AI Coding & Agents

swyx

@swyx

more conferences could implement this. so much high value time wasted without thought https://t.co/jn93l7JyoH

Sep 24, 2026, 08:42 PM UTC

♡ 1.5K likes↻ 112 reposts↳ 70 replies

LangChain

@LangChain

Final sessions of Interrupt NYC 🎙️ Fireside Chat w/ @RogoAI CEO & Co-Founder @gabestengel 🎙️ Evaluating Agentic AI at Scale with @linkedin https://t.co/kLEMO6bftf

Sep 24, 2026, 08:09 PM UTC

♡ 13 likes↻ 1 reposts↳ 5 replies

LangChain

@LangChain

Before Interrupt wraps up, stop by the LangChain Agent Arena! 🕹️ Play 30 seconds of Tetris to train your style 👉 Choose the model that plays it for you 👀 Watch it battle the reigning champion https://t.co/tSVU2zvcCz

Sep 24, 2026, 07:39 PM UTC

♡ 11 likes↻ 0 reposts↳ 4 replies

LangChain

@LangChain

A few things you can build: 1️⃣ Annotation queues: Review and label one (or many) runs at a time 2️⃣ Experiment comparisons: Compare outputs and metrics across experiments side by side 3️⃣ Trace reviews: Build trace or thread history views to inspect app behavior https://t.co/FlkGPcfsHV

Sep 24, 2026, 07:35 PM UTC

♡ 30 likes↻ 2 reposts↳ 6 replies

LangChain

@LangChain

Another awesome feature in Managed Deep Agents 0.8

Sep 24, 2026, 07:15 PM UTC

♡ 24 likes↻ 0 reposts↳ 1 replies

LangChain

@LangChain

Managed Deep Agents 0.8 makes the Slack experience even better!

Sep 24, 2026, 07:13 PM UTC

♡ 18 likes↻ 0 reposts↳ 2 replies

LangChain

@LangChain

Introducing LangSmith Custom Apps Create any interface from your agent data with a prompt. If you can think it, LangSmith can build it. Now GA. https://t.co/MayBpUbPdu https://t.co/9AODngofKx

Sep 24, 2026, 07:00 PM UTC

♡ 72 likes↻ 8 reposts↳ 10 replies

LlamaIndex 🦙

@llama_index

confidence scores only matter if they help you decide what to automate. for document extraction, that usually means knowing how much work you can safely accept at a given precision target. in our latest post, we look at confidence scoring through that lens, including: ✅️ confidence cutoffs ✅️ precision vs. recall ✅️ score coverage ✅️ score granularity ✅️ human review volume using ExtractBench, we compare how different extraction systems perform after confidence filtering. at a 97% precision target, LlamaParse Agentic Plus reached 66.48% recall on expected fields after filtering. the useful part of a confidence score isn’t the number itself. it’s whether you can use it to control automation and review in production. 👉️ read the full post: https://t.co/U462MW2JOf

Sep 24, 2026, 06:41 PM UTC

♡ 24 likes↻ 6 reposts↳ 7 replies

LangChain

@LangChain

Up next at Interrupt 🎙️ Fireside Chat w/ @OpenRouter CEO & Co-Founder @alexatallah 🎙️ Building Engine: How we approach agent improvement w/ @bentannyhill https://t.co/0u7XviPsOJ

Sep 24, 2026, 06:41 PM UTC

♡ 8 likes↻ 2 reposts↳ 4 replies

LangChain

@LangChain

Interrupt NYC Swag spotlight: ⌨️ A clicky fidget keycap ❄️ LangChain Sweatshirt 🖊️ Pens https://t.co/iEZPrgo5gV

Sep 24, 2026, 06:33 PM UTC

♡ 32 likes↻ 0 reposts↳ 2 replies

LangChain

@LangChain

The LangSmith Engine that could (be won) https://t.co/RENVfRAGO5

Sep 24, 2026, 06:15 PM UTC

♡ 17 likes↻ 0 reposts↳ 0 replies

LangChain

@LangChain

Introducing LangSmith Fine-Tuning and the smithtune CLI. LangSmith now handles the entire fine-tuning process. Use your traces to train specialized models that cut cost and latency. Now in Public Beta. https://t.co/hhH5Tvlm7e

Sep 24, 2026, 06:00 PM UTC

♡ 97 likes↻ 13 reposts↳ 13 replies

LangChain

@LangChain

1️⃣ Identify + export trajectories from LangSmith 2️⃣ Transform traces into SFT-ready training examples 3️⃣ Fine-tune open models w/ @baseten + @fireworks_AI 4️⃣ Evaluate in LangSmith All in one simple workflow. https://t.co/mbDEs4eT6z

Sep 24, 2026, 06:00 PM UTC

♡ 9 likes↻ 1 reposts↳ 1 replies

OpenAI Developers

@OpenAIDevs

GPT-6 Astra helps @harvey turn stacks of documents into structured legal drafts, so lawyers can focus more on strategy. https://t.co/Cm283IUzet

Sep 24, 2026, 05:34 PM UTC

♡ 606 likes↻ 37 reposts↳ 71 replies

LangChain

@LangChain

What is a trajectory? A conversational view of an agent session that pulls together:
 ✅ Human messages
 ✅ AI messages
 ✅ Tool messages
 ✅ System prompts
 …across the main agent + any subagents, then shows them in the order they first appeared.

Sep 24, 2026, 05:28 PM UTC

♡ 48 likes↻ 5 reposts↳ 6 replies

LangChain

@LangChain

After lunch, here’s what’s up next at Interrupt: 🎙️How @airbnb built Agentic AI on LangGraph 🎙️Deploying mission-critical agents to production w/ @VictorMoreira16 🎙️LangSmith for Mental Health AI w/ @SpringHealth https://t.co/ymkqOQrvYk

Sep 24, 2026, 05:12 PM UTC

♡ 21 likes↻ 2 reposts↳ 4 replies

LangChain

@LangChain

Introducing Trajectories in LangSmith. A view of agent behavior that everyone on the team can understand at a glance. https://t.co/8s9kHol2LO https://t.co/8cGrmhVa2F

Sep 24, 2026, 05:05 PM UTC

♡ 133 likes↻ 11 reposts↳ 12 replies

GitHub

@github

Dependabot pull requests are easy to review one at a time ... and tedious to review by the dozen. Build a GitHub Copilot app automation that does the first pass for you. Once it reviews open Dependabot pull requests, groups them by risk, verifies CI status, it'll provide a short summary. You write the instructions in plain language, so you can shape the automation to match how your team works. Schedule it before your workday starts and the results are ready when you log in. Try it out 👇 https://t.co/d83HeLTV7h

Sep 24, 2026, 04:40 PM UTC

♡ 147 likes↻ 16 reposts↳ 46 replies

LangChain

@LangChain

Special guests at the LangChain Demo Station: @nvidia!  Stop by and say hello during lunch! https://t.co/lAhK1gQSXp

Sep 24, 2026, 04:32 PM UTC

♡ 7 likes↻ 0 reposts↳ 2 replies

LangChain

@LangChain

And it’s time for a break! Grab lunch before we kick off the next round of sessions + workshops! https://t.co/P5oPCJ14UM

Sep 24, 2026, 04:26 PM UTC

♡ 12 likes↻ 0 reposts↳ 1 replies