LangSmith

Build Evals That Actually Matter - Nick Ung, Lyft

Jul 19, 2026 · 37:45

Nick Ung and Akshay from Lyft explain how to build evals that actually matter for customer-support AI agents, sharing their end-to-end pipeline. They argue offline evals must use a fine-tuned user simulator trained on real rider and driver transcripts to produce messy, frustrated behavior—not an off-the-shelf LLM that sounds too nice. Their LLM judge is treated as a binary classifier, calibrated against human labels using precision and recall, with metrics tied to actionable business outcomes like escalation decisions. They detail a continuous error-analysis loop that feeds production failures back into the offline test set and closes the loop through context, harness, or model learning. The talk also previews their config-driven eval harness with YAML primitives for tasks, datasets, and personas, enabling repeatable runs across development stages.

Evaluating AI Search: A Practical Framework for Augmented AI Systems — Quotient AI + Tavily

Jul 29, 2025 · 20:33

Julia Neagu (CEO of Quotient AI), Deanna Emery (founding AI researcher at Quotient AI), and Maitar Asher (Head of Engineering at Tavily) argue that traditional monitoring approaches like static benchmarks (e.g., SimpleQA) fail to capture the complexity of production AI search because the web is dynamic and truth is subjective. They present a framework combining dynamic datasets generated via a LangGraph-based agent that creates evidence-based Q&A pairs from multiple search providers, and holistic evaluation using three reference-free metrics: answer completeness, document relevance, and hallucination detection. In a two-part experiment comparing six anonymized AI search providers on a static (SimpleQA) and a dynamic benchmark of ~1,000 rows, ranking shifted significantly—provider F went from worst on SimpleQA to best on the dynamic benchmark. Reference-free answer completeness correlated 0.94 with correctness, and document relevance showed an inverse correlation with unknown answers. The speakers stress that evaluation should diagnose issues (e.g., incomplete answers with relevant documents suggest need for more retrieval) and guide improvements, ultimately aiming for…

3 ingredients for building reliable enterprise agents - Harrison Chase, LangChain/LangGraph

Jul 23, 2025 · 20:55

Harrison Chase, CEO of LangChain, argues that reliable enterprise agents depend on three ingredients: high value when right, high probability of success, and low cost when wrong. He says agents succeed by tackling high-value tasks like legal or research, and by doing more work through long-running processes. Reliability improves by blending deterministic workflows with agentic loops, as in LangGraph, and by using observability (LangSmith) to build trust. Cost is lowered by reversible actions (e.g., code diffs) and human-in-the-loop patterns like approvals and time travel. Chase predicts a future of ambient agents—event-triggered, human-supervised background agents—and notes code agents lead because code is verifiable and easily revertible.

[Evals Workshop] Mastering AI Evaluation: From Playground to Production

Jul 1, 2025 · 1:25:08

In this workshop, Braintrust Solutions Engineers Carlos Esteban and Doug guide participants through the complete AI evaluation lifecycle, from offline testing in the playground to production monitoring. They explain the three core ingredients of an eval—task, data set, and score—and demonstrate how to run evals both via the Braintrust UI and the SDK. The session covers LLM-as-judge vs. deterministic code scores, the importance of starting small with synthetic data, and how to use online scoring and logging to capture real user feedback. Human-in-the-loop review is highlighted as a way to establish ground truth and close the feedback loop. The presenters also address audience questions on bootstrapping data sets, non-determinism in LLM judges, and integrating evals into existing projects.

How to build world-class AI products — Sarah Sachs (AI lead @ Notion) & Carlos Esteban (Braintrust)

Jun 27, 2025 · 1:43:46

Sarah Sachs (AI lead at Notion) and Carlos Esteban (Braintrust) explain that building great AI products requires 10% prompting and 90% evals and observability, with Notion AI using Braintrust to iterate on prompts and models. Sachs details their cycle: curate small datasets, tie them to scoring functions (LLM-as-a-judge with per-sample prompts and heuristic checks), run evals before shipping, and use production logs to catch regressions. She notes Notion AI supports 100M+ users, switches models in under a day, and 60% of enterprise users are non-English—requiring multilingual eval rigor. Carlos and Doug then walk through Braintrust's framework: tasks (prompts, tools, agents), datasets, and scores (0-1). They demonstrate offline evals via playground and SDK, online scoring in production, user feedback capture, human review setup, and remote evals to bridge complex code with the playground. The workshop covers moving from pre-prod evals to production monitoring, closing the feedback loop by adding underperforming spans to datasets.

Case Study + Deep Dive: Telemedicine Support Agents with LangGraph/MCP - Dan Mason

Jun 22, 2025 · 1:56:13

Dan Mason of Stride presents a case study on building autonomous agents for telemedicine support, replacing a human-driven button-pushing workflow with LangGraph, Claude, MCP, and a Node.js/React/MongoDB stack, achieving roughly 10X capacity increase. The LLM-driven virtual operations associate ("Ava") assesses patient messages, updates state with anchors and scheduled messages, and passes proposals to an evaluator agent that scores confidence and complexity, escalating to humans below 75% confidence. Mason explains how treatment "blueprints" in Google Docs are read directly by the LLM instead of using RAG, enabling new treatments to be added without writing code. He details the eval system using LLM-as-a-judge via PromptFu and retry logic for tool-calling errors, and discusses trade-offs around confidence scoring, prompt caching, and model selection (Claude for steerability). The team includes two software engineers, one designer, and Mason, who wrote most LangGraph code with AI assistance (Kline).

