@braintrustdata Avatar @braintrustdata Braintrust

Braintrust posts on YouTube about braintrust, ai, intro, how to the most. They currently have [---] followers and [--] posts still getting attention that total [-----] engagements in the last [--] hours.

Engagements: [-----] #

Engagements Line Chart

Mentions: [--] #

Mentions Line Chart

Followers: [---] #

Followers Line Chart

CreatorRank: [---------] #

CreatorRank Line Chart

Social Influence

Social category influence cryptocurrencies finance technology brands social networks

Social topic influence braintrust #3, ai, intro, how to, llm #554, agent, model, engineering, vibe coding, tech

Top accounts mentioned or mentioned by @oneto100podcast

Top assets mentioned Braintrust (BTRST)

Top Social Posts

Top posts by engagements in the last [--] hours

"Shipping fast without losing AI quality at Replit Luis Hctor Chvez CTO of Replit explains how observability changed the way Replit builds its AI-powered platform. He shares how they discovered thousands of users were struggling with the same auth problem why focusing on patterns across sessions rather than individual traces lets the team fix entire families of issues and how cutting trace visibility from minutes to real-time transformed their debugging workflow"
YouTube Link 2026-02-16T15:39Z [---] followers, [--] engagements

"How Browserbase benchmarks browser agents Paul Klein founder of Browserbase explains why reliable browser agents need both browser observability and model observability working together. He shares how they built a public evals dashboard with Braintrust"
YouTube Link 2026-02-16T15:39Z [---] followers, [--] engagements

"Observing and improving AI at scale at Dropbox Josh Clemm VP of Engineering at Dropbox walks through the full evolution of their eval practice for Dash. He breaks down their multi-tier pipeline [---] smoke tests before merge 10000+ full-suite tests after and real-time LLM-as-judge in production and explains why his product teams now codify taste tone and success criteria into evals before writing a line of product code"
YouTube Link 2026-02-16T15:36Z [---] followers, [--] engagements

"Debugging and evaluating AI at Notion Sarah Sachs leads AI modeling at Notion where [--] engineers ship AI features across search agents and workspace automation. She walks through how Notion's eval approach evolved from simple prompt chains to complex agentic path-finding how they caught a tricky multilingual bug across Japanese Korean and English workspaces and why they've committed to rebuilding their AI framework every time a new generation of models changes what's possible"
YouTube Link 2026-02-16T15:38Z [---] followers, [--] engagements

"Intro to Evals with Braintrust In this video we walk through the complete eval workflow including creating datasets prompts and scorers"
YouTube Link 2025-10-07T20:14Z [---] followers, [----] engagements

"Intro to Remote Agent Evals with Braintrust In this video we walk through how you can connect an agent running on your local computer to Braintrust for easier iteration and collaboration. For more information visit the documentation: https://www.braintrust.dev/docs/guides/remote-evals"
YouTube Link 2025-10-14T17:26Z [---] followers, [---] engagements

"Announcing Braintrust's $36M Series A We're thrilled to announce that we've raised $36 million to advance the future of AI software engineering bringing our total funding to $45 million"
YouTube Link 2024-10-08T14:00Z [---] followers, [----] engagements

"Intro to Loop: the AI agent for evals and observability in Braintrust Learn how you can use Loop in Braintrust to optimize your eval and observability workflows"
YouTube Link 2025-11-24T16:10Z [---] followers, [---] engagements

"Measure what matters with Braintrust: Intro to AI evals This session breaks down the basics of evals - how to optimize prompts write good scoring functions and manage datasets. We cover framework and model-agnostic approaches that work with any AI application"
YouTube Link 2025-10-07T19:58Z [---] followers, [----] engagements

"Intro to Braintrust: AI Observability and Evals An end-to-end walkthrough of Braintrust the AI observability platform for building quality AI products. Using a customer support chatbot example I show you how to use evals and observability to build trust in your AI systems. 0:00 Intro: The AI iteration problem 0:24 What is Braintrust: evals + observability 0:38 Demo setup: SunshineCo support chatbot 0:57 Setting up AI providers in Braintrust 1:20 Building your first eval in the playground 2:07 Using AutoEvals and LLM-as-a-judge scorers 2:35 Brand alignment scorer with chain of thought 3:08"
YouTube Link 2026-01-22T17:11Z [---] followers, [----] engagements

