LangChain(@LangChainAI)

ICYMI: @hwchase17 joined @twentyminutevc with @HarryStebbings to discuss how better models change wh...

LangChain (@LangChain) — Mon, 19 Oct 2026 19:22:36 GMT

ICYMI: @hwchase17 joined @twentyminutevc with @HarryStebbings to discuss how better models change what you build, where the value in the agent stack ends up, and more.

Watch on YouTube: youtube.com/watch?v=1jDCPE…

Harry Stebbings@HarryStebbings

What percent of developer salary do you spend on coding tools and how has it changed?

“We spend probably roughly 30% of our engineering salary on coding tools. It has actually gone down the last two months, while the number of tokens that we have used has gone up.

First is visibility, second is basic cost controls, and third is we control the harness.

In that harness, we have done a bunch of work to control costs, things like prompt caching and routing.” @hwchase17 

Love to hear your thoughts @bcherny@amasad@HamelHusain@simonw

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄2❤️10👀3668📊2

⚡ Powered by xgo.ing

💡 Excellent recap of @hwchase17 + @HarryStebbings' conversation on @twentyminutevc ⤵️

LangChain (@LangChain) — Mon, 19 Oct 2026 19:21:19 GMT

💡 Excellent recap of @hwchase17 + @HarryStebbings' conversation on @twentyminutevc ⤵️

Sydney Runkle@sydneyrunkle

"it's underrated how hard it is to build agents!"

great convo w/ @hwchase17 and @HarryStebbings on @twentyminutevc

an agent = model + context + harness, and you can improve an agent by tweaking any of the three. a few takeaways:

1. the highest roi thing you can do is start by optimizing context (then the harness, then the weights); this is where domain knowledge lives and that's incredibly valuable

2. the story of continual learning is: run an agent, collect traces, aggregate learnings, fix something, measure the fix, loop! the fix can land in any of the three layers. those fixes all look different but the cycle is the same.

3. memory is still massively unsolved, but also massively important. the hardest part is distilling learnings from traces which is incredibly domain specific.

4. when you build agents, you're probably worried about a few things: accuracy, cost, latency, and security. we've seen these themes confirmed year after year in our dev surveys

5. when we think about reducing cost, the pipeline looks like adding visibility into spend, putting controls in place, and only then pushing on agent optimizations. this is how we reduced our coding agent spend @LangChain 

6. model routing, which is great for cost controls, is most effective in the harness (where the context needed for a routing decision lives)

7. open models are used for more narrow tasks right now (small parts of the agent loop OR for very specific domains w/ post-training), but as they improve they'll power more core agent loops

8. we're looking at a future with both horizontal agents and vertical agents. horizontal agents will use the vertical agents, and infra needs to change to support this load (agents can do background work at a rate that humans cannot).

youtube.com/watch?v=1jDCPE…

🔗 View Quoted Tweet

💬0🔄0❤️5👀2681📊1

⚡ Powered by xgo.ing

Agent evals run through the same graph. Every eval, from single-reply fixtures to simulated multi-t...

LangChain (@LangChain) — Mon, 19 Oct 2026 19:01:09 GMT

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.

💬1🔄1❤️0👀1015📊1

⚡ Powered by xgo.ing

Everything is measured in LangSmith. 1️⃣ All conversations land as a trace, are annotated by review...

LangChain (@LangChain) — Mon, 19 Oct 2026 19:01:09 GMT

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.

💬0🔄1❤️0👀960

⚡ Powered by xgo.ing

Nu by @getnuman is an AI health coach in regulated healthcare, built on LangGraph + LangSmith. Here...

LangChain (@LangChain) — Mon, 19 Oct 2026 19:01:08 GMT

Nu by @getnuman is an AI health coach in regulated healthcare, built on LangGraph + LangSmith.

Here's how their team ships fast without crossing the medical device line 🧵langchain.com/blog/how-numan…9

💬6🔄1❤️5👀3239📊7

⚡ Powered by xgo.ing

🏢 Come to our HQ in SF 🤝 Meet our team 🚀 Kickstart your sales career at LangChain Don’t miss o...

