You are a world-class sales development representative.
Write an outreach email based on the prospect information and provided content that could be of interest to the prospect.
The prospects come from the following sources:
(1) signups for LangGraph course. LangGraph is an open-source framework for building agent applications
(2) signups for LangSmith course. LangSmith is a platform for observability and evaluations for LLM applications
(3) general signups for LangChain academy (no course selected)
⟨'employee_info': {{'name': 'Usama', 'email': 'usama.masood@att.com', 'title': 'Principal Member of Technical Staff', 'last_name': 'Masood'⟩, 'company_info': ⟨'name': 'AT&T', 'description': "AT&T Inc. is a leading telecommunications, media, and technology services provider. The company offers wireless communications, data/broadband and internet services, local and long-distance telephone services, telecommunications equipment, managed networking, and wholesale services. AT&T operates the largest wireless network in North America and provides 5G and fiber internet services. They also operate FirstNet, America's first and only purpose-built public safety network. The company's fiber internet service passes more than 27.8 million total consumer and business locations, offering symmetrical upload and download speeds. AT&T is focused on connecting people to greater possibilities through expertise, simplicity, and inspiration.", 'employee_count': 149900, 'headquarters_location': 'Dallas, TX'⟩, 'source': None}}
[⟨'title': 'MCP Adapters for LangChain and LangGraph', 'content': 'The LangChain MCP Adapters is a Python package that makes it easy to use Anthropic Model Context Protocol (MCP) tools with LangChain & LangGraph. It:Converts MCP tools into LangChain- & LangGraph-compatible toolsEnables interaction with tools across multiple MCP serversSeamlessly integrates the hundreds of tool servers already published into LangGraph AgentsWhy use MCP Adapters:This adapter makes it simple to connect LangChain and LangGraph with the growing ecosystem of MCP tool servers. Instead of manually adapting each tool, you can now integrate them seamlessly. It also allows agents to pull from multiple MCP servers at once, making it easier to combine different tools for more powerful applications.MCP is gaining serious traction, and this adapter helps LangGraph agents take full advantage. Check it out: GitHub', 'link': 'https://changelog.langchain.com/announcements/mcp-adapters-for-langchain-and-langgraph?utm_source=LaunchNotes&utm_medium=rss', 'publication_date': 'Thu, 27 Feb 2025 07:28:51 +0000'⟩, ⟨'title': 'New ingest-backend service for faster LangSmith performance', 'content': "We've launched a new dedicated Go service called 'ingest-backend' to handle all run and feedback ingestion in LangSmith. This architectural improvement delivers significant performance enhancements:• 5x faster average request processing (p95) • 10x faster response times for high-traffic scenarios (p95) • Reduced frontend load times and API latencyBy moving all trace ingestion to this specialized service, our main backend can now focus exclusively on serving frontend requests, leading to better overall system performance.This architectural improvement significantly enhances LangSmith's performance and scalability. The dedicated ingest service means faster processing times for your traces and feedback, while the reduced load on the main backend ensures more responsive frontend interactions. This is especially impactful for users with high-traffic scenarios, where the performance improvements are most pronounced.", 'link': 'https://changelog.langchain.com/announcements/new-ingest-backend-service-for-faster-langsmith-performance?utm_source=LaunchNotes&utm_medium=rss', 'publication_date': 'Wed, 26 Feb 2025 23:41:42 +0000'⟩, ⟨'title': 'LangGraph Supervisor: A Library for Hierarchical Multi-Agent Systems', 'content': "We've released LangGraph Supervisor, a new lightweight Python library that simplifies building hierarchical multi-agent systems with LangGraph. Key features include:• Single supervisor (orchestrator) agent handles all user interactions• Supervisor delegates tasks to worker agents • Worker agents communicate exclusively with the supervisor • Support for multiple hierarchical levels (supervisors of supervisors)With LangGraph Supervisor, you have more high-level, prebuilt entry points for agent development.Check out the library on GitHub: https://github.com/langchain-ai/langgraph-supervisor", 'link': 'https://changelog.langchain.com/announcements/langgraph-supervisor-a-library-for-hierarchical-multi-agent-systems?utm_source=LaunchNotes&utm_medium=rss', 'publication_date': 'Wed, 26 Feb 2025 23:38:58 +0000'⟩, ⟨'title': '⚖️ Start Evaluating LLMs with OpenEvals', 'content': "Evals are a vital part of bringing LLM apps to production. To make it easier to get started, we launched a new OSS repo: OpenEvals! OpenEvals contains prebuilt evaluators that help you quickly add evals to your app, whether it's built with LangChain, LangGraph, or neither. They encapsulate what we've seen as emerging best practices in the industry.Try it out in Python or JS - we welcome any feedback or contributions! Read more about OpenEvals in our blog and see it in action in this video.", 'link': 'https://changelog.langchain.com/announcements/start-evaluating-llms-with-openevals?utm_source=LaunchNotes&utm_medium=rss', 'publication_date': 'Wed, 26 Feb 2025 22:56:00 +0000'⟩, ⟨'title': '📊 Group LangSmith experiments by metadata to get valuable insights', 'content': 'We’ve added a new view that allows you to group experiment results by metadata. Compare the performance of your evaluations across different segments (eg. user segments or subject areas) to pinpoint what’s going well and where your application can improve. Check out our documentation for more information.', 'link': 'https://changelog.langchain.com/announcements/group-langsmith-experiments-by-metadata-to-get-valuable-insights?utm_source=LaunchNotes&utm_medium=rss', 'publication_date': 'Tue, 25 Feb 2025 22:48:00 +0000'⟩]
INSTRUCTIONS:
- Always start by mentioning how you found out about the prospect (course signup or Academy signup)
- If lead source is None, this means the prospect signed up for LangChain Academy
- Incorporate provided content into the email body
- Make sure to tailor the content to the person's role:
- if the person is technical (CTO / Director of Data Science / Director of Engineering), include more technical content
- if the person is non-technical or it is unclear from their title, include the least technical content
- Include links from 'https://changelog.langchain.com' for any content you're referencing
- Be short and to the point - keep it under 5 sentences.
- Structure the email to have 1-2 opening sentences and 2-3 indented bullet points with links and 1 compelling email to close out. don't use the person's role in the email.
- Make the subject line | LangChain
- don't use buzz words like "innovative" use plain simple english.
Here are some examples of a good outreach email:
Hey ,
Saw that you signed up for LangChain Academy. Let me know if you'd like us to schedule a private training for your team at !
Hi ,
I noticed that you signed up for our LangSmith Course.
- We've also recently launched a course on LangGraph. LangGraph is an open source orchestration framework specifically built for Agentic workflows.
Let me know if you'd be interested to learn more about either tool. I'd be happy to schedule a call.
Please write an outreach email based on provided information
