ICYMI: @LangChain Deep Agents on @nvidia Nemotron 3 Ultra. frontier open-model agents at ~10x lower cost than closed. Run on Fireworks, then post-train it into specialized intelligence you own.

One week to Privy Home: IRL in SF 🌉 What to expect: ✔️ Workshops from @awscloud + @stripe Projects ✔️ Lightning talks from @LangChain @Alchemy @mpp, and other agentic builders ✔️ Great food, great coffee, better conversations Sip & ship with us ⤵️

All Paid Courses (Free for First 4000 People) 🎯 LLM Mastery (GPT, Claude, Grok) 🎯 AI Agent Building Masterclass 🎯 Advanced Prompt Engineering 🎯 AI Automation with Zapier & Make 🎯 No-Code AI SaaS Building 🎯 RAG Systems & Vector Databases 🎯 LangChain & Agent Frameworks 🎯 AI Content Monetization 🎯 AI for Freelancers 🎯 Chatbot Development 🎯 AI App Development 🎯 Generative AI for Business 🎯 AI Workflow Systems 🎯 And more... FREE for 48hrs only To get Simply: 1) Follow me [ MUST! ] for DM access 2) Like & RETWEET 3) Comment "AI " to grab your copies

Three-person data team, a queue of weekly requests, and every analytical question outside predefined dashboards stuck in someone's inbox — that was LangChain's BI era. 🔍 The team decided to change. What they needed was a platform unifying dashboards, notebooks, and conversational interfaces with native AI agent capabilities. They chose Hex and designed a five-layer context architecture: dbt data model definitions, a semantic layer, workspace guides, endorsements as trust signals, and GitHub integration. The migration was complete in six weeks with 100% company adoption. The transformation's core wasn't technical — it was about explicitness. Rewriting a weak definition like "account_status: The status of the account" into a full description covering lifecycle states, default filters, and reporting conventions alone changed how reliably the agent answered questions. Key metrics — ARR, pipeline, customer health — were given single authoritative definitions in the semantic layer. Endorsements pointed agents to canonical sources wherever multiple assets addressed the same concept, preventing confusion before it could happen. Today, every function — marketing, product, sales, customer engineering — runs its own analysis without routing through the data team. Monthly agent conversations total roughly 2,200, processing 40x the volume the three-person team could handle manually. The team's role has shifted from "answer every question" to "design the system that lets others answer questions." LangChain's detailed account of this journey, "How LangChain Built an Agent-First Data Stack," makes the case — in concrete numbers and design principles — for what a data team looks like in the agent era. #DataStack# #AIAgent#

Get skilled and certified for free! We just launched a new course to help you build practical agentic AI skills or validate the ones you already have. It covers: ✅ Core AI agent concepts and reasoning ✅ LangChain and the OpenAI Agent stack ✅ Model Context Protocol (MCP) ✅ OCI Enterprise AI Platform ✅ Oracle AI Database for agentic AI

Coding agents fire dozens of API calls per task, so a single developer can quietly burn thousands of dollars a week before anyone notices — here's how LangChain killed that "spend unpredictability" internally 💸 The key was folding budget control into the same place as observability. Title: How LangChain Made Coding Agent Spend Predictable URL: 💸 Overview An LLM Gateway built into LangSmith gives a company-wide, minute-level view of model spend and manages budgets centrally. Rather than a bolt-on proxy, it sits on the same foundation as existing tracing, evaluation, and user management. ❓ Challenges Solved Model usage spread from a few teams to the whole company, and premium model prices rose, so costs spiked. ・Coding agents trigger dozens of API calls per task ・Individual developers ran up thousands of dollars a week, unnoticed until month-end 💡 Methodology & Proposed Approach Budgets can be set across multiple layers. ・Caps at the organization, workspace, user, and API-key level ・Default monthly, weekly, daily, and hourly windows for all employees, with exceptions for heavy projects ・Covers agents accessed via Claude Code, Codex, and LangChain Deep Agents ・Deployed via MDM so no one has to set it up manually ・Runs are traced and tied to a user and API key; overspend can be diagnosed by inspecting the trace with evaluation data 🌍 Use Cases Engineering leaders can set team-level limits while still letting people use agents without fear of a surprise bill. The practical value is replacing the month-end billing shock with real-time monitoring. 📊 Lessons & Outcomes ・Static price tables go stale fast, so pricing must be handled dynamically, including caching and tier differences ・Cursor and Claude Desktop didn't route cleanly, so they measured the delta between Gateway-captured traffic and provider settings to correct for it ・Hard limits alone block real work, so they evolved into early-warning alerts and auditable budget-increase requests ・Since internal rollout, LLM costs have stayed within budget #CodingAgents# #LLMOps#

Judging billions of trace tokens a day with a frontier LLM was financially untenable 💸 Here's how fine-tuning a small open model matched the accuracy at 10-100x lower cost. Title: Building a 100x Cheaper Trace Judge with Fireworks URL: 💸 Overview LangChain Labs partnered with Fireworks to build a "Perceived Error" detector for agent traces. It detects cases where users felt the assistant made a mistake or needed correction — using a small open model. ❓ Challenges Solved LangSmith processes billions of tokens daily across production traces. ・Evaluating them with frontier LLMs is prohibitively expensive at scale ・The question: how to cost-effectively mine important signals from every trace while maintaining frontier performance? 💡 Methodology & Proposed Approach ・Supervised fine-tuning (SFT) with LoRA on the open-source Qwen-3.5-35B, on Fireworks infrastructure ・Training data from two production datasets: chat-langchain (technical Q&A, 707 examples) and Fleet (no-code agent, 727 examples) ・It learns "Perceived Error," doing the judging without relying on huge frontier models 📊 Experimental Results ・Accuracy: the fine-tuned Qwen matched or exceeded frontier models (96.1% on chat-langchain, 90.8% cross-domain on Fleet) ・Cost: 10-100x cheaper than frontier models depending on trace volume ・Transferability: the model trained on chat-langchain beat all frontier models on Fleet without retraining #LLMEvaluation# #FineTuning#

The EU AI Act deadline is August 2, 2026, with penalties up to €15M. Here's a practical guide mapping abstract articles to concrete features ⚖️ Title: How LangSmith and LangChain OSS Help You Meet EU AI Act Requirements URL: ⚖️ Overview This post explains how to meet the EU AI Act's requirements for high-risk systems using LangSmith and LangChain OSS features, mapping the articles to implementations like tracing, evaluation, and human oversight. ❓ Challenges Solved The EU AI Act imposes strict requirements on high-risk AI. The deadline is August 2, 2026, with penalties up to €15M or 3% of global revenue. The hard part is knowing which capabilities actually satisfy the abstract articles. 💡 How It Works (articles → features) ・Observability and tracing (Article 12): end-to-end traces of LLM calls, tools, and reasoning steps; retention of 14 days (base) / 400 days (extended); EU data residency options ・Quality and safety (Article 15): online evaluators continuously score production traffic, with prebuilt evaluators for toxicity, hallucination, PII leakage, prompt injection, and more ・Human oversight (Article 14): LangGraph's interrupt for human-in-the-loop, with resume-from-exact-point recovery ・Risk management (Article 9): custom dashboards track risk scores and trigger alerts 🌍 Practical Starting Point Build in this order — tracing → production evaluations → human-in-the-loop — and choose EU, self-hosted, or BYOC deployment based on data residency needs. #EUAIAct# #AIGovernance#