LangChain (@LangChain) — Mon, 19 Oct 2026 17:04:11 GMT

🏢 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.

🎟️ RSluma.com/ubhnxwnuMvif

💬1🔄0❤️10👀3466📊2

⚡ Powered by xgo.ing

Join our EMEA Deep Life Sci Workshop: Agent Engineering for Life Sciences for a hands-on look at how...

LangChain (@LangChain) — Mon, 19 Oct 2026 15:04:03 GMT

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:events.langchain.com/register/emea-…o

💬1🔄0❤️8👀4119📊2

⚡ Powered by xgo.ing

✅ Everything we shipped at Interrupt NYC and London ✅ Open source updates ✅ Upcoming events & li...

LangChain (@LangChain) — Mon, 19 Oct 2026 13:03:12 GMT

✅ Everything we shipped at Interrupt NYC and London
✅ Open source updates
✅ Upcoming events & livestreams

Catch up on everything LangChain in our latest newsletter.

https://t.co/VulhXu1Cel

💬4🔄3❤️17👀5235📊6

⚡ Powered by xgo.ing

At our recent Learning Loop event, @oneill_c from @baseten explained why continual learning keeps br...

LangChain (@LangChain) — Fri, 16 Oct 2026 19:00:00 GMT

At our recent Learning Loop event, @oneill_c from @baseten explained why continual learning keeps breaking, and what to try.

Watch the full session ⤵️

Your browser does not support the video tag.

🔗 View on Twitter

💬3🔄2❤️44👀10762📊13

⚡ Powered by xgo.ing

Agents with sandboxes run packages you didn't write. If one is malicious, any credential in the sand...

LangChain (@LangChain) — Fri, 16 Oct 2026 17:27:17 GMT

Agents with sandboxes run packages you didn't write. If one is malicious, any credential in the sandbox is exposed.

With Managed Deep Agents, the proxy adds your token outside the sandbox, only on calls to services you've allowed. The agent never sees it.

Caspar@caspar_br

A walkthrough of how Managed Deep Agents uses sandbox proxies to keep your credentials safe. langch.in/mda

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬15🔄6❤️58👀9726📊19

⚡ Powered by xgo.ing

🧵 Behind the scenes of AI Search in LangSmith: TL;DR 1️⃣ SmithDB turns traces into readable traje...

LangChain (@LangChain) — Fri, 16 Oct 2026 17:00:00 GMT

🧵 Behind the scenes of AI Search in LangSmith:

TL;DR

1️⃣ SmithDB turns traces into readable trajectories. Structured filters narrow the candidates when you search

2️⃣ A model checks each remaining trajectory against your description and streams back matches

Your browser does not support the video tag.

🔗 View on Twitter

💬15🔄3❤️54👀9412📊21

⚡ Powered by xgo.ing

When you search, structured filters like a time range narrow the candidates first. Then a small, fa...

LangChain (@LangChain) — Fri, 16 Oct 2026 17:00:00 GMT

When you search, structured filters like a time range narrow the candidates first.

Then a small, fast model checks each remaining trajectory against your description, with many checks running in parallel.

Each one usually takes under half second.

Matches stream back as they’re found, so you don’t wait for the full scan.

💬1🔄1❤️3👀1577📊2

⚡ Powered by xgo.ing

AI Search reads each trajectory within a fixed token budget. Most questions about behavior only nee...

LangChain (@LangChain) — Fri, 16 Oct 2026 17:00:00 GMT

AI Search reads each trajectory within a fixed token budget.

Most questions about behavior only need a small slice, and we checked that on 150 conversations from Open SWE, the coding agent our team uses every day.

✅ The median ran 84K tokens
✅ About 1.5K of that was the user’s messages and the agent’s final reply
✅ Roughly 3/4 was tool output: file reads, shell commands, test logs 

langchain.com/blog/agent-tra…

💬0🔄1❤️3👀1304📊1

⚡ Powered by xgo.ing

What does it take to move healthcare and life sciences agents from experimentation into trusted prod...

