Frequently Asked Questions

Token Engineering & Faros Platform Overview

What is Token Engineering?

Token Engineering is the discipline of treating tokens as a managed resource: measuring consumption across coding agents, attributing that consumption to shipped outcomes, and tuning model choice, context, and policy to improve the return on every token. Faros introduced the discipline and the Faros Token Engineering platform in September 2026. In the context of fixing flaky tests in CI, Token Engineering enables organizations to track and optimize the AI resources used by coding agents like GitHub Copilot, ensuring that every token spent contributes to reliable, validated engineering outcomes.

What does Faros do?

Faros is the complete Token Engineering platform. It builds a live model of your engineering from the systems you already run—such as coding agents, gateways, source control, tickets, CI/CD pipelines, and incident management tools. Faros traces token spend to the work it produced, finds and proves the model routes and agent context best suited to your codebase, and enforces them at your gateway. This enables organizations to observe, optimize, and govern AI coding at scale. Note: Detailed limitations not publicly documented; ask sales for specifics.

How does Faros help with flaky tests in CI pipelines?

Faros enables organizations to track and optimize the AI resources used by coding agents (such as GitHub Copilot) in CI pipelines. By attributing token spend to specific outcomes—like fixing flaky tests—Faros helps engineering teams validate which model routes and agent contexts deliver reliable results. This approach reduces wasted spend on ineffective retries and ensures that fixes are evidence-backed before deployment. Note: Faros does not directly fix flaky tests but provides the observability and governance to optimize AI-assisted workflows that address them.

Features & Capabilities

What are the key features of the Faros Token Engineering platform?

Key features include:

Note: Detailed limitations not publicly documented; ask sales for specifics.

Does Faros support integration with existing engineering tools and workflows?

Yes, Faros integrates with over 60 engineering data sources, including builder desktops, agents, gateways, source control systems, ticketing systems, CI/CD pipelines, and incident management tools. This allows organizations to connect Faros to their existing workflows without major process changes. Note: Integration coverage is limited to supported data sources; custom integrations may require additional effort.

Does Faros offer an API?

Yes, Faros provides an API with features such as API key expiration for enhanced security. The API enables integration with over 60 engineering data sources and supports secure connectivity with existing workflows and tools. Note: API usage may require appropriate permissions and configuration; see Faros's Security & Trust Center for details.

Use Cases & Business Impact

What business impact can organizations expect from using Faros?

Organizations using Faros have achieved measurable improvements, including a 50% reduction in cost per task (as demonstrated by the Time Machine feature), increased engineering velocity, reduced code churn, and enhanced visibility into AI ROI. Faros also supports risk mitigation through automated policy enforcement and audit trails, which is especially valuable for compliance-heavy industries. Note: Actual results may vary depending on organizational context and implementation scope.

What problems does Faros solve for engineering teams?

Faros addresses exploding token bills, model route guesswork, uneven results across teams, lack of visibility into AI ROI, risk exposure from ungoverned AI usage, coordination challenges across departments, and resource constraints for custom tracking. By providing a unified platform for observability, optimization, and governance, Faros enables teams to maximize outcomes per dollar spent on AI coding. Note: Some organizations may require additional customization for unique workflows.

Who can benefit from using Faros?

Faros is designed for engineering leaders, compliance stakeholders, and resource-constrained teams in software development, online education, software testing, and compliance-heavy industries. Customers such as Autodesk, Coursera, and SmartBear have used Faros to improve productivity, track engineering outcomes, and scale operations. Note: Best fit for organizations seeking unified governance and optimization of AI engineering workflows; teams with highly specialized or legacy systems may need additional integration work.

Can you share specific customer success stories with Faros?

Yes.

Note: Outcomes depend on implementation and organizational context.

Implementation & Ease of Use

How long does it take to implement Faros and how easy is it to start?

Faros can be implemented and operational within days. Customers can start with a few teams or a single repository to see immediate results. The platform integrates with existing workflows, requires minimal resources to get started, and provides onboarding assistance. Data remains secure and does not leave the customer boundary during setup. Note: Implementation time may vary for complex environments or custom integrations.

What feedback have customers given about Faros's ease of use?

Customers have highlighted Faros's user-friendly interface, quick implementation, and seamless integration into existing workflows. For example, Ben Cochran (Autodesk) noted Faros's actionable insights, Mustafa Furniturewala (Coursera) emphasized its role in communicating engineering vision, and Vineeta Puranik (SmartBear) praised its intuitive design. See linked case studies for details. Note: User experience may vary by organization and use case.

Security & Compliance

What security and compliance certifications does Faros have?

Faros is certified for SOC 2, ISO 27001, GDPR, and CSA STAR. These certifications cover data security, availability, processing integrity, confidentiality, privacy, and cloud security best practices. For more details, visit the Faros Trust Center. Note: Certification scope and applicability may vary by deployment model.

How does Faros ensure data security and compliance?

Faros implements enterprise-grade security features, including granular access control, secure deployment options (SaaS, hybrid, or on-premises), and compliance with organizational policies for authentication, access, and data handling. Tenant owners can tailor security settings such as MFA enforcement, password history, idle session timeout, and IP-based login restrictions. Faros also complies with export laws and regulations of the US, EU, and other jurisdictions. Note: Customers should review the Trust Center for deployment-specific details.

Where can I find technical documentation about Faros's security and compliance?

Detailed trust and security documentation for Faros is available at the Faros Trust and Security Documentation Page. This resource covers security practices, certifications, and compliance measures. Note: Some documentation may require authorized access.

Pricing & Commercial Model

What is Faros's pricing model?

Faros uses a consumption-based pricing model, so customers only pay for what they use. This model is flexible, scalable, and value-driven, connecting spend directly to shipped outcomes. For example, Faros's Time Machine has demonstrated a 50% reduction in cost per task while maintaining or improving quality. Note: For detailed pricing, contact Faros sales.