The RAG Stack We Landed On After 37 Fails - Jonathan Fernandes

Jun 3, 2025 · 18:52

Jonathan Fernandes, independent AI engineer, details the RAG stack his team settled on after 37 failed attempts, covering orchestration (LlamaIndex), embeddings (BAAI BGE small), vector database (Qdrant), LLMs (GPT-4, Qwen, Llama), reranking (Cohere), monitoring (Arize Phoenix), and evaluation (RAGAS). He demonstrates a live prototype in Google Colab using a London railway knowledge base, showing how a naive RAG returns irrelevant results (e.g., suggesting black cabs for "where can I get help at the station"). By swapping components—replacing in-memory storage with Qdrant, using an open-source embedding model, upgrading to GPT-4, and adding Cohere reranking—the answer improves to "go to booth number five next to the Eurostar ticket gates." For production, he deploys via Docker Compose with NVIDIA embedding/reranking models and Ollama for serving. The episode also stresses the importance of tracing latency per component and using RAGAS for systematic evaluation across many queries.

Lessons from building GenAI based applications — Juan Peredo

Feb 22, 2025 · 33:13

Juan Peredo details the hidden complexities of building GenAI applications, from model hosting and cost control to output validation and observability. He compares local (Ollama) vs cloud hosting (Modal, SkyPilot) and warns that an agent processing 3,000 calls/day with OpenAI O1 costs nearly $300,000/month, while LLaMA 3.3 70B drops that to $50,000/month. He explains techniques to mitigate hallucinations—prompt engineering, guardrails, RAG, and fine-tuning—each with trade-offs like added latency or cost. Peredo advocates externalizing prompts via LangChain Hub for easy iteration and future-proofing, and illustrates agent design with parallel calls to reduce latency. Finally, he stresses observability using tools like LangSmith to debug probabilistic failures, such as an LLM failing on case sensitivity.

Architecting and Testing Controllable Agents: Lance Martin

Oct 11, 2024 · 2:21:54

Lance Martin presents LangGraph, a graph-based framework for building controllable agents that trade some open-ended flexibility for significantly higher reliability compared to classic React agents, achieving 100% consistent tool-calling trajectories even with an 8B local model. He demonstrates self-corrective RAG patterns like Corrective RAG, SelfRAG, and Adaptive RAG, where the agent grades retrieved documents, checks for hallucinations, and routes to web search when needed. Martin also covers three testing loops: in-app error handling with LangGraph, pre-production evaluation using LangSmith to compare agent answers and tool trajectories against ground-truth datasets, and production monitoring with online evaluators that flag retrieval quality, answer relevance, and hallucinations without reference answers. He shares results from a five-question evaluation showing LangGraph agents achieve 80% answer accuracy and 100% tool-trajectory correctness with Fire Function V2, while React agents with GPT-4o degrade in tool reliability. The talk addresses practical concerns like handling many tools (suggesting RAG for tool selection), multi-turn conversations, and the importance of…

AI Engineering 201: The Rest of the Owl

Nov 8, 2023 · 56:57

Charles Frye, instructor of the Full Stack LLM Bootcamp, presents essential patterns for building language user interfaces (LUIs), arguing that while RAG chatbots are the 'to-do list app' of AI engineering, structured outputs via function calling (e.g., OpenAI's JSON schema, Instructor library) improve robustness, and agents with memory (like generative agents or Voyager in Minecraft) represent the true AI frontier. He emphasizes the need for hybrid search combining vector and keyword retrieval (citing Vespa, Postgres, Redis), and warns that monitoring and evaluation are the hardest engineering challenges: monitoring user behavior, latency quantiles (especially 99th percentile), and costs must be paired with observability tools like Honeycomb or Gantry, while evaluation often requires iterated decomposition or using LLMs as evaluators (GPT-4 as 90th percentile crowd worker). The episode concludes that shipping to learn — starting with production data to generate tests — is the dominant engineering mindset, and that the field is still filling in the gaps between inference and full product value.

Building Context-Aware Reasoning Applications with LangChain and LangSmith: Harrison Chase

Nov 1, 2023 · 18:54

Harrison Chase, CEO of LangChain, argues that building context-aware reasoning applications on LLMs requires treating the model as part of a larger system, and he outlines key approaches and challenges. He categorizes context provision as instruction prompting, few-shot examples, retrieval-augmented generation (RAG), and fine-tuning. For reasoning, he describes a spectrum from single LLM calls to chains, routers, agents with cycles, and autonomous agents like Auto-GPT. Chase then details engineering challenges: choosing the right cognitive architecture, data engineering for context, prompt engineering across multi-step systems, evaluation using LLM-assisted metrics and user feedback, and enabling collaboration between technical and non-technical team members. He emphasizes that the field remains early and that LangChain and LangSmith help prototype, debug, and iterate on these systems.