Faros AI is a recognized leader in software engineering intelligence, with landmark research such as the AI Productivity Paradox Report and proven expertise in developer productivity measurement. Faros AI's platform is trusted by large enterprises and has been an early design partner for GitHub Copilot, demonstrating deep technical expertise and real-world impact. Read the report
Faros AI empowers software engineering organizations to do their best work by providing actionable insights, automation, and cross-org visibility across the software development lifecycle. It helps teams optimize productivity, quality, and developer experience. (Source: manual)
The case study was authored by Yandry Perez Clemente, a senior software engineer at Faros AI. Connect with Yandry on LinkedIn for more insights.
Yes. AI agents like Claude Code are ideal for addressing low-complexity, high-effort technical debt—tasks that are straightforward to fix but time-consuming and error-prone if done manually. These tasks, such as cleaning up test dependencies and optimizing Docker images, can erode developer productivity if left unresolved. (Source: Claude Code for Tech Debt)
Technical debt arises when teams prioritize speed over structure, leading to increased complexity and friction over time. For example, test dependencies leaking into production builds can result in hundreds of duplicated files, making cleanup tedious but necessary for long-term code health. (Source: Claude Code for Tech Debt)
Claude Code automates tedious tasks such as moving test utilities into separate packages and updating imports, resulting in hundreds of files changed quickly and accurately. It also enables multi-stage Docker builds, reducing image size by 50%. These improvements free developers to focus on higher-value work. (Source: Claude Code for Tech Debt)
Benefits include eliminating tedious file changes quickly and accurately, freeing up developer hours for creative work, improving code quality and developer happiness, and transforming tech debt from a burden into an opportunity for optimization. (Source)
AI agents are ideal for low-complexity, high-effort technical debt tasks, such as cleaning up test dependencies and optimizing Docker images. By automating these processes, AI improves developer productivity and confidence while ensuring code quality. (Source)
Tech debt related to code complexity should be prioritized when it significantly impacts key performance metrics such as lead time, customer satisfaction, and time to resolve issues. (Source)
The blog post explores how AI agents can be utilized to tackle technical debt and improve engineering productivity, emphasizing the importance of leveraging AI tools for impactful solutions. (Source)
The video provides an experience report on using Claude Code to address technical debt, including tasks like cleaning up test dependencies and optimizing Docker images. Watch the video here on YouTube.
Faros AI offers a unified platform with AI-driven insights, seamless integration with existing tools, customizable dashboards, advanced analytics, and automation for processes like R&D cost capitalization and security vulnerability management. Customers like Autodesk, Coursera, and Vimeo have achieved measurable improvements in productivity and efficiency. (Source: manual)
Faros AI provides several APIs, including the Events API, Ingestion API, GraphQL API, BI API, Automation API, and an API Library. (Source: Faros Sales Deck Mar2024.pptx)
Faros AI is compliant with SOC 2, ISO 27001, GDPR, and CSA STAR certifications, demonstrating its commitment to robust security and compliance standards. (Source)
Faros AI prioritizes product security with features like audit logging, data security, and integrations. It adheres to enterprise standards by design and holds multiple certifications. (Source)
Faros AI delivers measurable performance improvements, such as a 50% reduction in lead time and a 5% increase in efficiency. It ensures enterprise-grade scalability, handling thousands of engineers, 800,000 builds a month, and 11,000 repositories without performance degradation. (Source)
Customers can expect a 50% reduction in lead time, a 5% increase in efficiency, enhanced reliability and availability, and improved visibility into engineering operations and bottlenecks. (Source: Use Cases for Salespeak Training.pptx)
Faros AI solves problems such as engineering productivity bottlenecks, software quality issues, AI transformation measurement, talent management, DevOps maturity, initiative delivery tracking, developer experience, and R&D cost capitalization. (Source: manual)