LangChain (@LangChain) — Fri, 16 Oct 2026 13:32:42 GMT

What does it take to move healthcare and life sciences agents from experimentation into trusted production systems?

Explore the architectures, evaluation practices, and production patterns teams are using as agents take on more complex work: 

➡️ info.langchain.com/guide/scaling-…

💬8🔄5❤️42👀6412📊14

⚡ Powered by xgo.ing

LangSmith for Startups spotlight: @tryopine The customer intelligence layer for revenue teams Opine...

LangChain (@LangChain) — Thu, 15 Oct 2026 20:49:49 GMT

LangSmith for Startups spotlight: @tryopine
The customer intelligence layer for revenue teams

Opine traces every production LLM run through LangSmith, and gates every prompt and model change behind LangSmith evals.

See what Opine looks like on your hardest open deal at tryopine.com. 

And if you'd rather help build the context customer intelligence layer than buy it, they’re hiring across GTM and engineering!

Your browser does not support the video tag.

🔗 View on Twitter

💬6🔄4❤️24👀7740📊9

⚡ Powered by xgo.ing

Our education team answered the most common questions we've received over the years about agent eval...

LangChain (@LangChain) — Thu, 15 Oct 2026 19:02:42 GMT

Our education team answered the most common questions we've received over the years about agent evals. 

Check it out ⤵️

Divya Santhanam@divyasan0

Agent evals come with a lot of questions, and our team hears the same ones over and over. So I wrote down the most common ones and answered them here ⬇️

langchain.com/blog/common-qu…

🔗 View Quoted Tweet

💬11🔄3❤️39👀10869📊14

⚡ Powered by xgo.ing

"I can finally find the data that I want without having to fight my tooling." LangSmith helps @Trus...

LangChain (@LangChain) — Thu, 15 Oct 2026 17:02:19 GMT

"I can finally find the data that I want without having to fight my tooling."

LangSmith helps @TrustVanta find traces fast, align evaluators to labeled examples, and improve AI quality end to end.

⏯️ Zheng Tao on why "LangSmith gets it."

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄6❤️22👀8622📊5

⚡ Powered by xgo.ing

Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVID...

LangChain (@LangChain) — Thu, 15 Oct 2026 15:17:36 GMT

Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVIDIA.

Open weights. 120B parameters, 12B active.

Nemotron 3.5 Super VL averaged an 87% pass rate on our Deep Agents behavioral suite.

Speed stood out, too. On our Harbor-lite benchmark: 55% less total task time than DeepSeek V4.1 Flash, with similar success.

docs.langchain.com/oss/python/int…

💬11🔄6❤️45👀7284📊16

⚡ Powered by xgo.ing

How do agents remember? The longer an agent runs, the more it takes in (instructions, tool results,...

LangChain (@LangChain) — Wed, 14 Oct 2026 19:16:31 GMT

How do agents remember?

The longer an agent runs, the more it takes in (instructions, tool results, files, and drafts), which results in decreased accuracy and reasoning.

Read how LangChain's Deep Agents harness addresses this by moving context out of the active window without deleting it ⤵️

Jess Weng@jess_weng18

New blog dropped 👀
langchain.com/blog/context-e…p

🔗 View Quoted Tweet

💬25🔄18❤️102👀13951📊38

⚡ Powered by xgo.ing

Claude Platform traces can now be sent to LangSmith through OpenTelemetry. Export from Claude Manag...

LangChain (@LangChain) — Wed, 14 Oct 2026 17:38:19 GMT

Claude Platform traces can now be sent to LangSmith through OpenTelemetry.

Export from Claude Managed Agents, the Messages API, or the Claude SDKs with native OTel support. Traces show up in LangSmith so you can inspect every step and improve agent performance.

It’s available now in public beta.

Docs: docs.langchain.com/langsmith/trac…

ClaudeDevs@ClaudeDevs

Now in public beta, Claude Platform can send OpenTelemetry traces from the Messages API, Claude Managed Agents, and the Claude SDKs to your observability stack.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬12🔄8❤️66👀9123📊17

⚡ Powered by xgo.ing

How @OrangeBusiness evaluate agents in their enterprise AI platform: ✅ RAG quality: golden datasets...

