# ![@braintrust Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1687132266391289856.png) @braintrust Braintrust

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

### Engagements: [---] [#](/creator/twitter::1687132266391289856/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1687132266391289856/c:line/m:interactions.svg)

- [--] Week [-----] -32%
- [--] Month [------] -26%
- [--] Months [-------] -50%
- [--] Year [-------] -33%

### Mentions: [--] [#](/creator/twitter::1687132266391289856/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1687132266391289856/c:line/m:posts_active.svg)

- [--] Week [--] +18%
- [--] Month [--] +35%
- [--] Months [---] +250%
- [--] Year [---] +148%

### Followers: [-----] [#](/creator/twitter::1687132266391289856/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1687132266391289856/c:line/m:followers.svg)

- [--] Week [-----] +0.07%
- [--] Month [-----] +1.10%
- [--] Months [-----] +15%
- [--] Year [-----] +45%

### CreatorRank: [---------] [#](/creator/twitter::1687132266391289856/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1687132266391289856/c:line/m:influencer_rank.svg)

### Social Influence

**Social category influence**
[cryptocurrencies](/list/cryptocurrencies)  99% [technology brands](/list/technology-brands)  10% [social networks](/list/social-networks)  2% [finance](/list/finance)  1% [events](/list/events)  1%

**Social topic influence**
[braintrust](/topic/braintrust) #5, [ai](/topic/ai) 26%, [llm](/topic/llm) 3%, [how to](/topic/how-to) 3%, [hubspot](/topic/hubspot) #76, [dropbox](/topic/dropbox) 3%, [vercel](/topic/vercel) 2%, [calls](/topic/calls) 2%, [finance](/topic/finance) 2%, [open ai](/topic/open-ai) 2%

**Top accounts mentioned or mentioned by**
[@ankrgyl](/creator/undefined) [@vercel](/creator/undefined) [@darubberduckiee](/creator/undefined) [@dominikkoch](/creator/undefined) [@modal](/creator/undefined) [@tryramp](/creator/undefined) [@dvddkkim](/creator/undefined) [@akionuernberger](/creator/undefined) [@marcklingen](/creator/undefined) [@i_mohanram](/creator/undefined) [@hubspot](/creator/undefined) [@bernhardsson](/creator/undefined) [@braintrustdata](/creator/undefined) [@tolanworld](/creator/undefined) [@dropbox](/creator/undefined) [@navans](/creator/undefined) [@browserbase](/creator/undefined) [@llamaindex](/creator/undefined) [@retool](/creator/undefined) [@debsourya005](/creator/undefined)

**Top assets mentioned**
[Braintrust (BTRST)](/topic/braintrust)
### Top Social Posts
Top posts by engagements in the last [--] hours

"We've eliminated user-based pricing. Invite more engineers PMs and cross-functional partners and build quality AI together"  
[X Link](https://x.com/braintrust/status/2009304598175981989)  2026-01-08T16:42Z [----] followers, [----] engagements


"Learn more https://braintrustdata.link/invite https://braintrustdata.link/invite"  
[X Link](https://x.com/braintrust/status/2009304599690092645)  2026-01-08T16:42Z [----] followers, [---] engagements


"Ralph doesn't just eat paste he eats tokens. If you're going to let Ralph Wiggum run overnight use Braintrust to log every iteration every error and every token spent"  
[X Link](https://x.com/braintrust/status/2011845852600353277)  2026-01-15T17:00Z [----] followers, [---] engagements


"Learn how https://www.braintrust.dev/blog/ralph-wiggum-debugging https://www.braintrust.dev/blog/ralph-wiggum-debugging"  
[X Link](https://x.com/braintrust/status/2011845853510513099)  2026-01-15T17:00Z [----] followers, [---] engagements


"What's new: - Thread layout search: search for keywords inside long LLM traces - Raw trace search: search & download a JSON export of your logs - Span tagging: Tag any span & filter for that tag later on - Restructured docs: new sections for deploy evaluate & annotate"  
[X Link](https://x.com/braintrust/status/2012217157661192298)  2026-01-16T17:35Z [----] followers, [----] engagements


"Read more https://braintrustdata.link/updates-1-16-26 https://braintrustdata.link/updates-1-16-26"  
[X Link](https://x.com/braintrust/status/2012217158642622540)  2026-01-16T17:35Z [----] followers, [---] engagements