"Demo of attachments"
YouTube Link 2024-10-24T04:08Z [--] followers, [---] engagements

"Braintrust: Build and evaluate an AI assistant This example walks you through how to build and evaluate an AI question and answer chat assistant. The assistant answers questions based on the user's information that is already saved in a vector DB (Chroma). Learn more and get the code examples at braintrustdata.com/docs/examples/rag"
YouTube Link 2023-09-25T20:58Z [---] followers, [----] engagements

"Evaluating agents: how we built Loop the AI assistant for evals Join Doug Guthrie Solutions Engineer at Braintrust for a walkthrough of Loop Braintrusts new AI assistant for evals. We cover best practices for evaluating complex agentic systems and how Loop can help you generate synthetic datasets improve your prompt tasks and write better scoring functions"
YouTube Link 2025-07-16T18:46Z [---] followers, [----] engagements

"What to do when a new model comes out Every week new state-of-the-art AI models are released promising breakthrough performance but how can you know if they're right for your app Join Phil Hetzel Solutions Engineer at Braintrust as he shares practical strategies for evaluating new AI models with real-world data. In this webinar you'll learn how to: - Establish baseline performance metrics for your current AI models - Effectively benchmark new AI models against your application's real data - Compare model performance to confidently decide on deployment - Swap models with minimal disruption -"
YouTube Link 2025-06-11T18:28Z [---] followers, [---] engagements

"Braintrust - Rapidly ship AI without the guesswork Evaluate your AI applications with Braintrust: the enterprise-grade stack for building high quality AI products. From experiment tracking to prompt playground to data management we take uncertainty and tedium out of shipping AI. Sign up at braintrustdata.com"
YouTube Link 2023-09-25T20:58Z [---] followers, [----] engagements

"How Hostinger Evaluates AI Applications with Braintrust Braintrust enables developers to rapidly ship AI without guesswork. Watch as Liucija a Senior Data Scientist on the AI team @ Hostinger walks through how she leverages Braintrust to accelerate Hostinger's AI development process and drive business outcomes. Learn more about Hostinger: https://www.hostinger.com/ Learn more about Braintrust: https://www.braintrustdata.com/"
YouTube Link 2024-02-27T18:53Z [---] followers, [----] engagements

"LLM Logs Breakdown #ai #evals #observability #braintrust #tech #coding #vibecoding #engineer"
YouTube Link 2026-01-16T18:12Z [---] followers, [----] engagements

"How To Turn Messy Production Logs Into Dataset #ai #evals #observability #data #logs #vibecoding"
YouTube Link 2026-01-12T17:38Z [---] followers, [----] engagements

"Evals for real-world voice agents This video breaks down practical steps to build measure and scale voice agents with consistency and quality in production. We discuss how Navan runs evals for its AI voice agent to solve the last-mile challenges for travelers and finance teams"
YouTube Link 2025-11-18T22:04Z [---] followers, [---] engagements

"How To Log LLM Calls #ai #evals #observability #llm #braintrust #vibecoding #logs #data"
YouTube Link 2026-01-13T17:30Z [---] followers, [----] engagements

"Playgrounds VS Experiments #ai #observability #evals #tech #softwareengineer #llm #vibecoding"
YouTube Link 2026-01-14T23:16Z [---] followers, [----] engagements

"4 Reason To Create AI Experiment #ai #evals #observability #braintrust #tech #llm #logging #monitor"
YouTube Link 2026-01-21T18:32Z [---] followers, [----] engagements

"Making your AI better at detecting spam Here's a walkthrough of building your first spam classifier using Braintrust with structured outputs custom scorers and model comparison. 0:00 Intro to building a spam classifier 0:14 Review the dataset 0:38 Creating a playground environment 1:33 Using structured outputs 2:11 Writing a custom deterministic scorer for correctness 2:45 Running a full eval experiment 3:06 Comparing models: swapping to o3-mini 3:59 Conclusion Full example in the Braintrust cookbook: https://github.com/braintrustdata/braintrust-cookbook/tree/main/examples/SpamClassifier"
YouTube Link 2026-01-30T00:44Z [---] followers, [---] engagements