LangChain (@LangChain) — Wed, 14 Oct 2026 13:01:40 GMT

How @OrangeBusiness evaluate agents in their enterprise AI platform:

✅ RAG quality: golden datasets, retrieval recall, answer faithfulness
✅ Agent behavior: tool selection accuracy, prompt injection robustness
✅ Production traces: latency, cost, failed runs, human feedback

All in LangSmith, with regression evals before changes reach production, and LangChain for model neutrality & portability

langchain.com/blog/how-orang…?

💬23🔄2❤️39👀7894📊26

⚡ Powered by xgo.ing

ICYMI: AI Search in LangSmith!

LangChain (@LangChain) — Tue, 13 Oct 2026 19:36:00 GMT

ICYMI: AI Search in LangSmith!

LangChain@LangChain

🔎 Announced at Interrupt: AI Search in LangSmith

You used to need an evaluator or read hours of conversations to find traces that answer questions such as:

💬 Does the user seemed frustrated?"

💬 Where did the agent fail to complete the task?

💬 Where is the user trying to cancel their subscription?

Now, just describe it. LangSmith returns the traces where it happenlangchain.com/blog/agent-tra…uCT9

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬3🔄1❤️26👀8900📊5

⚡ Powered by xgo.ing

And that's a wrap on Interrupt London!

LangChain (@LangChain) — Tue, 13 Oct 2026 18:35:52 GMT

And that's a wrap on Interrupt London!

💬1🔄0❤️15👀8807📊2

⚡ Powered by xgo.ing

The sessions may have ended, but the attendee reception sponsored by @focused_dot_io has just begun....

LangChain (@LangChain) — Tue, 13 Oct 2026 16:45:49 GMT

The sessions may have ended, but the attendee reception sponsored by @focused_dot_io has just begun. 🥂

💬1🔄1❤️14👀5502📊2

⚡ Powered by xgo.ing

Final sessions of Interrupt: 🎙️@hwchase17 Fireside Chat with @DunBradstreet SVP, AI Solutions &am...

LangChain (@LangChain) — Tue, 13 Oct 2026 15:25:56 GMT

Final sessions of Interrupt: 

🎙️@hwchase17 Fireside Chat with @DunBradstreet SVP, AI Solutions & Data Science Ilya Meyzin

🎙️ Crossing the Production Bottleneck of Agentic Projects with Igor Nikolaienko, Gen AI Architect at @DeutschePostDHL

💬3🔄3❤️18👀4940📊5

⚡ Powered by xgo.ing

🔎 Announced at Interrupt: AI Search in LangSmith You used to need an evaluator or read hours of co...

LangChain (@LangChain) — Tue, 13 Oct 2026 14:56:00 GMT

🔎 Announced at Interrupt: AI Search in LangSmith

You used to need an evaluator or read hours of conversations to find traces that answer questions such as:

💬 Does the user seemed frustrated?"

💬 Where did the agent fail to complete the task?

💬 Where is the user trying to cancel their subscription?

Now, just describe it. LangSmith returns the traces where it happenlangchain.com/blog/agent-tra…uCT9

Your browser does not support the video tag.

🔗 View on Twitter

💬20🔄12❤️75👀27087📊34

⚡ Powered by xgo.ing

Train your agent, win a train! 🚂 Stop by the LangChain Agent Arena sponsored by @nvidia to win a L...

LangChain (@LangChain) — Tue, 13 Oct 2026 14:14:39 GMT

Train your agent, win a train! 🚂

Stop by the LangChain Agent Arena sponsored by @nvidia to win a LangSmith Engine.

💬3🔄1❤️14👀5466📊4

⚡ Powered by xgo.ing

Next up 🎙️@dorco8 at @mondaydotcom on building online & offline LLM Eval Pipelines with LangSm...