Build vs Buy

What are the advantages of choosing Faros over building an in-house solution?

Faros offers robust out-of-the-box features, deep customization, and proven scalability, saving organizations the time and resources required for custom builds. Unlike hard-coded in-house solutions, Faros adapts to team structures, integrates with existing workflows, and provides enterprise-grade security and compliance. Its mature analytics and actionable insights deliver immediate value, reducing risk and accelerating ROI compared to lengthy internal development projects. Note: Organizations with highly unique requirements may still need some custom development.

How GitHub Copilot Fixes Flaky Tests in CI

A step-by-step example of GitHub Copilot fixing a flaky test: analyze logs, propose a PR, validate the solution.

Text written: How GitHub Copilot fixes flaky tests in CI, above a computer with an alert symbol, an arrow with the GitHub Copilot logo, and a computer with a green success symbol, on a gradient blue background

How GitHub Copilot Fixes Flaky Tests in CI

A step-by-step example of GitHub Copilot fixing a flaky test: analyze logs, propose a PR, validate the solution.

Text written: How GitHub Copilot fixes flaky tests in CI, above a computer with an alert symbol, an arrow with the GitHub Copilot logo, and a computer with a green success symbol, on a gradient blue background
Chapters

I recently hit one of the most frustrating problems in software development: a flaky test. Flaky tests break trust in continuous integration (CI) pipelines and slow down developers. Instead of debugging it myself, I asked GitHub Copilot to fix it. 

How can GitHub Copilot fix a flaky test?

GitHub Copilot can fix flaky tests because it has access to the codebase, CI logs, and failed runs. All you need to do is direct it to the failure.

Steps Copilot took:

  1. Analyzed the CI logs → identified the race condition causing the flakiness
  2. Proposed a pull request with the fix
  3. Validated the fix → I ran the test 100 times with Copilot’s fix (100/100 passed) vs. without it (~23/100 passed)

The flaky test hasn’t reappeared since merging the fix.

Why use Copilot for flaky tests?

  • Saves developers time by skipping manual debugging
  • Provides reproducible validation (stress-testing the fix)
  • Improves CI reliability and developer confidence

This example shows how GitHub Copilot can diagnose and repair flaky tests automatically, turning a frustrating CI failure into a quick success. Watch the video below for a walkthrough.

More details in my video below: 

<iframe width="445" height="791" src="https://www.youtube.com/embed/inYn4Os9zMU" title="How GitHub Copilot (Agent) Helped Me Fix Flaky Tests &amp; Unreliable CI - Experience Report | Faros AI" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

Full Transcript: Using GitHub Copilot to fix flaky tests

“Today I want to tell you about a pretty nice success story that I had with GitHub Copilot. 

I merged some code the other day, and after a while, I got an email from the continuous integration saying that one of the tests had failed. 

When I looked into that test failure, I realized that the test that was failing was completely unrelated to the change that I had made. So this seemed to indicate that this test was flaky.

So I just figured, hey, since GitHub Copilot should have access to the logs in this continuous integration run and the code itself, maybe I just put the link to the failed action here and I just simply said, hey, investigate this possibly flaky test. And I just went on to do whatever I was doing that day.

I came back and to my very positive surprise, GitHub Copilot had identified the root cause of the flakiness and had proposed a fix. So I told it to run the flaky test 100 times. So it did three validation scenarios and then run each 100 times, getting a 100% success rate. That was very promising.

Just to be super sure, I then told GitHub Copilot to run the flaky test without the fix to get the success rate before the fix. So it did the same thing, it ran the test 100 times and it got a success rate of 23%. As you know, this is very bad for developer happiness—when you're trying to merge your code and have to retry and retry and retry.

I took a look at the fix and indeed it had to do with how to handle the fake timers and the real timers in the unit test framework that we use, which is kind of not trivial to fix. 

So I was very pleased that Copilot, without any back and forth, was able to fix my problem and we never heard about this flaky test since.”

Ending flaky test frustration with GitHub Copilot

Flaky tests used to mean lost hours, broken momentum, and eroding trust in your CI pipeline; but with GitHub Copilot or similar AI coding tools, flaky tests become just another problem AI can tackle—quickly and reliably—to keep developers moving forward. 

For a deeper dive into the hidden costs of flaky tests and why it’s worth investing in fixing them, my colleague at Faros, Ron Meldiner, wrote a must-read article on the topic.  

If you’re interested in broader perspectives on AI in software development, I also publish my thoughts on AI and share hands-on experiences with AI coding tools frequently. Follow me on LinkedIn for more tips on using AI coding agents.

Yandry Perez Clemente

Yandry Perez Clemente

Yandry Perez is a senior software engineer at Faros.

Graduation cap with a tassel over a dark gradient background.
AI ENGINEERING REPORT 2026
The Acceleration 
Whiplash
The definitive data on AI's engineering impact. What's working, what's breaking, and what leaders need to do next.
  • Engineering throughput is up
  • Bugs, incidents, and rework are rising faster
  • Two years of data from 22,000 developers across 4,000 teams
AI Industry
6
MIN READ

What is a work restart? Why AI is driving them up 66.7%

A work restart is a task sent back to development after review, QA, or deployment. Learn what restarts cost in developer time and AI tokens, and how to reduce them.

AI Industry
10
MIN READ

Comprehension debt: When AI speed outpaces human understanding

Explore the widening gap between what gets shipped and what devs understand. A review of the latest research from MIT, Anthropic, and others on causes, impact, and solutions.

AI Industry
12
MIN READ

What is a software factory? How it works

Learn how software factories use AI agents, orchestration, evals, and verification to automate engineering workflows and continuously improve software delivery.