Building Reliable Autonomous Agentic AI Systems

Building Reliable Autonomous Agentic AI Systems

Friday, February 13, 2026 • 8 to 10 AM PST / 11 AM to 1 PM EST

Can’t attend live? Register anyway and we’ll send you the full session recording.

Reserve Your Spot

All registrants will receive the session recording.

We respect your privacy. Your information will only be used for this webinar and related communications from TechEmpower.

Over the past few years, CTOs have been building LLM-based systems using a DAG workflow approach. Autonomous agentic systems are a different sport.

Reliability is quickly becoming the dividing line between agentic AI that demos well and agentic AI you can trust in production. As soon as an LLM can take actions, teams run into the same hard questions: How do we test it to make sure it’s producing reliable results? How do we keep tool calling safe? How do we prevent loops and runaway costs? How do we orchestrate long-running work with retries and recoverability? How do we evaluate agent behavior so we can improve it with confidence, not vibes?

That is why we are hosting an expert-led session to give engineering and product leaders practical patterns they can apply immediately.

This two-hour, high-impact mini-conference covers:

A closed-loop evaluation walkthrough: how to build "plan -> act -> judge -> revise" harnesses, curate ground truth, calibrate automated judges, and catch regressions before they hit production.
The core orchestration patterns that make agents dependable: durable state, resumability, retries, and deterministic controls around nondeterministic models.
How to evaluate agentic systems with evidence: task suites, ground truth, judges, and a repeatable iteration loop that improves reliability over time.
What guardrails high-performing teams use to prevent loops, contain cost, and stop safely when the agent is uncertain or stuck.
A moderated discussion among presenters and attendees to surface concrete design questions and tradeoffs from real deployments.

Come join fellow CTOs, VPEs, heads of engineering, and senior product leaders who want practical, reality-based insights on building reliable autonomous agentic AI solutions.

Tony Karrer (Moderator)

Tony is the founder of TechEmpower, a 30-person software development services company. Tony has worked as a fractional CTO at over 30 different companies including as the original CTO at eHarmony helping them to get to a $110M financing in their 4th year. Tony has worked on AI solutions for more than two decades across a wide variety of industries and is currently the fractional CTO of a healthcare AI company backed by AI Fund and a fractional CTO of an AI insurance SaaS company. Tony is also cofounder of the LA CTO Forum - the largest CTO professional organization in the US.

Sinan Ozdemir (Speaker)

Sinan is an AI consultant, educator, and workshop leader who helps businesses implement practical AI solutions. He is the founder of Crucible, an AI factory platform that converts AI workflows into custom models companies own and control. Sinan is the author of multiple AI books including "Building Agentic AI" as part of Pearson's A.I. Signature Series, and regularly delivers live trainings and video courses for O'Reilly Media on topics including AI agents, Transformers, and NLP. A Y Combinator alum, he previously founded Kylie.ai in 2014, an early AI agent with computer use capabilities that was later acquired. He holds 4 patents in AI/ML, serves as an AI & LLM Advisor at Tola Capital, and holds a master's degree in pure mathematics from Johns Hopkins University.

Jared Zoneraich (Speaker)

Jared Zoneraich is the founder and CEO of PromptLayer, the AI engineering workbench for building, evaluating, and monitoring LLM products in production. PromptLayer processes millions of LLM requests daily, powering thousands of AI teams and enabling collaboration between ML engineers and domain experts through prompt versioning, evals, agents, and historical logs. Jared works closely with teams deploying autonomous agents in real-world environments and regularly speaks on practical agent design, evaluation, and operational best practices. Previously, he held engineering roles at Tecton, Facebook, and Google, studied at UC Berkeley, and organized hackathons where he taught thousands of people to code.

Ray Myers (Speaker)

Ray Myers is a legacy code expert with 18 years of Software Engineering experience across four industries. His recent work explores the delicate intersection of AI and maintainability. He publishes guidance on the Craft vs Cruft YouTube channel with influences from DevOps to Taoism.

Ryan Doan (Speaker)

Ryan Doan is the VP of Engineering at OutRival, a high-growth Miami startup redefining digital work. He leads the build-out of “Digital Workers”—AI agents that handle phone calls, SMS, email, and software-driven workflows—helping institutions grow revenue, reduce operating costs, and improve customer satisfaction at scale. Previously, Ryan helped grow Semantic Health (acquired in 2023) by delivering state-of-the-art CAC and CDI solutions for hospitals, scaling from a single Canadian site to deployments across the United States, Australia, and the UAE within three years. Before healthcare, he founded MLExpert, a technical interview prep platform that grew to 75,000+ students in four years. Earlier in his career at Amazon, Ryan reduced subscription churn and helped personalize retail search, contributing to $1B+ in growth-adjusted ARR in under four years. He’s passionate about making Miami a global hub for AI innovation and building OutRival into the de facto platform for repetitive digital work.