Claude 3 on Amazon Bedrock

Use case typeDocument automationUpdated Jun 13, 2026

FloQast built an AI-powered accounting transformation solution using Anthropic Claude 3.5 Sonnet on Amazon Bedrock. The platform supports accounting transaction matching and AI Annotations for audit evidence, combining S3, Textract, Step Functions, Lambda, Bedrock Agents, and Guardrails. The article says the solution is integrated into the FloQast platform and designed to automate reconciliation and audit workflows at scale.

Organization: FloQast
Industry: Professional Services
Location: United States
Published: April 2025

Reported outcomes

Time: −38%

Time & speed

Time: −23%Time: −44%

Catalog median for time & speed deployments: −50% across 295 reported metrics. Compare benchmarks →

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Time: 38% decrease

AWS Machine Learning BlogApr 30, 2025Blog postInferred claimMedium evidence strength

The article reports a 38% reduction in reconciliation time, a 23% decrease in audit process duration and discrepancies, and a 44% improvement in workload management.

Normalized claim

Time: 23% decrease

AWS Machine Learning BlogApr 30, 2025Blog postInferred claimMedium evidence strength

The article reports a 38% reduction in reconciliation time, a 23% decrease in audit process duration and discrepancies, and a 44% improvement in workload management.

Normalized claim

Time: 44% decrease

AWS Machine Learning BlogApr 30, 2025Blog postInferred claimMedium evidence strength

The article reports a 38% reduction in reconciliation time, a 23% decrease in audit process duration and discrepancies, and a 44% improvement in workload management.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: FloQast
Provider: AWS
Maturity: Scaled Production
Linked source: AWS Machine Learning Blog

The article says the solution is integrated into the FloQast platform and designed to automate reconciliation and audit workflows at scale

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 3 of 3

1Accounting Automation
2Document Processing
3Agentic AI

FloQast embedded Amazon Bedrock into its platform for AI Transaction Matching and AI Annotations.
The solution uses natural-language rule generation, Amazon Bedrock Agents for multi-step orchestration, Amazon Textract to extract data from uploaded evidence, and Amazon Bedrock Guardrails to filter outputs.
Users can upload supporting documents to S3, have Textract extract the data, and then use Claude 3.5 Sonnet on Bedrock to apply audit rules and generate pass/fail annotations.

Technologies

Amazon Bedrock Amazon Bedrock Agents Amazon Bedrock Guardrails Amazon Textract Amazon S3 AWS Step Functions AWS Lambda

The article reports a 38% reduction in reconciliation time, a 23% decrease in audit process duration and discrepancies, and a 44% improvement in workload management.

Architecture

Users upload audit evidence documents into Amazon S3. Amazon Textract extracts data from the documents, then AWS Step Functions and AWS Lambda support sanitization and workflow processing. Application logic sends the extracted data to Anthropic Claude 3.5 Sonnet on Amazon Bedrock. Amazon Bedrock Agents orchestrate multi-step accounting tasks, and Amazon Bedrock Guardrails filters annotation outputs before they are stored and reviewed in the FloQast platform.

Implementation partners1

Anthropic

Sources & evidence1

Evidence: Medium50/100Evidence strength