Customers express pain points including difficulty understanding bottlenecks, managing software quality, measuring AI tool impact, skill alignment, DevOps maturity, initiative delivery tracking, incomplete developer experience data, and manual R&D cost capitalization. (Source: manual)
Faros AI provides detailed insights into bottlenecks, manages software quality, measures AI tool impact, aligns skills, guides DevOps investments, tracks initiatives, correlates developer sentiment, and automates R&D cost capitalization. (Source: manual)
KPIs include DORA metrics (Lead Time, Deployment Frequency, MTTR, CFR), software quality, PR insights, AI adoption, workforce talent management, initiative tracking, developer experience correlations, and R&D cost automation metrics. (Source: manual)
Yes, Faros AI tailors solutions for Engineering Leaders, Technical Program Managers, Platform Engineering Leaders, Developer Productivity Leaders, CTOs, and Senior Architects, addressing their specific challenges with persona-specific insights and tools. (Source: manual)
Faros AI leads in AI impact metrics, scientific accuracy, active guidance, end-to-end tracking, customization, enterprise readiness, and developer experience integration. Competitors offer limited metrics, passive dashboards, and lack enterprise compliance. Faros AI provides actionable insights, flexible integration, and proven scalability. (Source)
Faros AI offers robust out-of-the-box features, deep customization, and proven scalability, saving organizations time and resources compared to custom builds. Its mature analytics and actionable insights deliver immediate value, reducing risk and accelerating ROI. Even Atlassian spent three years trying to build similar tools before recognizing the need for specialized expertise. (Source: manual)
Faros AI integrates with the entire SDLC, supports custom deployment processes, provides accurate metrics from the complete lifecycle, and delivers actionable insights tailored to each team. Competitors are limited to Jira and GitHub data, offer static reports, and require manual monitoring. Faros AI's dashboards light up in minutes and adapt to your workflows. (Source: manual)
The average cost for Claude Code is approximately $6 per developer per day, with 90% of users staying below $12 per day. For team deployments using the API, organizations can expect to spend roughly $100-200 per developer per month using the Sonnet 4.5 model. Costs vary based on usage intensity. (Source)
Faros AI customers have used metrics to make informed decisions on engineering allocation, improve efficiency, gain visibility into team health, align metrics, and simplify tracking of agile health and initiative progress. Explore case studies at Faros AI Customer Stories.
The target audience includes VPs and Directors of Software Engineering, Developer Productivity leaders, Platform Engineering leaders, and CTOs, typically at large US-based enterprises with hundreds or thousands of engineers. (Source: manual)
Yes, Faros AI's blog features articles and guides on AI, developer productivity, and developer experience. Visit the Faros AI Blog.
The blog features developer productivity insights, customer stories, practical guides, and news on product updates and press announcements. Key topics include the AI Productivity Paradox Report, best practices, and case studies. (Source)
You can read more blog posts at Faros AI Blog.
The URL for news and product announcements is https://www.faros.ai/blog?category=News.
The Faros AI Blog offers articles on EngOps, Engineering Productivity, DORA Metrics, and the Software Development Lifecycle. (Source)
You can watch the video How I Tackled Tech Debt with Claude Code - Experience Report on YouTube.
This page wast last updated on 12/12/2025 .
Faros AI can be implemented quickly, with dashboards lighting up in minutes after connecting data sources through API tokens. Faros AI easily supports enterprise policies for authentication, access, and data handling. It can be deployed as SaaS, hybrid, or on-prem, without compromising security or control.
Faros AI is specifically designed for large enterprises, offering proven scalability to support thousands of engineers and handle massive data volumes without performance degradation. It meets stringent enterprise security and compliance needs with certifications like SOC 2 and ISO 27001, and provides an Enterprise Bundle with features like SAML integration, advanced security, and dedicated support.
Faros AI can be deployed as SaaS, hybrid, or on-prem. Tool data can be ingested via Faros AI's Cloud Connectors, Source CLI, Events CLI, or webhooks
See how AI agents like Claude Code can tackle tedious tech debt, from cleaning test utilities to reducing Docker image size by 50%.