"Trace workshop @notionhq @EricTLiu is leading an intro to evals workshop for PMs with @daRubberDuckiee. Come ship your first eval"  
[X Link](https://x.com/braintrust/status/2015452871211340099)  2026-01-25T15:53Z [----] followers, [---] engagements


"In-person only (SF) on Feb 25: https://www.braintrust.dev/trace https://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2015453444128321588)  2026-01-25T15:55Z [----] followers, [---] engagements


"Build durable AI agents with @temporalio get built-in observability with Braintrust"  
[X Link](https://x.com/braintrust/status/2013640185406509415)  2026-01-20T15:50Z [----] followers, [---] engagements


"Learn more https://braintrustdata.link/temporal https://braintrustdata.link/temporal"  
[X Link](https://x.com/braintrust/status/2013640187608211953)  2026-01-20T15:50Z [----] followers, [---] engagements


"Trace talk @replit On Feb [--] @pirroh takes the stage to discuss agent observability at scale with @ankrgyl. If you're in SF come: http://www.braintrust.dev/trace http://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2014393890225217800)  2026-01-22T17:45Z [----] followers, [----] engagements


"Is bash really all your agent needs We worked with @vercel to run head-to-head evals. Result: tool choice matters but evals matters more https://braintrustdata.link/bash-agent-evals https://braintrustdata.link/bash-agent-evals"  
[X Link](https://x.com/braintrust/status/2014430378975441234)  2026-01-22T20:10Z [----] followers, [---] engagements


"Get started with evals observability and Braintrust in [--] minutes. We walk through building a production-ready AI support chatbot with regression detection online & offline scoring and prompt versioning"  
[X Link](https://x.com/braintrust/status/2014741184954954201)  2026-01-23T16:45Z [----] followers, [---] engagements


"Your agent can be better at detecting spam. Here's how to write an eval to compare o3-mini to Claude [---] Sonnet on spammy messages and why the lower-scoring model might actually be right"  
[X Link](https://x.com/braintrust/status/2017266604073951256)  2026-01-30T16:00Z [----] followers, [---] engagements


"Watch it here https://youtu.be/5kw-JusvdtA https://youtu.be/5kw-JusvdtA"  
[X Link](https://x.com/braintrust/status/2017266604891836526)  2026-01-30T16:00Z [----] followers, [---] engagements


"Trace talk @tryramp Adison Lampert shares how her team uses evals and traces to catch edge cases and manage risk in financial AI systems"  
[X Link](https://x.com/braintrust/status/2017678251804491778)  2026-01-31T19:15Z [----] followers, [---] engagements


"Trace workshop @hubspot Martin Serrano is leading an intro to evals workshop for engineers. Get started with evals and observability using the Braintrust SDK"  
[X Link](https://x.com/braintrust/status/2018017770101776659)  2026-02-01T17:45Z [----] followers, [---] engagements


"@HubSpot Bring your laptop. Feb [--]. San Francisco. In-person only. https://www.braintrust.dev/trace https://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2018023234348999111)  2026-02-01T18:06Z [----] followers, [---] engagements


"@tryramp See you on Feb [--] at the California Academy of Sciences in SF. https://www.braintrust.dev/trace https://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2018023558350590238)  2026-02-01T18:08Z [----] followers, [---] engagements


"@modal @bernhardsson Space is limited. See you on February [--] in SF: https://www.braintrust.dev/trace https://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2018338640472981957)  2026-02-02T15:00Z [----] followers, [---] engagements


"AI is moving into production at FinServ companies with direct impacts on customers revenue and risk. Join Braintrust for a session on how FinServ leaders can improve AI in production using evals and AI observability"  
[X Link](https://x.com/braintrust/status/2018743762101395472)  2026-02-03T17:49Z [----] followers, [---] engagements


"See you there https://luma.com/finserv https://luma.com/finserv"  
[X Link](https://x.com/braintrust/status/2018743816342180276)  2026-02-03T17:50Z [----] followers, [---] engagements


"Trace is sold out. Join the waitlist https://www.braintrust.dev/trace https://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2019521374079840652)  2026-02-05T21:19Z [----] followers, [---] engagements


"Subscribe to the Braintrust YouTube to catch the keynote after the event https://www.youtube.com/@BraintrustData https://www.youtube.com/@BraintrustData"  
[X Link](https://x.com/braintrust/status/2019521385853317326)  2026-02-05T21:19Z [----] followers, [---] engagements