"Intro to Human Review with Braintrust Learn how to set up human review as part of your eval and observability workflows in Braintrust"
YouTube Link 2025-10-22T18:21Z [---] followers, [---] engagements

"Product updates: Better search & revamped docs Four major features shipped in Braintrust over the last two weeks. 0:00 - Intro 0:03 - Thread Layout Search 0:45 - Raw Traces 1:32 - Span Tagging 2:06 - Restructured Documentation Find the complete list on our changelog and share your feedback on X Discord email or in the comments. Homepage 👉 https://www.braintrust.dev/home Changelog 👉 https://www.braintrust.dev/docs/changelog GitHub 👉 https://github.com/braintrustdata/ Discord 👉 https://discord.gg/6G8s47F44X Newsletter 👉 https://www.braintrust.dev/newsletter X/Twitter 👉"
YouTube Link 2026-01-16T15:00Z [---] followers, [---] engagements

"Bringing structure to AI evals at Retool Allen Kleiner AI Engineering Lead at Retool explains what it looks like to debug a multi-agent system where a single trace can be hundreds of megabytes and hundreds of tool calls deep. He walks through how they diagnosed agents that were silently giving up on tasks how observability directly shapes their product roadmap and why quality is the non-negotiable foundation of everything his team ships"
YouTube Link 2026-02-16T15:37Z [---] followers, [--] engagements

"Making AI quality measurable at BILL Mohsen Sardari former VP of Engineering at BILL explains why quality isn't optional when you're building AI for financial automation. He walks through BILL's practice of scrutinizing every incorrect output their layered approach spanning evaluations grounding checks and guardrails and how product managers shifted from writing PRDs to contributing directly to eval datasets a change that helped them ship multiple agents in a single quarter"
YouTube Link 2026-02-16T15:37Z [---] followers, [--] engagements

"Improving AI quality in real workflows at Navan Sarav Bhatia engineering leader at Navan shares how her team evaluates AI voice agents that make real phone calls to hotel front desks around the world. She explains why a completed call doesn't always mean a successful outcome how user behavior drove them to build memory into their agents and why she thinks the teams that institutionalize evals will be the ones that build great AI"
YouTube Link 2026-02-16T15:40Z [---] followers, [--] engagements

"Intro to Multimodal Evals with Braintrust Learn how to write evals for datasets with images and other files"
YouTube Link 2025-10-31T05:44Z [---] followers, [---] engagements

"Building a deep research agent with Temporal and Braintrust Here's a walkthrough of building deep research agent using Temporal workflows for durable execution and Braintrust for tracing and prompt iteration. 0:00 Intro 0:32 How Temporal workflows make agents durable 0:45 Full observability with Braintrust tracing 1:10 Inspecting traces: activities spans and tool calls 1:28 Loading prompts from Braintrust at runtime 1:45 The iteration loop: trace update rerun Full example in the Braintrust cookbook: https://www.braintrust.dev/docs/cookbook/recipes/TemporalDeepResearch Homepage 👉"
YouTube Link 2026-01-20T15:37Z [---] followers, [---] engagements

"Intro to Logging with Braintrust In this video we walk through how to enable logging in Braintrust for applications using the OpenAI Agent SDK"
YouTube Link 2025-09-17T23:42Z [---] followers, [---] engagements

"From traces to evals at Vercel Malte Ubl CTO of Vercel explains how evals became the foundation of iteration velocity for v0. He talks through what happens when a new frontier model drops and you need to be first to ship it why the shift from one-shot to multi-step agents made observability far more complex and the deep collaboration between Vercel and Braintrust on representing the increasingly complex AI API stack"
YouTube Link 2026-02-16T15:38Z [---] followers, [--] engagements

"In the Loop with Braintrust: Technical Q&A Join Braintrust CEO Ankur Goyal for a virtual Q&A session designed for technical leaders and builders shaping the future of AI-driven applications. Originally recorded on April [--] 2025"
YouTube Link 2025-04-22T19:15Z [---] followers, [---] engagements