LangChain (@LangChain) — Tue, 13 Oct 2026 14:01:12 GMT

Next up

🎙️@dorco8 at @mondaydotcom on building online & offline LLM Eval Pipelines with LangSmith Traces

🎙️@hwchase17 on building agents that improve over time

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄2❤️25👀7325📊5

⚡ Powered by xgo.ing

🕹️At Interrupt? Swing by the LangChain Agent Arena sponsored by @nvidia 1️⃣ Train an agent by play...

LangChain (@LangChain) — Tue, 13 Oct 2026 12:54:42 GMT

🕹️At Interrupt? Swing by the LangChain Agent Arena sponsored by @nvidia

1️⃣ Train an agent by playing Tetris 
2️⃣ Choose a model w/ LangSmith LLM Gateway
3️⃣ Watch it compete

🏆 See the results on the leaderboard

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄1❤️19👀6244📊4

⚡ Powered by xgo.ing

PSA: We have Interrupt swag 👀

LangChain (@LangChain) — Tue, 13 Oct 2026 12:29:17 GMT

PSA: We have Interrupt swag 👀

💬4🔄1❤️29👀6507📊6

⚡ Powered by xgo.ing

After lunch: 🎙️How @OVOenergy builds secure customer support agents 🎙️@BenTannyhill on how we bu...

LangChain (@LangChain) — Tue, 13 Oct 2026 12:27:39 GMT

After lunch:

🎙️How @OVOenergy builds secure customer support agents

🎙️@BenTannyhill on how we built LangSmith Engine

🎙️How @jimdo built an AI companion for small biz with LangSmith

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄2❤️14👀5216📊3

⚡ Powered by xgo.ing

Excited to partner with @scaledown_team 🤝 Their constrained decision models now plug into your age...

LangChain (@LangChain) — Tue, 13 Oct 2026 12:17:58 GMT

Excited to partner with @scaledown_team 🤝

Their constrained decision models now plug into your agents via:

✅ langchain-scaledown, an OSS package with prebuilt scaledown middlewares

✅ Support in the LangSmith LLM Gateway, with tracing, spend limits, and rate limits

Neal Patel@neal_k_patel

You already gave the LLM the answer. So why is it writing it out from scratch?

Introducing a new AI model architecture: Constrained Decoding Models (CDMs)

LLMs were built to write. Most production workloads just need an answer: fast, consistent, and affordable.

CDMs are purpose-built for 1 task each. They read your input once and skip the token-by-token generative loop that makes LLMs slow and expensive.

Not just a decision model, but a family of 3 CDMs live today:

• Classify: define your labels and get back a calibrated probability + reason for each. Used for routing, tagging, and intent detection.
 • Extract: describe the entities in natural language and get back well-formed JSON with confidence scores + citations. Used for web scraping, document processing, and PII redaction.
 • Summarize: pass in long text, images, or PDFs and get back a consistent summary under 1,000 tokens. Used for context compaction, metadata generation, and transcript digests.

Built for production:

• 1M tokens of multimodal (text + image) input, 31x larger than Jev
 • 77.2% on DecisionBench vs Jev's 72%
 • 200x faster, 467x cheaper than frontier LLM APIs
 • $0.05/M input tokens. Output is free (yes, even for summarize)

Live on your favorite platforms today:
 @OpenRouter@vercel_dev@LiteLLM@LangChain@TrustedRouter@itsArthurAI@useRouterPlus

Get 50M input tokens for free (for the first 50 hours) at link below 👀

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬6🔄6❤️38👀6749📊9

⚡ Powered by xgo.ing

New in LangChain: Support for @scaledown_team's constrained decision models, which are optimized for...

LangChain (@LangChain) — Tue, 13 Oct 2026 12:09:24 GMT

New in LangChain: Support for @scaledown_team's constrained decision models, which are optimized for quick, cost-effective decisions:

✅ Compatible with LangChain + Deep Agents
✅ Trace every call with LangSmith LLM Gateway

Start summarizing, extracting, and classifying today.

Sydney Runkle@sydneyrunkle

we're excited to partner with @scaledown_team to offer support for their new constrained decision models (CDMs) in @LangChain!

these cheap+fast models are tailored to specific critical tasks in the agent loop, like summarization, extraction, and classification.