"Read the cookbook https://braintrustdata.link/12-labs-cookbook https://braintrustdata.link/12-labs-cookbook"  
[X Link](https://x.com/braintrust/status/2019861317725642939)  2026-02-06T19:50Z [----] followers, [---] engagements


"What's new: - Spans as table rows: filter experiments at the span level - Autocomplete + linting: validate your code when writing scorers - Data point comparison: see how experiments performed on one input - Multiple trace views: switch between custom views for easier review"  
[X Link](https://x.com/braintrust/status/2020914470864785504)  2026-02-09T17:35Z [----] followers, [---] engagements


"Read more https://braintrustdata.link/updates-2-9-26 https://braintrustdata.link/updates-2-9-26"  
[X Link](https://x.com/braintrust/status/2020914472269865072)  2026-02-09T17:35Z [----] followers, [---] engagements


"Watch the demo https://braintrustdata.link/remote-agent-eval https://braintrustdata.link/remote-agent-eval"  
[X Link](https://x.com/anyuser/status/2021276849125376042)  2026-02-10T17:35Z [----] followers, [---] engagements


"Trace lineup is live. Speakers from Ramp Replit Notion Zendesk Dropbox HubSpot FanDuel Box and more. Bring your team. In person only. Space is limited. Feb [--] in SF http://braintrust.dev/trace http://braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2008936915505197381)  2026-01-07T16:20Z [----] followers, [----] engagements


"Trace talk @modal @bernhardsson will discuss the shift from shipping AI features to running AI systems and whats next for production AI"  
[X Link](https://x.com/braintrust/status/2018338639378272581)  2026-02-02T15:00Z [----] followers, [----] engagements


"Evaluate how good Twelve Labs' language model Pegasus is at actually understanding what's going on in a video using Hugging Face's MMVU dataset & Braintrust for evals"  
[X Link](https://x.com/braintrust/status/2019861295072194939)  2026-02-06T19:50Z [----] followers, [---] engagements


"What are remote evals and why are they useful [--]. Some evals require complex dependencies (game engines databases specialized hardware) [--]. Product managers and designers need to run evals too but don't always have a dev environment setup [--]. Running evals can be GPU-intensive Remote evals run evaluation code on one machine while triggering and controlling it from anywhere. The heavy dependencies stay where they need to be but teams can still iterate on test cases modify parameters and see results. Braintrust engineer Alex built an AI assistant for Unreal Engine that can execute commands like"  
[X Link](https://x.com/braintrust/status/2021276847934222826)  2026-02-10T17:35Z [----] followers, [---] engagements


"How do you create an eval to judge how "good" AI-generated music is LLMs don't have ears and music is subjective so LLM-as-a-judge won't work. This is an example that calls for human review: collect subjective ratings from people directly in the workflow making it easy to compare results when automated scoring isn't possible. In this video Alex builds an eval that asks GPT-4.5 and Claude [---] Sonnet to generate music by writing Tone.js code. He sets up a custom human review for "goodness": a 0-10 slider for how enjoyable the music is. After running both experiments he listens to each generated"  
[X Link](https://x.com/braintrust/status/2021639231009911232)  2026-02-11T17:35Z [----] followers, [---] engagements


"Watch the demo https://braintrustdata.link/human-review https://braintrustdata.link/human-review"  
[X Link](https://x.com/braintrust/status/2021639232029090062)  2026-02-11T17:35Z [----] followers, [---] engagements


"Opus [---] and GPT-5.3 just dropped and everyone wants to know which is better. But don't obsess over the leaderboard rankings. Understand what the benchmarks are telling you and pick the right model for your needs. Here's a 5-part guide on major benchmarks (SWE-bench HLE OSWorld) and what they actually measure. https://twitter.com/i/web/status/2022018975035429083 https://twitter.com/i/web/status/2022018975035429083"  
[X Link](https://x.com/braintrust/status/2022018975035429083)  2026-02-12T18:44Z [----] followers, [---] engagements


"Read the blog https://braintrustdata.link/model-measurement https://braintrustdata.link/model-measurement"  
[X Link](https://x.com/braintrust/status/2022018976037957873)  2026-02-12T18:44Z [----] followers, [---] engagements


"Coursera built a four-step approach to evaluating their AI features with Braintrust: [--]. Define clear evaluation criteria up front [--]. Curate targeted datasets [--]. Implement both heuristic and model-based scorers [--]. Run evaluations and iterate rapidly"  
[X Link](https://x.com/braintrust/status/2022367421948899635)  2026-02-13T17:49Z [----] followers, [---] engagements