"How to evaluate AI agents with Braintrust Join Braintrust CEO Ankur Goyal for a live session on how to evaluate AI agents effectively. We'll break down the basics of getting started with evaluations choosing or writing scoring functions and applying these concepts with practical examples from Anthropic's recent guide to building effective agents. We'll also be joined by Vitor Balocco from Zapier who will share how his team has integrated evaluations into their CI/CD pipeline for their agentic features like Zapier Agents. This is a great opportunity to learn actionable steps to improve your"
YouTube Link 2025-06-10T20:19Z [---] followers, [----] engagements

"Improving AI quality in real workflows at Navan Sarav Bhatia engineering leader at Navan shares how her team evaluates AI voice agents that make real phone calls to hotel front desks around the world. She explains why a completed call doesn't always mean a successful outcome how user behavior drove them to build memory into their agents and why she thinks the teams that institutionalize evals will be the ones that build great AI"
YouTube Link 2026-02-16T15:40Z [---] followers, [--] engagements

"Shipping fast without losing AI quality at Replit Luis Hctor Chvez CTO of Replit explains how observability changed the way Replit builds its AI-powered platform. He shares how they discovered thousands of users were struggling with the same auth problem why focusing on patterns across sessions rather than individual traces lets the team fix entire families of issues and how cutting trace visibility from minutes to real-time transformed their debugging workflow"
YouTube Link 2026-02-16T15:39Z [---] followers, [--] engagements

"How Browserbase benchmarks browser agents Paul Klein founder of Browserbase explains why reliable browser agents need both browser observability and model observability working together. He shares how they built a public evals dashboard with Braintrust"
YouTube Link 2026-02-16T15:39Z [---] followers, [--] engagements

"Debugging and evaluating AI at Notion Sarah Sachs leads AI modeling at Notion where [--] engineers ship AI features across search agents and workspace automation. She walks through how Notion's eval approach evolved from simple prompt chains to complex agentic path-finding how they caught a tricky multilingual bug across Japanese Korean and English workspaces and why they've committed to rebuilding their AI framework every time a new generation of models changes what's possible"
YouTube Link 2026-02-16T15:38Z [---] followers, [--] engagements

"From traces to evals at Vercel Malte Ubl CTO of Vercel explains how evals became the foundation of iteration velocity for v0. He talks through what happens when a new frontier model drops and you need to be first to ship it why the shift from one-shot to multi-step agents made observability far more complex and the deep collaboration between Vercel and Braintrust on representing the increasingly complex AI API stack"
YouTube Link 2026-02-16T15:38Z [---] followers, [--] engagements

"Making AI quality measurable at BILL Mohsen Sardari former VP of Engineering at BILL explains why quality isn't optional when you're building AI for financial automation. He walks through BILL's practice of scrutinizing every incorrect output their layered approach spanning evaluations grounding checks and guardrails and how product managers shifted from writing PRDs to contributing directly to eval datasets a change that helped them ship multiple agents in a single quarter"
YouTube Link 2026-02-16T15:37Z [---] followers, [--] engagements

"Bringing structure to AI evals at Retool Allen Kleiner AI Engineering Lead at Retool explains what it looks like to debug a multi-agent system where a single trace can be hundreds of megabytes and hundreds of tool calls deep. He walks through how they diagnosed agents that were silently giving up on tasks how observability directly shapes their product roadmap and why quality is the non-negotiable foundation of everything his team ships"
YouTube Link 2026-02-16T15:37Z [---] followers, [--] engagements

"Observing and improving AI at scale at Dropbox Josh Clemm VP of Engineering at Dropbox walks through the full evolution of their eval practice for Dash. He breaks down their multi-tier pipeline [---] smoke tests before merge 10000+ full-suite tests after and real-time LLM-as-judge in production and explains why his product teams now codify taste tone and success criteria into evals before writing a line of product code"
YouTube Link 2026-02-16T15:36Z [---] followers, [--] engagements

"Why Evals Are Important #ai #tech #evals #observability #logs #data #braintrust #explained"
YouTube Link 2026-02-12T17:57Z [---] followers, [----] engagements

"3 Reasons To Use Remote Evals #ai #evals #observability #braintrust #llms #coding #explained #tech"
YouTube Link 2026-02-11T19:14Z [---] followers, [----] engagements