🔗 View Quoted Tweet

💬6🔄1❤️21👀8082📊6

⚡ Powered by xgo.ing

Up next at Interrupt: 🎙️ @GregorBeuster on building visual agents at DB Engineer & Consulting ...

LangChain (@LangChain) — Tue, 13 Oct 2026 10:42:52 GMT

Up next at Interrupt:

🎙️ @GregorBeuster on building visual agents at DB Engineer & Consulting with Deep Agents

🎙️@VictorMoreira16 on what it takes to deploy mission-critical agents to production

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄1❤️12👀5023📊3

⚡ Powered by xgo.ing

LangChain Academy is almost in session!

LangChain (@LangChain) — Tue, 13 Oct 2026 10:40:39 GMT

LangChain Academy is almost in session!

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄1❤️11👀8083📊2

⚡ Powered by xgo.ing

In between sessions? Don’t forget to say hello to our sponsors during the show! @FactoryAI @p0 @C...

LangChain (@LangChain) — Tue, 13 Oct 2026 10:27:47 GMT

In between sessions?

Don’t forget to say hello to our sponsors during the show!

@FactoryAI@p0@CopilotKit@tavilyai@focused_dot_io

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄1❤️24👀6296📊7

⚡ Powered by xgo.ing

🔴 @hwchase17’s opening keynote starts NOW! Join the livestream: https://t.co/RZxuocQV6f

LangChain (@LangChain) — Tue, 13 Oct 2026 09:35:29 GMT

🔴 @hwchase17’s opening keynote starts NOW! 

Join the livestream:interrupt.langchain.com/london/ldn-liv…f

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄0❤️9👀3541📊2

⚡ Powered by xgo.ing

Not at Interrupt? We’re livestreaming @hwchase17’s keynote at 10:30am BST. 🔴 https://t.co/RZxuoc...

LangChain (@LangChain) — Tue, 13 Oct 2026 09:13:03 GMT

Not at Interrupt? 

We’re livestreaming @hwchase17’s keynote at 10:30am BST.

🔴interrupt.langchain.com/london/ldn-liv…H

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄4❤️8👀3840📊3

⚡ Powered by xgo.ing

Starting at 10:30! First sessions of Interrupt: 🎙️@hwchase17 opening keynote 🎙️Fireside Chat w/...

LangChain (@LangChain) — Tue, 13 Oct 2026 09:07:40 GMT

Starting at 10:30!

First sessions of Interrupt:

🎙️@hwchase17 opening keynote

🎙️Fireside Chat w/ Harrison Chase + @orange Group Chief AI Officer Usman Javaid

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄1❤️11👀3391📊5

⚡ Powered by xgo.ing

Fuel up for Interrupt!

LangChain (@LangChain) — Tue, 13 Oct 2026 08:52:27 GMT

Fuel up for Interrupt!

💬1🔄0❤️8👀3632📊2

⚡ Powered by xgo.ing

The doors are open! 🪪 Grab your badge ☕️ Have a bite 🎉 Get ready for an amazing day Sessions star...

LangChain (@LangChain) — Tue, 13 Oct 2026 08:42:26 GMT

The doors are open!
🪪 Grab your badge
☕️ Have a bite
🎉 Get ready for an amazing day

Sessions start at 10:30!

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄1❤️13👀3867📊3

⚡ Powered by xgo.ing

POV: You’re arriving at Interrupt London

LangChain (@LangChain) — Tue, 13 Oct 2026 08:27:01 GMT

POV: You’re arriving at Interrupt London

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄0❤️8👀3895📊2

⚡ Powered by xgo.ing

LangChain has arrived in London!

LangChain (@LangChain) — Tue, 13 Oct 2026 07:51:15 GMT

LangChain has arrived in London!

💬1🔄0❤️11👀3520📊2

⚡ Powered by xgo.ing

LangSmith LLM Gateway now supports the OpenAI Decisions API. Your agents get low latency inference, ...

