Moving Fast with AI Evals | Washington Meetup

3rd Washington DC Meetup – From Ground Truth to Confident Decisions: Moving Fast with AI Evals

How do AI teams move fast without compromising confidence in what they ship? And how do they know when evaluation results provide enough evidence to make the next decision?

AI evaluations are only as reliable as the examples, judgments, and criteria behind them. Building meaningful evaluations requires more than automated scores. It requires representative ground truth, human judgment, and a clear connection between evaluation results and business decisions.

At The Test Tribe’s 3rd Washington DC Meetup, Alekhya Guduri will explore how teams can build reliable AI evaluation practices, manage uncertainty, and turn evaluation findings into confident decisions about when to launch, iterate, or investigate further.

Session - From Ground Truth to Confident Decisions: Moving Fast with AI Evals
Speaker: Alekhya Guduri, Senior Director of Engineering at Indeed

Alekhya works at the intersection of technology, business strategy, and organizational leadership. At Indeed, she leads engineering quality, program management, and AI evaluation, connecting technical insights with business priorities to guide investment decisions and execution.
Her work focuses on helping teams navigate ambiguity, make informed trade-offs, and translate emerging AI capabilities into measurable business value. She is also an Executive MBA candidate at NYU Stern, Class of 2027.

Drawing on her experience leading AI evaluation programs, Alekhya will explore how to establish reliable ground truth, combine automated evaluations with human review, and determine when the available evidence is sufficient to move forward, even when uncertainty remains.

The session will cover:

• Building Reliable Ground Truth: Creating representative datasets using clear evaluation criteria and human review.
• Combining AI and Human Judgment: Using LLM-based evaluators alongside human assessments to identify meaningful quality gaps.
• Turning Evaluations into Decisions: Translating evaluation results into explicit launch, iterate, or stop decisions.
• Managing Uncertainty: Distinguishing uncertainties that require further investigation from those that can be managed through experimentation and monitoring.

Event Details

• Date: 9 December 2026
• Time: 06:00 PM – 08:00 PM Local Time
• Venue: 1501 Langston Blvd., Arlington, VA 22209, USA

Agenda

• 6:00 PM – 6:15 PM: Welcome & Introductions
• 6:15 PM – 7:15 PM: Speaker Session by Alekhya Guduri on “From Ground Truth to Confident Decisions: Moving Fast with AI Evals”, including Q&A
• 7:15 PM – 8:00 PM: Networking over snacks
• 8:00 PM: Event Wrap

Stay back to connect with fellow QA and Engineering professionals, exchange perspectives, and discuss how teams can build confidence in
AI systems without slowing down innovation.

About The Test Tribe

The Test Tribe is the world's largest software testing community, empowering testers globally since 2018. With 980+ events and 176K+ lives touched across 130+ countries, we bring testers together to learn, grow, and connect through meetups, conferences, cohorts, masterclasses, and more.

Become a Speaker at The Test Tribe Events

Wish to share your insights with the community at a future event?
Submit your talk idea here, and if it resonates with the perspective we are trying to build at our events, our team will connect with you.

By RSVPing, you agree to our Terms and Conditions and Privacy Policy and consent to be contacted by The Test Tribe and our event partners.