Coding agents were the most common type of agents that respondents used in their daily workflows, led by tools like Claude Code, Cursor, and GitHub Copilot.
@langchain
-
Organizations Still Early in Adoption of Evaluation Methods for LLMs
By
–
Meanwhile, orgs are earlier in their evals usage, with around half of respondents running offline evals on test sets and just over one-third running online evals on production data.
-
Observability Becomes Essential for Production Agent Monitoring
By
–
Observability is now table stakes, with most production teams fully tracing their agents for visibility into their behavior.
-
Quality Over Cost: Agent Reliability Remains Top Priority in 2025
By
–
Quality remains the biggest barrier to production. Making sure agent outputs are reliable is still the hardest part. Factors like cost were cited less frequently as blockers than in previous years, with more orgs focused on making agents work well and fast.
-
Customer Service and Research Drive Over Half of Agent Use Cases
By
–
Customer service and research & data analysis account for over half of agent use cases. Agents are most valuable today where work is repetitive, knowledge-heavy, or customer-facing.
-
Deploying Stateful LangChain Agents Serverlessly on AWS Lambda
By
–
Serverless LangChain Agent Deployment on AWS Made by the LangChain Community Deploy LangChain agents on AWS Lambda using LangGraph's DynamoDB checkpoints for stateful conversations in serverless. By AWS Community Builder Thomas. Watch the tutorial:
-
Production-Ready Voice AI Agents Course with LangChain and Twilio
By
–
Phone Calling Agents Course Made by the LangChain Community Build production-ready voice AI agents for real calls via Twilio. Uses Opik (native LangChain integration), open-source models, multi-week course with live sessions. Check it out: https://
github.com/neural-maze/re
altime-phone-agents-course
… -
PeopleHub: AI-Powered LinkedIn Intelligence Tool by LangChain
By
–
PeopleHub: AI-Powered LinkedIn Intelligence Made by the LangChain Community Open-source LinkedIn intelligence by Meir Kadosh. Uses LangGraph 1.0.1 to orchestrate automated research workflows—profile analysis, parallel scraping, and AI-generated reports. Check it out on
-
LangSmith Agent Builder Overview No-Code Platform
By
–
LangSmith Agent Builder Overview in Chinese Made by the LangChain Community Agent Builder: a no-code platform with "non-workflow" architecture for flexible AI agents. Built into LangSmith with observability, evaluation, and deployment. Full walkthrough in Chinese by
-
Build Deep Agents in LangChain Academy Course
By
–
🌟 Build Deep Agents in our LangChain Academy course 🌟
— LangChain (@LangChain) 28 novembre 2025
Many agents today follow the same simple pattern: run in a loop, call tools. That architecture works well enough, but it breaks down as tasks get more complex.
Today, companies of all sizes – from startups to large… pic.twitter.com/fSzwcKsj1QBuild Deep Agents in our LangChain Academy course Many agents today follow the same simple pattern: run in a loop, call tools. That architecture works well enough, but it breaks down as tasks get more complex. Today, companies of all sizes – from startups to large