Deep Agents, LangChain, and LangGraph each offer distinct approaches to building agents. In this post, we cover the key distinctions between our open source frameworks and when you should reach for each one.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Deep Agents, LangChain, and LangGraph each offer distinct approaches to building agents. In this post, we cover the key distinctions between our open source frameworks and when yo…
Learn how LangChain built an autonomous SRE agent for Kubernetes deployments with Deep Agents, human approval for changes, LangSmith tracing, and evals.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Learn how LangChain built an autonomous SRE agent for Kubernetes deployments with Deep Agents, human approval for changes, LangSmith tracing, and evals.
Learn how to evaluate voice agents across execution, outcomes, and caller experience using LangSmith traces, code evaluators, LLM judges, and human review.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Learn how to evaluate voice agents across execution, outcomes, and caller experience using LangSmith traces, code evaluators, LLM judges, and human review.
LangChain built ReviewBench, a benchmark for evaluating code review agents against real PR feedback from trusted reviewers. The article explains how tasks are curated from real reviews, how the benchmark runs, its scoring metrics, initial results, and future plans.
ReviewBench is built from real PR comments by trusted reviewers in the LangSmith monorepo.
Raw comments are filtered with an LLM gate and manual curation into verifiable eval tasks.
LangSmith LLM Gateway is now in public beta, providing a centralized governance layer between agents and models with runtime controls including cost caps, rate limits, model fallbacks, and sensitive data redaction, helping teams avoid vendor lock-in and manage model usage consistently.
LangSmith LLM Gateway acts as a centralized governance layer for agent-model calls, offering runtime controls.
Supports cost limits, rate limiting, model fallbacks, and sensitive data redaction.
Learn how Similarweb uses LangSmith to evaluate long-form agent research reports with rubrics, faithfulness checks, traces, and baseline comparisons.
Match the evaluation method to the output. Golden answers work for focused questions, while long-form reports need rubrics, faithfulness checks, and baseline comparisons.
Treat scores as signals, not answers. Similarweb used LangSmith to connect each score to evaluator comments, traces, and A/B comparisons.
This month features Jensen Huang and Harrison Chase on open agent systems with the NVIDIA NemoClaw blueprint, LangSmith updates including free Sandboxes trial, Slack integration, and voice tracing, plus open-source releases like OpenWiki Brains and RLMs in Deep Agents. Also: new course, upcoming events, and customer stories from Schneider Electric and Pendo.
Jensen Huang and Harrison release the NVIDIA NemoClaw blueprint for open agent systems.
We revamped how we benchmark Deep Agents. Here's the eval setup we run in Harbor across coding, conversation, and retrieval, and how we use it to ship changes.
End-to-end evals with Harbor using environment, instruction, and evaluation script.
Three benchmarks: Harbor-Index (autonomous), τ³-bench (conversation), ContextBench (retrieval).
This article summarizes three years of experience building agent systems with graphs using LangGraph at LangChain. Graph engineering is not a new concept but a proven approach to building reliable agents. It covers when to use graphs, when to avoid them, and key lessons learned: agent graphs are usually not DAGs, loops are simple graphs, and dynamic transitions matter.
Graph engineering is an approach to represent agent workflows as graphs, balancing determinism and agency.
LangGraph has been used for three years, with 65M+ monthly downloads, adopted by startups and enterprises.
LangSmith now supports tracing for voice agents built with Pipecat, LiveKit, OpenAI Realtime, and Gemini Live. Capture audio, STT and TTS latency, interruptions, tool calls, and more in one trace.
LangSmith launches Python integrations to trace four popular voice agent frameworks.
Voice agents need observability including audio recording, latency analysis, and interruption detection.
Learn how LangChain built IssueBench, a synthetic benchmark for evaluating how well LangSmith Engine identifies, categorizes, and groups issues in agent traces.
IssueBench consists of 15 tasks across SRE log analysis, software engineering, and customer support domains.
Engine must identify issues, assign failure categories, attach to existing issues, and group new failures.
The gateway is the runtime control plane for enterprise AI, turning policy into enforceable decisions across every model call, tool call, and agent hop.
Governance requires a runtime control plane (LLM gateway) to enforce policy across model calls, tool calls, and agent interactions.
Foundations include security, authentication, audit logs, user management, provider secrets, data separation, and data residency.
