What AI tools did Factory use?

Factory used Claude 3 Opus, Claude 3 Haiku in this implementation within the Technology sector.

What business function does this AI use case address?

This use case focuses on Software Engineering, demonstrating how AI can drive impact in that area.

TechnologySoftware Engineering

How Factory Uses Claude to Automate Software Development Workflows

Factory built autonomous AI agents called Droids using Claude 3 Opus and Claude 3 Haiku to automate labor-intensive software engineering tasks at scale. These Droids handle code review, documentation, refactors, migrations, and feature requests across the entire software development lifecycle. Customers using Factory Droids saved 550,000 hours of development time and saw a 20% reduction in development cycle time.

Impact

550,000 hours

Development time saved

20%

Development cycle time reduction

Code churn reduction

Challenge

Software development organizations lacked tools that could handle the ambiguity and complexity of the full software lifecycle at scale, resulting in bottlenecks and inconsistent engineering practices.

Solution

Factory built autonomous Droid agents powered by Claude 3 Opus for complex reasoning and Claude 3 Haiku for high-volume tasks, automating code review, documentation, refactors, migrations, and feature requests.

Tools & Technologies

Claude 3 Opus Large Language Models

Claude 3 Haiku Large Language Models

What Leaders Say

“The Claude 3 model family is best-in-class for agentic engineering tasks. Claude 3 Opus outperformed comparable models by a fair margin.”
Eno Reyes, CTO and Co-Founder, Factory

Get the full context.

Full Story

Large-scale software engineering organizations face a persistent challenge: inconsistent practices, bottlenecks, and the sheer volume of routine tasks that slow down development teams. Factory, a software automation company founded in 2023, set out to change this by building autonomous AI-powered systems capable of navigating the full complexity of the software development lifecycle.

The challenge was significant. No existing tool could handle the ambiguity inherent in real-world software projects — navigating unclear requirements, diverse codebases, and the nuanced judgment calls that experienced engineers make daily. Factory needed a model family that could reason deeply for complex decisions and also operate at high speed for high-volume routine tasks.

Factory selected Anthropic's Claude 3 model family as the foundation for their Droid platform. Claude 3 Opus powers the complex reasoning and decision-making tasks, outperforming comparable models in agentic engineering benchmarks. Claude 3 Haiku handles high-volume, speed-sensitive operations where throughput matters most. Together, they enable Droids to perform code review, generate documentation, execute refactors and migrations, and implement feature requests autonomously.

The results have been transformative for Factory's customers. Across deployments, the platform has saved 550,000 hours of development time, reduced development cycle times by 20%, and cut code churn by 3x. These gains come not from replacing engineers but from eliminating the repetitive, time-consuming work that slows teams down and reduces focus on high-value problem-solving.

Similar Cases

Pfizer

93%

database reduction

Pfizer achieved a 93% database reduction and 20% cost avoidance by migrating their global SAP environment to S/4HANA on IBM Power10 infrastructure.

PharmaceuticalsTechnology

IBM Consulting

IBM Power Virtual Server

Jamf

Under 45 minutes

performance review skill build time

Jamf deployed Claude Enterprise across 16 departments, then built interactive workflow skills using Claude Cowork that transformed manual spreadsheet-based processes into guided, conversational experiences. Performance reviews that previously required months of effort are now built in under 45 minutes, and non-engineering teams independently create custom data dashboards.

Confluent, a data streaming platform company with 2,000+ employees and 4,000+ customers, deployed Glean to solve the knowledge fragmentation that came with rapid growth from 250 to 2,000+ employees across 20+ systems. Glean indexed the company's full tool stack — Slack, Salesforce, Confluence, and more — enabling instant knowledge retrieval across all teams. The result: 15,000+ hours saved monthly, a 13% increase in support team satisfaction, and over 70% employee adoption.

reduction in development time

Classmethod, a leading Japanese cloud integrator, deployed Claude Code across its engineering teams to address chronic developer shortages. The tool automated code generation, review, and testing workflows, reducing development time by up to 90% on specific tasks and cutting code review time by 80%.

increase in outbound leads

Lusha is a B2B sales intelligence platform with 1.5 million users and a database of over 200 million business contacts. By deploying Elasticsearch as both a full-text search engine and a vector database for AI-powered lead recommendations, Lusha helps customers generate 300% more leads, achieve conversion rates up to 10x higher, and realize return on investment of up to 1,000%.

engineering productivity improvement

Nextdoor, the neighborhood social network, deployed Glean as a unified Work AI layer embedded directly into the tools employees already use. Rather than mandating adoption, the team built a self-reinforcing learning loop of Slack channels, live office hours, and quick-win storytelling that turned early experimentation into company-wide AI habits — with engineering productivity gains of 2–3x and RevOps workflows shrinking from hours to minutes.

website creation time

Hostinger partnered with Anthropic to build Hostinger Horizons, an AI-powered platform that converts natural language prompts into complete, functional websites and applications. The solution eliminates the steep learning curve of traditional web builders, enabling non-technical users to create professional online presences in minutes instead of days.

rfp completion time reduction

Go1, an Australian learning and development content aggregator serving enterprise clients across Europe, the Middle East, and North America, deployed Writer’s Knowledge Graph and custom AI apps to automate RFP responses and scale marketing content production across multiple languages. The system cut RFP completion time by 50%, reduced time on content marketing guides by 75%, and delivered 40% time savings on marketing campaigns.

Technology

Writer AI Studio

Writer Knowledge Graph