"Product updates: Span tables and multiple custom trace views Four features shipped in Braintrust over the last two weeks. 0:03 - Spans as Table Rows 0:47 - TypeScript & Python Autocomplete 1:05 - Per-Data Point Experiment Comparison 1:54 - Multiple Trace Views Find the complete list on our changelog and share your feedback on X Discord email or in the comments. Homepage 👉 https://www.braintrust.dev/home Changelog 👉 https://www.braintrust.dev/docs/changelog GitHub 👉 https://github.com/braintrustdata/ Discord 👉 https://discord.gg/braintrust Newsletter 👉"
YouTube Link 2026-02-09T17:40Z [---] followers, [---] engagements

"Making your AI better at detecting spam Here's a walkthrough of building your first spam classifier using Braintrust with structured outputs custom scorers and model comparison. 0:00 Intro to building a spam classifier 0:14 Review the dataset 0:38 Creating a playground environment 1:33 Using structured outputs 2:11 Writing a custom deterministic scorer for correctness 2:45 Running a full eval experiment 3:06 Comparing models: swapping to o3-mini 3:59 Conclusion Full example in the Braintrust cookbook: https://github.com/braintrustdata/braintrust-cookbook/tree/main/examples/SpamClassifier"
YouTube Link 2026-01-30T00:44Z [---] followers, [---] engagements

"Intro to Braintrust: AI Observability and Evals An end-to-end walkthrough of Braintrust the AI observability platform for building quality AI products. Using a customer support chatbot example I show you how to use evals and observability to build trust in your AI systems. 0:00 Intro: The AI iteration problem 0:24 What is Braintrust: evals + observability 0:38 Demo setup: SunshineCo support chatbot 0:57 Setting up AI providers in Braintrust 1:20 Building your first eval in the playground 2:07 Using AutoEvals and LLM-as-a-judge scorers 2:35 Brand alignment scorer with chain of thought 3:08"
YouTube Link 2026-01-22T17:11Z [---] followers, [----] engagements

"4 Reason To Create AI Experiment #ai #evals #observability #braintrust #tech #llm #logging #monitor"
YouTube Link 2026-01-21T18:32Z [---] followers, [----] engagements

"Building a deep research agent with Temporal and Braintrust Here's a walkthrough of building deep research agent using Temporal workflows for durable execution and Braintrust for tracing and prompt iteration. 0:00 Intro 0:32 How Temporal workflows make agents durable 0:45 Full observability with Braintrust tracing 1:10 Inspecting traces: activities spans and tool calls 1:28 Loading prompts from Braintrust at runtime 1:45 The iteration loop: trace update rerun Full example in the Braintrust cookbook: https://www.braintrust.dev/docs/cookbook/recipes/TemporalDeepResearch Homepage 👉"
YouTube Link 2026-01-20T15:37Z [---] followers, [---] engagements

"LLM Logs Breakdown #ai #evals #observability #braintrust #tech #coding #vibecoding #engineer"
YouTube Link 2026-01-16T18:12Z [---] followers, [----] engagements

"Product updates: Better search & revamped docs Four major features shipped in Braintrust over the last two weeks. 0:00 - Intro 0:03 - Thread Layout Search 0:45 - Raw Traces 1:32 - Span Tagging 2:06 - Restructured Documentation Find the complete list on our changelog and share your feedback on X Discord email or in the comments. Homepage 👉 https://www.braintrust.dev/home Changelog 👉 https://www.braintrust.dev/docs/changelog GitHub 👉 https://github.com/braintrustdata/ Discord 👉 https://discord.gg/6G8s47F44X Newsletter 👉 https://www.braintrust.dev/newsletter X/Twitter 👉"
YouTube Link 2026-01-16T15:00Z [---] followers, [---] engagements

"Playgrounds VS Experiments #ai #observability #evals #tech #softwareengineer #llm #vibecoding"
YouTube Link 2026-01-14T23:16Z [---] followers, [----] engagements

"How To Log LLM Calls #ai #evals #observability #llm #braintrust #vibecoding #logs #data"
YouTube Link 2026-01-13T17:30Z [---] followers, [----] engagements

