ServiceNow uses LangSmith, knowledge graph and MCP to orchestrate agents
When I first saw ServiceNow’s newest suite, I thought it might finally bridge the gap between transparent bots and fully-autonomous workflows. The company has been wrestling with how to keep its customer-success agents clear enough for engineers while still letting them run on their own. Their answer is a set of tools that pull data, context and execution paths into a single view.
By building a graph-based map of internal knowledge and a protocol for passing model state, ServiceNow appears to give its orchestration layer a better line of sight into each agent’s choices. The real hook is the tracing feature - it lets developers watch a request from start to finish, spot bottlenecks and tweak performance without guesswork. In practice, a dev can follow a ticket from the moment a user raises it, through the AI-powered steps, all the way to resolution.
The outcome? A system that feels more observable and manageable, something that has been hard to pull off at scale. This sets the stage for the integrated stack and its standout tracing capability.
ServiceNow has integrated their knowledge graph and Model Context Protocol (MCP) with LangGraph to create a comprehensive technology stack for agent orchestration across their platform. LangSmith tracing: The standout feature for agent development LangSmith offers detailed tracing capabilities by providing the input, output, context used, latency, token counts at every step of agent orchestration and helps users to improve the agents performance. The intuitive structuring of trace data into inputs and outputs for each node makes debugging significantly easier than parsing through logs. ServiceNow uses LangSmith's tracing capabilities to: - Debug agent behavior step-by-step: Understanding exactly how agents make decisions and where issues occur - Observe input/output at every stage: Seeing the context, latency, and token generation for each step in the agent workflow - Build comprehensive datasets: Creating golden datasets from successful agent runs to prevent regression Rigorous evaluation strategy with custom metrics ServiceNow implemented a sophisticated evaluation framework in LangSmith tailored to their multi-agent system.
Will the new stack actually move the needle? ServiceNow’s AI team says they’ve stitched a knowledge graph and the Model Context Protocol into LangGraph, aiming for a single platform that can steer agents through sales and customer-success tasks. Hooking LangSmith’s tracing into the mix lets developers watch each decision step, which they claim is the standout feature.
In practice, you can spot a prompt that works, or one that trips up, and then tweak the prompt or the routing logic. The write-up, however, doesn’t share any hard numbers, so it’s unclear whether that extra visibility will speed up lead conversion or boost post-sale satisfaction. Adding LangSmith, LangGraph, the knowledge graph and MCP also piles on complexity - maintenance could become a headache.
Still, the design does try to cover the whole customer journey, from spotting a lead to later follow-ups, even if the results are still missing. As ServiceNow keeps polishing the stack, we’ll need real-world data to see how it reshapes enterprise workflows.
Further Reading
- ServiceNow Knowledge 2025: 10 Game-Changing Takeaways - Aelum Consulting
- LangSmith now supports MCP - LangChain - Changelog - LangChain Changelog
- The Model Context Protocol (MCP) Ecosystem (2024-2025) - Rick Xie Blog
- Still worth using LangGraph and LangSmith combo in 2025? - Latenode Community
- My CreatorCon 2025 Experience: Innovation, AI Agents and Community - ServiceNow Community
Related Reading
Research & Benchmarks Consensus uses GPT-5 and Responses API to speed scientific research
Research & Benchmarks Developers say Sora, unlike Vine/TikTok, is not about people in social media
Research & Benchmarks Google AI Advisors Let Users Probe Performance with Conversational “Why” Queries
Common Questions Answered
How does ServiceNow combine its knowledge graph with the Model Context Protocol (MCP) and LangGraph for agent orchestration?
ServiceNow integrates its internal knowledge graph and MCP with LangGraph to form a unified technology stack. This combination enables agents to access structured knowledge, maintain model state across steps, and execute workflows consistently across the platform.
What role does LangSmith tracing play in improving ServiceNow's AI‑driven agents?
LangSmith provides detailed tracing that records inputs, outputs, context, latency, and token counts at each orchestration step. By exposing this data, developers can pinpoint where prompts succeed or fail and iteratively refine agent performance.
Which workflows are targeted by ServiceNow's new agent orchestration stack?
The stack is designed for sales and customer‑success workflows, allowing agents to automate tasks while remaining transparent to engineers. By unifying knowledge, context, and execution, the platform aims to streamline these high‑touch processes.
Why is the tracing feature described as the standout capability of ServiceNow's integration?
Tracing is highlighted because it gives engineers a step‑by‑step view of an agent’s decision‑making, including latency and token usage. This visibility helps teams quickly identify bottlenecks and adjust prompts for more reliable outcomes.