Real-World Lessons from Shipping LLM-Based Software
Real-World Lessons from Shipping LLM-Based Software
Can’t attend live? Register anyway and we’ll send you the full session recording.
Reserve Your Spot
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.
An Online Mini-Conference, Friday, August 14, 2026
Over the past year, we've been learning a lot about building and shipping LLM-based software, especially as our solutions have shifted toward agentic loops and tool calls. We've picked up hard lessons along the way around context management, evals, guardrails, and more.
That is why we are hosting an online mini-conference where four engineering leaders share the real-world lessons that came from building and running LLM-based software in production, at companies including Bridgewater Associates, Prudential Financial, and Morgan & Morgan.
This mini-conference covers:
Why context management is the bottleneck in production LLM systems, and strategies for addressing it.
Moving from retrieval-augmented generation (RAG) to page-by-page LLM extraction when processing massive documents like 5,000-page medical records, and from narrowly scoped LLM tasks toward more autonomous agents handling larger workflows.
Building and evaluating an AI agent platform at hedge-fund scale, avoiding over-engineered agent architectures and oversized eval suites, and where deterministic glue code beats agent-based orchestration.
Deploying a financial advisor AI assistant in a highly regulated industry: practical experience with context management, evals, judging, guardrails, and observability.
How to design permissions and security boundaries for agents and tools.
Practical evals, and how to avoid letting them get in the way of a good product.
Come join fellow CTOs, senior product leaders, and startup CEOs who want practical, reality-based insights on building LLM-based software that holds up in production.
Tony Karrer (Moderator)
Tony is the Founder/CEO of TechEmpower, a 20-person software / AI development services company. Tony has worked as a fractional CTO at over 40 different companies including as the original CTO at eHarmony, helping them 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 AI companies in healthcare, legal, and insurance. Tony is also cofounder of the LA CTO Forum, the largest CTO professional organization in the US.
Santiago "Santi" Weight
Santi is a Technical Lead in Bridgewater's AIA Labs, the AI organization at Bridgewater Associates, the world's largest macro-economic hedge fund. At Bridgewater, Santi started and led the development of the AI Analyst, the core agent underpinning Bridgewater's Agentic fund. Today, the AI Analyst saves roughly one analyst-week per day among analysts and researchers, and is being used to build automated trading and research pipelines.
Rohit Kapa
Rohit Kapa is the Vice President of Data Science and AI at Prudential Financial, where he leads AI strategy and use cases for the Individual Life Insurance business unit, delivering over $50M in year-over-year P&L impact. With more than 14 years of financial services leadership, he specializes in building scalable AI/ML and Generative AI solutions. Rohit is also an active researcher with published papers on Knowledge Graphs and NLP, and has three first-author patents pending across mortality risk and agentic AI solutions.
Keith McFarlane
Keith McFarlane is the Chief Technology Officer of Globality, Inc., an AI-first agentic sourcing and procurement platform. He has spent roughly 30 years in enterprise engineering leadership, including earlier work modernizing legacy platforms at Oracle, and now leads Globality's work on secure, autonomous AI agents for enterprise procurement, including its Glo negotiation agent.
Paras Chaudhary
Paras Chaudhary is a Staff Software Engineer and Tech Lead Manager at Morgan & Morgan, P.A., America's largest personal injury law firm. A Columbia University graduate and former Amazon engineer, he leads the firm's internal agentic AI stack, including OCR, document extraction, and case triage tools now used daily by roughly 70% of the firm's case staff.
© 2026 TechEmpower