LangChain has released a hosted version of an open-source extraction service that supports extracting structured data from PDF, HTML, and text files. The service is free to use but not intended for production workloads or sensitive data. It allows users to define extraction schemas, add few-shot examples, and switch between different LLM models. With a simple frontend, developers can quickly experiment and integrate the service into their own LangChain workflows.
LangChain launched a hosted version of an open-source structured data extraction service with a simple frontend.
Supports PDF, HTML, and text files; users can define custom schemas and provide few-shot examples.
The article addresses the challenge of proving ROI for agentic AI in financial services, noting that traditional monitoring fails with multi-agent systems' dynamic costs. Using two real-world use cases—RFP processing automation and AML compliance monitoring—it demonstrates how combining LangChain's observability tools (LangSmith, LangGraph) with Pay-i's economic intelligence platform connects engineering metrics to business value, enabling leadership to see clear returns on AI investments.
Multi-agent AI systems have a dynamic cost structure that traditional FinOps tools cannot handle.
LangSmith provides engineering-level observability; Pay-i links costs to business outcomes.
OpenWiki 0.2 generates codebase wikis in the OKF format, helping developers organize repo docs with metadata, changelogs, and agent-friendly retrieval.
OpenWiki 0.2 adds support for OKF, a proposed standard from Google Cloud for structuring knowledge wikis.
Wiki files now include YAML front matter with fields like title, description, tags, categories, and resource URLs.
Build custom AI agents in Fleet without code, then deploy them to Slack in one click. Give agents custom identities, use them in channels and threads, and keep work moving where your team already collaborates.
Fleet allows building specialized AI agents using natural language, no coding required.
Agents can be deployed to Slack with one click and have their own identity.
To enable AI agents to autonomously execute tasks, they require isolated, secure, and quickly deployable computing environments. This article explains why agents need their own 'computer' and how LangSmith Sandboxes meet this need through microVM isolation, snapshots and forks, an auth proxy, and secure execution. It also discusses security risks like prompt injection and mitigation strategies.
Agents need isolated execution environments to run code, install packages, and access networks, not just to generate text.
LangSmith Sandboxes provide each agent with a hardware-virtualized microVM that boots in under 1 second and automatically cleans up.
OpenWiki Brains turns sources like Gmail, Notion, Git, X, Hacker News, and web search into a local wiki that agents can use as fresh, proactive memory.
OpenWiki Brains turns external sources into a local wiki for agents to use as proactive memory.
Two modes: Personal Brain for general context and Code Brain for code documentation.
Learn how to build a venture capital research agent that produces investment memos in 90 seconds with cited sources, using the Perplexity Agent API, LangGraph, and LangSmith. The agent runs parallel research nodes for team, financials, product, and market, then synthesizes a memo with seven sections, including a thesis and recommendation. Every claim is traced to primary sources, making the output auditable. The article also compares three search providers and offers takeaways for building similar agents.
An agent built with Perplexity Agent API, LangGraph, and LangSmith generates a draft investment memo in ~90 seconds at ~$0.40, with every claim cited.
Four parallel research nodes (team, financials, product, market) gather evidence, then a tool-less synthesizer composes the memo.
LangChain and NVIDIA launch the NemoClaw Deep Agents blueprint, combining Deep Agents Code, Nemotron 3 Ultra, and OpenShell for open, governed enterprise agents.
The blueprint integrates LangChain's Deep Agents framework, NVIDIA's Nemotron 3 Ultra model, and NVIDIA OpenShell runtime.
It achieves a 0.86 score on LangChain's agent eval suite at $4.48 cost, roughly 10x lower than competing models.
By tuning only the harness (scaffolding) around the Nemotron 3 Ultra, we achieved a best run of 0.86 on the Deep Agents suite, nearly matching Opus 4.8's best of 0.87, at roughly 10x lower cost. This article details the eval-driven approach, prompt engineering, middleware optimizations, and what didn't work.
Tuning the harness alone took Nemotron 3 Ultra to a best run of 0.86 on Deep Agents, nearly matching Opus 4.8's 0.87, at about 10x lower cost per run.
Evals are the training data for harness work: every change runs through a trace-driven loop, screened cheaply first, and kept only if wins repeat across trials with no regressions.
Run Deep Agents Code on NVIDIA NemoClaw with deny-by-default networking, human approval, and audit logs for sensitive code modernization.
Deep Agents Code (dcode) runs as a governed blueprint on NemoClaw with the open Nemotron 3 Ultra model, giving you control over source, model, and audit trail.
Deny-by-default networking, human approval, and full audit logs provide the controls a regulated team needs.