DevOpsConference45min
Un-observable AI is un-trustworthy AI
This talk addresses the critical need for responsible, ethical, and sustainable AI as systems move into production. It explores how observability and telemetry can provide the visibility needed to detect bias, monitor resources, and implement guardrails—ensuring trust, reliability, and reduced environmental impact in large-scale AI deployments.
Annie FreemanCoralogix
talkDetail.whenAndWhere
Wednesday, April 1, 15:30-16:15
Zaal 3
talks.roomOccupancytalks.noOccupancyInfo
As more AI systems move into production, ensuring models are responsible, ethical, and sustainable becomes critical. This talk explores how observability can help teams build AI systems they can actually trust.
For the last few years, I’ve been driven by the question: what responsibility do we have for the software we put into the world? That question originally led me to focus on reducing the environmental impact of software. Now, as teams deploy inference-heavy LLM workloads into production, it’s become even more pressing.
Using LLMs at scale raises serious questions around energy usage, cost, and ethics. A Gartner report predicts that 40% of agentic AI projects will be canceled by the end of 2027 due to escalating costs and unclear business value. How much of that comes down to a lack of visibility into how these systems behave once they’re live?
So how do you build trust in AI systems? How do you detect drift toward bias or toxicity? How do you understand the real resource cost and carbon footprint of inference at scale? And once you do have visibility, how do you turn it into meaningful guardrails?
In this talk, we’ll look at
For the last few years, I’ve been driven by the question: what responsibility do we have for the software we put into the world? That question originally led me to focus on reducing the environmental impact of software. Now, as teams deploy inference-heavy LLM workloads into production, it’s become even more pressing.
Using LLMs at scale raises serious questions around energy usage, cost, and ethics. A Gartner report predicts that 40% of agentic AI projects will be canceled by the end of 2027 due to escalating costs and unclear business value. How much of that comes down to a lack of visibility into how these systems behave once they’re live?
So how do you build trust in AI systems? How do you detect drift toward bias or toxicity? How do you understand the real resource cost and carbon footprint of inference at scale? And once you do have visibility, how do you turn it into meaningful guardrails?
In this talk, we’ll look at
- Why traditional monitoring falls short for AI,
- Which signals actually matter for responsible systems,
- How to instrument AI workloads with OpenTelemetry,
- How to use telemetry data to implement guardrails that improve trust, sustainability, and reliability in production AI.
Annie Freeman
Annie is a Developer Advocate at Coralogix, where she connects with developers to spark conversations about smarter observability and how to connect deep technical metrics with outcomes that matter. As a Green Software Champion, Annie also advocates for reducing the environmental impact of software and empowering developers to create solutions that are both impactful and sustainable. Originally from New Zealand, she brings a warm, community-focussed approach to her talks and content. Prior to Coralogix, she was a software engineer at Xero, and has a background in law.
talkDetail.shareFeedback
talkDetail.feedbackNotYetAvailable
talkDetail.feedbackAvailableAfterStart
talkDetail.signInRequired
talkDetail.signInToFeedbackDescription
occupancy.title
occupancy.votingNotYetAvailable
occupancy.votingAvailableBeforeStart
talkDetail.signInRequired
occupancy.signInToVoteDescription
comments.speakerNotEnabledComments