# WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar

Source: [AI Engineer](https://www.youtube.com/watch?v=8G_1-3IO4ZQ)  
Feed7 permalink: https://feed7.dev/p/wtf-is-the-context-layer-the-missing-infrastructure-for-production-agent-0t47xqf  
Published: 2026-07-14T22:45:06.000Z  
Trust: Source Linked (source_linked)

## Why Included

Atlan’s agent experiments argue for shared, versioned context instead of per-agent memory: a portable layer for business facts, skills, norms, retrieval, and feedback across changing harnesses.

## Source Summary

Atlan moved among Relevance, Google ADK, Glean, Claude Code, and Codex, repeatedly stranding context inside individual systems. Its current shared layer supports about **300 skills** and **40 agents**, combining business definitions, data relationships, playbooks, and norms.

## Practical Implication

Treat agent context like code: give it owners, versioning, dependency management, access controls, and portable retrieval interfaces. Keep shared knowledge outside any single harness so agents do not learn separately or continue using stale positioning and metrics.

## Agent-Ready Context

Atlan moved among Relevance, Google ADK, Glean, Claude Code, and Codex, repeatedly stranding context inside individual systems. Its current shared layer supports about **300 skills** and **40 agents**, combining business definitions, data relationships, playbooks, and norms.

Treat agent context like code: give it owners, versioning, dependency management, access controls, and portable retrieval interfaces. Keep shared knowledge outside any single harness so agents do not learn separately or continue using stale positioning and metrics.

This is Atlan’s account of its own implementation, not a comparative evaluation of context-layer designs. The talk identifies unresolved problems around drift, downstream breakage, governance, and deciding which context should be local or global.

## Context Map

- Layer: context
- Domains: coding, data
- Topics: context-engineering, skills, agent-memory

## Uncertainty

- This is Atlan’s account of its own implementation, not a comparative evaluation of context-layer designs. The talk identifies unresolved problems around drift, downstream breakage, governance, and deciding which context should be local or global.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.