Discussion on agentic LLM adoption in production, focusing on LangChain and LlamaIndex tooling, production readiness, tools, evaluation and observability, safety and guardrails.

Dialogue on deploying agentic LLMs in production, focusing on LangChain and LlamaIndex usage, tools, evaluation and observability, safety and guardrails.

Agentic LLM adoption (LangChain/LlamaIndex in production, tools, evaluation and observability, safety and guardrails)

Agentic LLM adoption (LangChain/LlamaIndex in production, tools, evaluation and observability, safety and guardrails).

Join Kostia Omelianchuk and Lukas Beisteiner as they unpack the full scope of Grammatical Error Correction (GEC) from task framing, evaluation, and training to inference optimization and serving high-performance production systems at Grammarly. They will discuss: The modern GEC recipe (shift from heavily human-annotated corpora to semi-synthetic data generation), LLM-as-a-judge techniques for scalable evaluation, and techniques to make deployment fast and affordable, including Speculative Decoding.

Dialogue 2: Agentic LLM adoption (LangChain/LlamaIndex in production, tools, evaluation and observability, safety and guardrails)

Discussion on LangChain and LlamaIndex in production, tools, evaluation and observability, safety and guardrails for agentic LLM workflows.

Agentic LLM adoption — LangChain and LlamaIndex in production, tools, evaluation and observability, safety and guardrails.

Agents are powerful—but without feedback, they're flying blind. In this talk, we’ll walk through how to build self-improving agents by closing the loop with evaluation, experimentation, tracing, and prompt optimization. You’ll learn how to capture the right telemetry, run meaningful tests, and apply insights in a way that actually improves performance over time. Whether you’re building copilots, chatbots, or autonomous workflows, this session will give you the practical tools and architecture patterns you need to make your agents smarter—automatically.