"How To Turn Messy Production Logs Into Dataset #ai #evals #observability #data #logs #vibecoding"
YouTube Link 2026-01-12T17:38Z [---] followers, [----] engagements

"Intro to Loop: the AI agent for evals and observability in Braintrust Learn how you can use Loop in Braintrust to optimize your eval and observability workflows"
YouTube Link 2025-11-24T16:10Z [---] followers, [---] engagements

"Evals for real-world voice agents This video breaks down practical steps to build measure and scale voice agents with consistency and quality in production. We discuss how Navan runs evals for its AI voice agent to solve the last-mile challenges for travelers and finance teams"
YouTube Link 2025-11-18T22:04Z [---] followers, [---] engagements

"Intro to Multimodal Evals with Braintrust Learn how to write evals for datasets with images and other files"
YouTube Link 2025-10-31T05:44Z [---] followers, [---] engagements

"Intro to Human Review with Braintrust Learn how to set up human review as part of your eval and observability workflows in Braintrust"
YouTube Link 2025-10-22T18:21Z [---] followers, [---] engagements

"Intro to Remote Agent Evals with Braintrust In this video we walk through how you can connect an agent running on your local computer to Braintrust for easier iteration and collaboration. For more information visit the documentation: https://www.braintrust.dev/docs/guides/remote-evals"
YouTube Link 2025-10-14T17:26Z [---] followers, [---] engagements

"Intro to Evals with Braintrust In this video we walk through the complete eval workflow including creating datasets prompts and scorers"
YouTube Link 2025-10-07T20:14Z [---] followers, [----] engagements

"Measure what matters with Braintrust: Intro to AI evals This session breaks down the basics of evals - how to optimize prompts write good scoring functions and manage datasets. We cover framework and model-agnostic approaches that work with any AI application"
YouTube Link 2025-10-07T19:58Z [---] followers, [----] engagements

"Intro to Logging with Braintrust In this video we walk through how to enable logging in Braintrust for applications using the OpenAI Agent SDK"
YouTube Link 2025-09-17T23:42Z [---] followers, [---] engagements

"Evaluating agents: how we built Loop the AI assistant for evals Join Doug Guthrie Solutions Engineer at Braintrust for a walkthrough of Loop Braintrusts new AI assistant for evals. We cover best practices for evaluating complex agentic systems and how Loop can help you generate synthetic datasets improve your prompt tasks and write better scoring functions"
YouTube Link 2025-07-16T18:46Z [---] followers, [----] engagements

"What to do when a new model comes out Every week new state-of-the-art AI models are released promising breakthrough performance but how can you know if they're right for your app Join Phil Hetzel Solutions Engineer at Braintrust as he shares practical strategies for evaluating new AI models with real-world data. In this webinar you'll learn how to: - Establish baseline performance metrics for your current AI models - Effectively benchmark new AI models against your application's real data - Compare model performance to confidently decide on deployment - Swap models with minimal disruption -"
YouTube Link 2025-06-11T18:28Z [---] followers, [---] engagements

"How to evaluate AI agents with Braintrust Join Braintrust CEO Ankur Goyal for a live session on how to evaluate AI agents effectively. We'll break down the basics of getting started with evaluations choosing or writing scoring functions and applying these concepts with practical examples from Anthropic's recent guide to building effective agents. We'll also be joined by Vitor Balocco from Zapier who will share how his team has integrated evaluations into their CI/CD pipeline for their agentic features like Zapier Agents. This is a great opportunity to learn actionable steps to improve your"
YouTube Link 2025-06-10T20:19Z [---] followers, [----] engagements

"In the Loop with Braintrust: Technical Q&A Join Braintrust CEO Ankur Goyal for a virtual Q&A session designed for technical leaders and builders shaping the future of AI-driven applications. Originally recorded on April [--] 2025"
YouTube Link 2025-04-22T19:15Z [---] followers, [---] engagements

"Announcing Braintrust's $36M Series A We're thrilled to announce that we've raised $36 million to advance the future of AI software engineering bringing our total funding to $45 million"
YouTube Link 2024-10-08T14:00Z [---] followers, [----] engagements

Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing