proomt

Search

Search posts, papers, and topics

All posts

InfoQAjay Prakash28 min readtalkintermediate

Presentation: Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP

Read on infoq.com

Summary

LinkedIn built a “Contextual Agent Playbooks and Tools” layer that wraps internal services (code search, docs, feature flags, etc.) behind the open‑source Model Context Protocol (MCP). By feeding LLM‑powered coding agents the exact internal artifacts they need, the agents can diagnose incidents, generate PRs, and update incident tickets in minutes, delivering a reported 20 % productivity gain wit…

  • MCP lets any LLM‑agent call LinkedIn’s internal tools (code search over ~1 000 repos, wiki/docs, feature‑flag store, metrics) as first‑class primitives.
  • Agents can fetch logs, recent changes, and runbooks, then synthesize a root‑cause summary and even open a PR, cutting incident triage from hours to minutes.
  • Operational guardrails (e.g., sandboxed execution, human‑in‑the‑loop verification, strict diff checks) keep generated changes reliable; LinkedIn reports zero reliability regression after rollout.
  • Over 600 agent‑driven workflows are in production, spanning incident response, code refactoring, and routine ops tasks.

Scaling LLM agents to massive, highly regulated codebases requires more than raw model capability; you need a systematic way to inject proprietary context and enforce safety. LinkedIn’s MCP‑based layer shows a practical path for other large tech orgs to get real productivity from AI agents without…

6/10
devopsllmobservabilityarchitectureml infra

Related reading

  1. Article: Beyond Relevance: A Governance-First Architecture for Enterprise Personalization

    The article proposes a governance‑first architecture for enterprise personalization, where policy‑driven steps (memory, journey graph, AI routing, scoring, trust checks, outcome simulation) shape the recommendation before it is returned. A reference FastAPI implementation demonstrates the pattern with external YAML policies and optional LLM assistance.

    InfoQinfoq.com19 min

  2. How Data 360 Builds Trusted Context: The Enduring Layer for Enterprise AI

    Salesforce’s Data 360 provides a shared runtime that assembles the minimal, authorized slice of enterprise data (“Trusted Context”) for each AI‑agent turn. A six‑stage Agent Context Engine (Resolve, Plan, Reconcile, Govern, Compile, Learn) pulls data from structured, unstructured, and streaming sources across Salesforce, Snowflake, Databricks, etc., applies fine‑grained policy, and returns a toke…

    Salesforce Engineeringsalesforce.com11 min

  5. The DevFest Community Workshop Experience: Building Real Agents Together

    Google’s DevFest Community Workshop introduced a “Workbench” format that emphasizes architectural mental models over copy‑paste code, guiding engineers to build long‑running, self‑evolving multi‑agent systems with the Agent Development Kit and Gemini Enterprise platforms. Attendees learned state‑separation, workflow pausing, and self‑patching pipelines, and the series will continue in five more c…

    Google Cloud Bloggoogle.com2 min

  6. Article: Architecting Secure and Scalable Facial Verification Systems

    A real‑world post‑mortem of a high‑volume face verification service that moved from a naïve synchronous API to an async, layered pipeline (edge validation, preprocessing, decoupled detection/verification, decision engine) to achieve 8.5k rpm, p99 < 1.8 s, 30 % cost savings, and strict privacy controls.

    InfoQinfoq.com15 min