"Read the case study https://braintrustdata.link/coursera https://braintrustdata.link/coursera"  
[X Link](https://x.com/braintrust/status/2022367434678698423)  2026-02-13T17:49Z [----] followers, [--] engagements


"To run an eval all you need is a task dataset and scorers. When you put those together you can expose regressions or blind spots and drive improvements to your AI product"  
[X Link](https://x.com/braintrustdata/status/1977801528632074692)  2025-10-13T18:20Z [----] followers, [---] engagements


"Read more to learn how to get started: https://braintrust.dev/blog/measuring-what-matters https://braintrust.dev/blog/measuring-what-matters"  
[X Link](https://x.com/braintrustdata/status/1977801529332527447)  2025-10-13T18:20Z [----] followers, [---] engagements


"If you're building an agent locally but still want to iterate on evals in Braintrust you can use remote evals. Here's how to get started"  
[X Link](https://x.com/braintrust/status/1978142622196625492)  2025-10-14T16:55Z [----] followers, [---] engagements


"We're hosting the official @vercel Ship AI afterparty with our friends at Browserbase. Come hang out with other builders in SF on Oct 23: https://luma.com/gxgoscgt https://luma.com/gxgoscgt"  
[X Link](https://x.com/braintrust/status/1978521285870104751)  2025-10-15T18:00Z [----] followers, [----] engagements


"Braintrust is now available on the @Vercel Marketplace. Run evals monitor quality and user experience and benchmark across models all from your Vercel dashboard"  
[X Link](https://x.com/braintrust/status/1978853470745640989)  2025-10-16T16:00Z [----] followers, [---] engagements


"@vercel Learn more: Check out the Vercel Marketplace listing: https://vercel.com/marketplace/braintrust https://braintrust.dev/blog/vercel-marketplace https://vercel.com/marketplace/braintrust https://braintrust.dev/blog/vercel-marketplace"  
[X Link](https://x.com/braintrustdata/status/1978861094656418246)  2025-10-16T16:30Z [----] followers, [---] engagements


"New JSON attachments let you log arbitrarily large or nested JSON beyond any trace limits. Use them for long conversation transcripts doc collections embeddings and more"  
[X Link](https://x.com/braintrust/status/1979247300862939142)  2025-10-17T18:05Z [----] followers, [---] engagements


"Learn more: https://www.braintrust.dev/docs/guides/attachments#json-attachments https://www.braintrust.dev/docs/guides/attachments#json-attachments"  
[X Link](https://x.com/braintrustdata/status/1979247301974487094)  2025-10-17T18:05Z [----] followers, [---] engagements


"Join us next week for AI evals on Tap an official @githubuniverse [----] side event - featuring lightning talks on how real teams ship AI that works - amidst cars coffee & conversations at the Motoring Club SF. Sign up: https://luma.com/oy066i3b https://luma.com/oy066i3b"  
[X Link](https://x.com/braintrust/status/1980695592054485269)  2025-10-21T18:00Z [----] followers, [---] engagements


"Non-technical teammates at @tolanworld spend hours a day in Braintrust making sure that everyone's favorite alien BFF feels as authentic as possible. Their eval workflow allows them to iterate on prompts and ship updates - all without writing any code"  
[X Link](https://x.com/braintrust/status/1981014257379541422)  2025-10-22T15:06Z [----] followers, [----] engagements


"@tolanworld Learn more: https://www.braintrust.dev/blog/portola https://www.braintrust.dev/blog/portola"  
[X Link](https://x.com/braintrustdata/status/1981014258562326621)  2025-10-22T15:06Z [----] followers, [---] engagements


"Human review is still a key part of many teams' eval workflows especially when it comes to subjective definitions of quality like for music generation. Here's how to get started with human review and maximize your productivity:"  
[X Link](https://x.com/braintrust/status/1981392169547030640)  2025-10-23T16:08Z [----] followers, [---] engagements


"New on @readtechnically: Why evals are critical for AI that actually works. Shows how teams evolve from "vibes-based" prompt testing systematic evaluation. Plus the story of how we fixed a blocking bug in [--] min during a deal"  
[X Link](https://x.com/braintrust/status/1981757579047936483)  2025-10-24T16:20Z [----] followers, [---] engagements


