🏢 Come to our HQ in SF
🤝 Meet our team
🚀 Kickstart your sales career at LangChain
Don’t miss our SDR recruiting social on October 27th! Save your spot today.
🎟️ RSVP: https://t.co/87Ge22Mvif https://t.co/d6TdSAgTGO
Join our EMEA Deep Life Sci Workshop: Agent Engineering for Life Sciences for a hands-on look at how to build, trace, evaluate, and improve research agents for complex life sciences workflows.
🌍 Register for the EMEA session: https://t.co/Ilm9IwoCEo https://t.co/rG40nCIj0k
Agent evals run through the same graph.
Every eval, from single-reply fixtures to simulated multi-turn conversations with LLM patient personas, runs against the real agent, so what they score is exactly what a patient would meet.
Everything is measured in LangSmith.
1️⃣ All conversations land as a trace, are annotated by reviewers, and feed the loop.
2️⃣ Datasets and experiments live in the same place, allowing them to run themed dataset model configs and compare results.
3️⃣ Triage and improvement workflows read their inputs and write scores back through LangSmith.
The GitHub Security Lab used an open-source agent to find 24 Android vulnerabilities, including a location leak in a navigation app with 10M downloads.
How to run the taskflows on your own project 💡
https://t.co/9L79bg7pfG
If you loved our jev pod with @completeskeptic and are in the react/js/frontend community (especially if i've seen your work before), hit me up and i can refer you in to typesafe
@benthompson also @ritakozlov i am slowly converting our broadway group to be #nothingbutNET fans
(people! sign up for my next show https://t.co/IPctl08GnL -> preview here
https://t.co/GlxowfKmmh)
this one is EVEN MORE HIGH PRODUCTION VALUE WTF https://t.co/HeaVCsWI5E
fellow youtubers:
at this point we currently own probably the highest volume A/B testing operation in tech youtube (publishing avg ~2-10 videos* a day this year of real technical content)
is there any theory/tooling that you have that we should be testing? mostly i have fable/astra managing our channel but probably could use advice or ideas on what "next level" looks like
some findings below:
*yes seriously, every day, its a lot, we will probably cap it here for a few years in order to do justice to the speakers we already have, quantity is a nongoal for us despite appearances
ok i really need the prompt(s) for this video because this is near-kurzgesagt level clarity of explanation (not yet illustration) https://t.co/xRkcrZKSqD
Your workflows have changed with AI. How about your setup?
Physical controls are back. Take the new Logitech MX Keypad, now directly integrated with the GitHub Copilot app.
This experience allows you to run agentic workflows with control, map a repeated prompt, start or resume a session, and help you stay in flow.
https://t.co/zbcYD8xQKf
@dexhorthy @Jeffdelaney23 @ThePrimeagen kinda like this chart to tell the story. basically no love for 2 years and then slowly we get recommended via browsing. our CTR sucks. https://t.co/XcQM6lzVvU