LangChain (@LangChain) — Fri, 09 Oct 2026 20:28:46 GMT

LangSmith LLM Gateway now supports the OpenAI Decisions API. Your agents get low latency inference, and LLM Gateway gives you a centralized place to control them with model fallbacks, data redaction policies, and spend limits.

Read more to get started → docs.langchain.com/langsmith/llm-…

💬8🔄1❤️23👀2971📊11

⚡ Powered by xgo.ing

The 3 questions every agent builder should be able to answer: ✅ Where the agent fails ✅ How to repr...

LangChain (@LangChain) — Fri, 09 Oct 2026 19:00:00 GMT

The 3 questions every agent builder should be able to answer:

✅ Where the agent fails
✅ How to reproduce it
✅ How to make it stop

Watch @JakeBroekhuizen’s session: youtu.be/oVKGKdIAgtg

Your browser does not support the video tag.

🔗 View on Twitter

💬30🔄8❤️51👀9856📊35

⚡ Powered by xgo.ing

New in Managed Deep Agents 0.9: Reactions API for @SlackHQ Channels. When it comes to building effe...

LangChain (@LangChain) — Fri, 09 Oct 2026 17:03:58 GMT

New in Managed Deep Agents 0.9: Reactions API for @SlackHQ Channels.

When it comes to building effective user agent experiences, loading states are underrated.

Now, you can build loading states and receipts using either heuristics, decision models, or custom logic.

nathan drezner@ndrezn

We've been thinking a lot about great agent UX with Managed Deep Agents - here's some of what we've been building in this area and a bit about our product philosophy x.com/i/article/2108…

🔗 View Quoted Tweet

💬21🔄4❤️47👀9794📊21

⚡ Powered by xgo.ing

Experience the best of Interrupt. Access our archive and watch every session on-demand: https://t....

LangChain (@LangChain) — Fri, 09 Oct 2026 16:03:46 GMT

Experience the best of Interrupt. 

Access our archive and watch every session on-demand: interrupt.langchain.com/recordings

LangChain@LangChain

We simplified agent authentication, memory, and channels, and brought in web search as a pre-built tool for Managed Deep Agents.

Watch @VictorMoreira16’s full Interrupt NYC session for an inside look: youtu.be/XcsspzECTKA

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄6❤️37👀8782📊6

⚡ Powered by xgo.ing

We simplified agent authentication, memory, and channels, and brought in web search as a pre-built t...

LangChain (@LangChain) — Fri, 09 Oct 2026 16:02:32 GMT

We simplified agent authentication, memory, and channels, and brought in web search as a pre-built tool for Managed Deep Agents.

Watch @VictorMoreira16’s full Interrupt NYC session for an inside look: youtu.be/XcsspzECTKA

Your browser does not support the video tag.

🔗 View on Twitter

💬7🔄7❤️59👀12572📊17

⚡ Powered by xgo.ing

LangSmith Signals from the last month: ✅ Claude Sonnet 5: #9 to #2 in model adoption. 51% more orgs...

LangChain (@LangChain) — Fri, 09 Oct 2026 15:02:29 GMT

LangSmith Signals from the last month:

✅ Claude Sonnet 5: #9 to #2 in model adoption. 51% more orgs using it

✅ gpt 5.6 luna: #3 to #1 in call footprints. 65% more calls

✅ Two open-weights models are now in the adoption top 10, but not for call volume

✅ Smaller, faster models dominate call footprints

💬16🔄7❤️33👀9260📊19

⚡ Powered by xgo.ing

✅ 60k queries handled ✅ 500+ customer accounts ✅ 85%+ of sessions resolved without a support ticket ...

LangChain (@LangChain) — Fri, 09 Oct 2026 13:04:28 GMT

✅ 60k queries handled
✅ 500+ customer accounts
✅ 85%+ of sessions resolved without a support ticket
✅ 250+ cases auto-detected + escalated to the right team

@SnykSec Assist. Built on LangChain + LangGraph. Observability in LangSmith. 

Full story: langchain.com/blog/how-snyk-…

💬8🔄12❤️100👀9303📊29