"Here's what's new in Braintrust: - Spans in logs table - "Pretty" data view - Stream @Vercel traces to Braintrust - Java SDK"  
[X Link](https://x.com/braintrust/status/1982122878007955631)  2025-10-25T16:31Z [----] followers, [---] engagements


"@vercel Read more: https://braintrustdata.link/updates-10-25-2025 https://braintrustdata.link/updates-10-25-2025"  
[X Link](https://x.com/braintrust/status/1982122878762918062)  2025-10-25T16:31Z [----] followers, [---] engagements


"Another great Evals on Tap last night post @github Universe. Thanks for everyone that came by see you at the next one"  
[X Link](https://x.com/braintrust/status/1983572142328586262)  2025-10-29T16:30Z [----] followers, [---] engagements


"Engineers on the @Dropbox Dash team use Braintrust to make sure their conversational AI is as accurate and reliable as possible. Their automated eval workflow allows them to ship prompt changes and model updates with the same rigor as production code"  
[X Link](https://x.com/braintrust/status/1984008821241454602)  2025-10-30T21:25Z [----] followers, [----] engagements


"@Dropbox Learn more: https://www.braintrust.dev/blog/dropbox https://www.braintrust.dev/blog/dropbox"  
[X Link](https://x.com/braintrust/status/1984008878065955043)  2025-10-30T21:25Z [----] followers, [---] engagements


"There's nothing scarier than shipping without evals. Learn how to evaluate even the spookiest images with Braintrust"  
[X Link](https://x.com/braintrust/status/1984305825092161937)  2025-10-31T17:05Z [----] followers, [----] engagements


"Missed @ankrgyl at @Vercel Ship AI Session replays are now available"  
[X Link](https://x.com/braintrust/status/1985484390839849335)  2025-11-03T23:09Z [----] followers, [---] engagements


"@ankrgyl @vercel Learn more about building the agentic ecosystem for developers: https://vercel.com/ship/ai/session/agent-marketplace-panel-showcase-i https://vercel.com/ship/ai/session/agent-marketplace-panel-showcase-i"  
[X Link](https://x.com/braintrustdata/status/1985484392416854178)  2025-11-03T23:09Z [----] followers, [---] engagements


"@navan's AI voice agent is built to solve challenges for travelers and finance teams. Sign up to hear how their engineering team uses multimodal evals to make sure the agent is truly helpful"  
[X Link](https://x.com/braintrustdata/status/1985844574749618500)  2025-11-04T23:00Z [----] followers, [--] engagements


"From rebooking travel to managing expenses @navan's AI voice agent tackles real-world challenges for travelers and finance teams. Learn how their engineering team uses multimodal evals to ensure its truly helpful"  
[X Link](https://x.com/braintrust/status/1986159297428877599)  2025-11-05T19:50Z [----] followers, [---] engagements


"Here's what's new in Braintrust: - New documentation site - Editable and queueable Loop messages - AI proxy support for new models Read more: https://www.braintrust.dev/broadcasts/64d8d2b4-8d2b-4b8e-882b-30a3c4ab47aa https://www.braintrust.dev/broadcasts/64d8d2b4-8d2b-4b8e-882b-30a3c4ab47aa"  
[X Link](https://x.com/braintrust/status/1987233449229353468)  2025-11-08T18:59Z [----] followers, [----] engagements


"Update: @braintrustdata @braintrust"  
[X Link](https://x.com/braintrust/status/1987239173020160183)  2025-11-08T19:21Z [----] followers, 19.5K engagements


"See you at AWS re:Invent next month We're hosting an afterparty on Wed Dec [--] with @browserbase @modal & @llama_index"  
[X Link](https://x.com/braintrust/status/1988006640402993459)  2025-11-10T22:11Z [----] followers, [----] engagements


"@browserbase @modal @llama_index Come through https://luma.com/lateshift https://luma.com/lateshift"  
[X Link](https://x.com/braintrust/status/1988006672200003697)  2025-11-10T22:11Z [----] followers, [---] engagements


"Gemini [--] is now available in Braintrust"  
[X Link](https://x.com/braintrust/status/1990853862240989586)  2025-11-18T18:45Z [----] followers, [---] engagements


"AI has changed the observability pillars: Traditional metrics logs traces AI traces evals annotation"  
[X Link](https://x.com/braintrust/status/1991190505267319158)  2025-11-19T17:03Z [----] followers, [---] engagements


