With Great Tooling Comes Great Responsibilities

AI tooling for coding, productivity, and as a product is taking over the engineering world but with all this great tooling, some questions remain. How do you keep track of your spend and ensure that ROI is clear? How do you secure your system and your data? How do you govern your agents?

In this talk I'll discuss how governance, compliance, and cost tracking can turn a good product into a profitable one. Drawing on my experience shipping AI tooling at Datadog, where we serve thousands of engineers and process millions of AI-assisted interactions a month, I'll share how we've navigated these challenges at scale, including the guardrails, cost controls, and model-routing strategies (open-weight and proprietary) that reduced our cost per interaction by 3X while keeping quality and latency intact.

From putting guardrails in place to using open-weight models, I'll cover the best practices I learned along the way, so you can leave with battle-tested, real-world patterns rather than theoretical advice.

Key Takeaways:

  1. How to bake in Governance, compliance and cost tracking
  2. Making trade off to reach profitability 

Speaker

Clémence Burnichon

Clémence Burnichon

Senior Director of Engineering @Datadog, 15+ Years in the Data and AI Industry

With over 15 years of experience in the data and AI industry, Clémence has been instrumental in helping leading retailers, media & entertainment companies, and fashion tech innovators unlock value through cutting-edge AI solutions. In April 2023, she joined Datadog as an Engineering Director, taking charge of the data science organization. Since January 2025, Clémence has expanded her leadership to oversee two organizations within Datadog: the AI Platform and Core Analytics teams. She is supporting the development of AI features that empower Datadog’s customers, by providing the infrastructure, tooling, and data that enable engineers across the company. Known for her strong leadership, Clémence fosters high-performing teams of data scientists, backend engineers, and infrastructure specialists, all dedicated to anticipating and meeting the evolving needs of Datadog’s customers.

Read more →