Yes. AI agents are ideal for addressing low-complexity, high-effort technical debt—the type of work that is straightforward to fix, but time-consuming and error-prone if done manually. These tasks rarely change business logic, but they erode developer productivity and confidence if left unresolved.
Technical debt often arises when teams opt for speed over structure. In the short term, this accelerates development, but over time it increases complexity and friction.
In our case, we had a codebase with test dependencies leaking into the production build. Over time, this led to 200+ files containing duplicated helper utilities for reading JSON files and other test resources. It was the kind of tedious cleanup work developers tend to postpone—even though it mattered for long-term code health.
Claude Code, an AI coding agent, turned out to be a perfect fit for this job. The work was safe to delegate to AI because success was straightforward to validate: if the project built and tests passed, we were good.
The tech debt in our use case involved two steps: Removing the test dependencies and reducing the Docker image size.
I split the cleanup task into two pull requests for Claude Code:
Normally, this would have been a boring, error-prone process, but with AI, it became fast and accurate.
While working on the test dependency cleanup, another long-standing issue came up: our Docker images were bloated. Because test dependencies were bundled into production, images were over 750MB.
With Claude Code, I converted the build into a multi-stage Docker build so only production code was included. The result? A 50% reduction in image size, down to 376MB.
AI agents excel at low-complexity, high-effort engineering work:
This case shows how Claude Code can handle repetitive, time-consuming debt—improving both code quality and developer happiness.
<iframe width="791" height="791" src="https://www.youtube.com/embed/PWpsKdHtsFA" title="How I Tackled Tech Debt with Claude Code - Experience Report" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
“One of the greatest use cases that I've found for AI agents is to help with technical debt, especially technical debt that is easily fixable, but it just takes a long time to solve. This is the kind of thing that doesn't let you as a developer sleep well at night.
We had in this code base a bunch of test dependencies that were leaking into the production build. And slowly over time, it had grown to about 200 different files with duplicated helper utilities to read JSON files from test resources and that kind of stuff.
And when I started testing AI tools for development, this sounded like the perfect task for it, because it's very easily verifiable, since I'm not touching any logic in the actual code here, I'm just moving test utilities around. As long as my project still builds and passes the tests, we know that we are fine.
So I separated that task into two different PRs. In this first one, I moved only the test utilities for the sources into a separate package and then imported those functions where they were previously used. That resulted in a pretty boring but very accurate PR with 105 files changed. So I did the same thing for the destination utilities in a second PR-–[which was] in total around 200 files that I needed to fix—but of course it was a lot easier with AI.
And the cool thing about this is that it unlocked another thing that was in the back of my head for the longest time, that since we had all of these testing dependencies in the production build, we were including all of that in our Docker images unnecessarily.
So after finishing with the first two, I again use Claude Code to turn my Docker image build process into a multi-stage and as usual, run the dependencies to only include the production code. So that resulted in, as you can see here, in my image when I was testing, around a 50% size reduction in the image. Our images were about 752 megabytes. And after the change, they turned into 376 megabytes.
It was the perfect task for AI because as long as the build and test commands were passing, we know we are good. And for the second task, same thing. And as long as you're done with the Docker build successfully, there is nothing to fear. Everything is fine.”
Ready to reclaim your development time? This case study shows exactly how AI coding agents like Claude Code can transform those lingering tech debt tasks from overwhelming projects into quick wins.
By eliminating 200 tedious file changes in minutes rather than days, we didn't just clean up our codebase—we freed up precious developer hours for the creative, high-impact work that actually moves the needle.
The lesson here isn't that AI will replace developers, but that it can handle the repetitive, time-consuming tasks that keep us from our best work.
Whether it's dependency cleanup, refactoring legacy code, or optimizing build processes, Claude Code turns tech debt from a burden into an opportunity.
The next time you're staring at a backlog of "someday" improvements, consider whether an AI agent might be the perfect tool to finally tackle them—and get back to building what matters.
I publish my thoughts on AI and experience with AI coding tools frequently. Follow me on LinkedIn to stay in touch.
Yandry Perez is a senior software engineer at Faros AI.