"Read more https://braintrustdata.link/three-pillars https://braintrustdata.link/three-pillars"  
[X Link](https://x.com/braintrust/status/1991190558400762210)  2025-11-19T17:03Z [----] followers, [---] engagements


"Build AI that works"  
[X Link](https://x.com/braintrust/status/1991916396331049393)  2025-11-21T17:07Z [----] followers, [----] engagements


"What's new in Braintrust: - Dataset schemas and form-based editing - Publicly shareable traces - Custom monitor chart generation"  
[X Link](https://x.com/braintrust/status/1992289496189079772)  2025-11-22T17:50Z [----] followers, [---] engagements


"Read more https://braintrustdata.link/updates-11-21-2025 https://braintrustdata.link/updates-11-21-2025"  
[X Link](https://x.com/braintrust/status/1992289496897835511)  2025-11-22T17:50Z [----] followers, [---] engagements


"Production AI breaks in unexpected ways. Loop helps you figure out what happened and what to fix fast"  
[X Link](https://x.com/braintrust/status/1992999808374637035)  2025-11-24T16:52Z [----] followers, 15.9K engagements


"Describe what you're looking for and Loop will help you find failure patterns surface root causes generate datasets and write precise queries when you need filters"  
[X Link](https://x.com/braintrust/status/1992999809230196999)  2025-11-24T16:52Z [----] followers, [---] engagements


"PMs use it to identify issues by impact. Engineers use it to debug and build scorers based on real traces. Teams share one view of how AI behaves in production"  
[X Link](https://x.com/braintrust/status/1992999810304016609)  2025-11-24T16:52Z [----] followers, [---] engagements


"Learn more about Loop https://braintrustdata.link/loop-launch-x https://braintrustdata.link/loop-launch-x"  
[X Link](https://x.com/braintrust/status/1992999811235172411)  2025-11-24T16:52Z [----] followers, [---] engagements


"To build Loop we went deep on real conversations patterns and prototypes across product and design engineering"  
[X Link](https://x.com/braintrust/status/1993378113225465990)  2025-11-25T17:55Z [----] followers, [---] engagements


"Heres how we built it https://braintrustdata.link/collaborative-evals-loop https://braintrustdata.link/collaborative-evals-loop"  
[X Link](https://x.com/braintrust/status/1993378113879724140)  2025-11-25T17:55Z [----] followers, [---] engagements


"Loop helps your team move faster across the entire AI development workflow. Use Loop to create scorers analyze logs clean datasets and iterate on prompts using production data. Get started with Loop"  
[X Link](https://x.com/braintrust/status/1993731738435244453)  2025-11-26T17:21Z [----] followers, [---] engagements


"And follow along with the cookbook: https://braintrustdata.link/loop-cookbook https://braintrustdata.link/loop-cookbook"  
[X Link](https://x.com/braintrust/status/1993731740914077826)  2025-11-26T17:21Z [----] followers, [---] engagements


"The team at @retool built a data-driven workflow where production logs directly inform their prioritization decisions. Using Loop they query production data semantically to surface insights in seconds turning observability into a roadmap"  
[X Link](https://x.com/braintrust/status/1994418504573886873)  2025-11-28T14:50Z [----] followers, [---] engagements


"@retool Learn more about their workflow https://braintrustdata.link/retool-blog https://braintrustdata.link/retool-blog"  
[X Link](https://x.com/braintrust/status/1994418505349804371)  2025-11-28T14:50Z [----] followers, [---] engagements


"If you're at #AWSreInvent and working with Bedrock agents learn how to deploy a Strands Agent on AgentCore with full observability"  
[X Link](https://x.com/braintrust/status/1995927672342356356)  2025-12-02T18:46Z [----] followers, [---] engagements


"Deploy now https://braintrustdata.link/aws-cookbook https://braintrustdata.link/aws-cookbook"  
[X Link](https://x.com/braintrust/status/1995927672963092503)  2025-12-02T18:46Z [----] followers, [---] engagements


"You can now vibe code custom annotation UIs directly in Braintrust. Investigate specific issues share views across your team and debug your product in a workflow that matches your use case"  
[X Link](https://x.com/braintrust/status/1998044996478410973)  2025-12-08T15:00Z [----] followers, [---] engagements


"You can now query Braintrust in SQL"  
[X Link](https://x.com/braintrust/status/1998453501890908548)  2025-12-09T18:03Z [----] followers, [---] engagements


"Trace our first user conference is on Feb [--] at the California Academy of Sciences in SF. [---] AI builders. Hands-on workshops. Live demos. Sessions taught by the teams actually shipping production AI. Save the date https://braintrustdata.link/trace-save-the-date-x https://braintrustdata.link/trace-save-the-date-x"  
[X Link](https://x.com/braintrust/status/1999173591460466979)  2025-12-11T17:45Z [----] followers, [---] engagements


"What's new in Braintrust: - Custom vibe-coded trace views - MCP servers - Slack integration"  
[X Link](https://x.com/braintrust/status/2000680831040233881)  2025-12-15T21:34Z [----] followers, [---] engagements


"Read more https://braintrustdata.link/updates-12-12-25 https://braintrustdata.link/updates-12-12-25"  
[X Link](https://x.com/braintrust/status/2000680831652692192)  2025-12-15T21:34Z [----] followers, [---] engagements


"Brainstore is the purpose-built database for AI observability. It handles the volume and complexity of modern AI systems so you can run eval workflows at scale. And it makes Braintrust 24x faster than competitors"  
[X Link](https://x.com/braintrust/status/2001720547097399488)  2025-12-18T18:25Z [----] followers, 19.6K engagements


"See the benchmarks https://braintrustdata.link/brainstore https://braintrustdata.link/brainstore"  
[X Link](https://x.com/braintrust/status/2001720548154372433)  2025-12-18T18:25Z [----] followers, [---] engagements


"Claude Code is fast for building agents. Debugging should be too. We connected Claude Code and Braintrust as a two-way system so traces flow out and production data flows back into your terminal"  
[X Link](https://x.com/braintrust/status/2003534542452240444)  2025-12-23T18:33Z [----] followers, [---] engagements


"Read more https://braintrustdata.link/claude-code https://braintrustdata.link/claude-code"  
[X Link](https://x.com/braintrust/status/2003534543140094367)  2025-12-23T18:33Z [----] followers, [---] engagements


"Watch it here https://youtu.be/qpmMxRwXzEQ https://youtu.be/qpmMxRwXzEQ"  
[X Link](https://x.com/braintrust/status/2014741187760910824)  2026-01-23T16:45Z [----] followers, [---] engagements


"RT @dvddkkim: I compared Kimi K2.5 to Sonnet [---] to see which is better at prompt optimization using @braintrust I gave it [--] scenarios --"  
[X Link](https://x.com/braintrust/status/2016388852748083542)  2026-01-28T05:52Z [----] followers, [--] engagements


"@tryramp See you on Feb [--] at the California Academy of Sciences: https://www.braintrust.dev/trace https://www.braintrust.dev/trace"  
[X Link](https://x.com/braintrust/status/2017678252769169441)  2026-01-31T19:15Z [----] followers, [---] engagements


"LLM-as-a-judge scorers are a powerful tool you can use when you need to evaluate more complex responses to LLM calls. We published an OpenAI cookbook to work through different strategies for detecting hallucinations check it out in the @OpenAIDevs cookbook library"  
[X Link](https://x.com/braintrust/status/1851282581079408736)  2024-10-29T15:18Z [----] followers, 87.2K engagements


"Were launching support for the @OpenAI Realtime API through the Braintrust Proxy accessible via a one-line code change with user-facing auth logging and evals built right in. Building AI apps with the most cutting-edge models should be simple secure and measurable"  
[X Link](https://x.com/braintrust/status/1853478795698982966)  2024-11-04T16:45Z [----] followers, [----] engagements


"Braintrust is now 80x faster than any other LLM observability platform on the market. To achieve this benchmark we built Brainstore the first database designed to handle the high scale and complexity of AI data"  
[X Link](https://x.com/braintrust/status/1896607082180473258)  2025-03-03T17:02Z [----] followers, 99.5K engagements


"Evals should be easy. Meet Loop the AI agent for automatic prompt dataset and scorer optimization. @aiDotEngineer"  
[X Link](https://x.com/braintrust/status/1930782318433910907)  2025-06-06T00:22Z [----] followers, 38.7K engagements


"Agents are transforming how we interact with technology but building them can feel like navigating a maze of frameworks. Some of the best agents follow a pretty simple pattern a while loop with tools"  
[X Link](https://x.com/braintrust/status/1953892709267087398)  2025-08-08T18:54Z [----] followers, 57.7K engagements

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