Context Lake
Org-scoped knowledge lake for AI agents—catalog graph, connector action/trigger sync, files and URLs—retrieved on demand as a ContextPack
Exemplar
How this harness capability fits the Exemplar platform—governed agent operations, not a standalone prompt playground.
Why Exemplar
Agents that invent services or miss blast radius are not “hallucinating randomly”—they lack a governed view of production truth.
Context Lake is not Memory: the lake is shared org knowledge; Memory is long-term personal/agent state. Keep them separate so retrieval stays auditable.
What Exemplar delivers
A multi-tenant index and graph over your catalog plus connector-fed documents—same estate the console operators manage.
On-demand ContextPack delivery via REST, MCP, and Agent studio preview—not a mandatory dump into every message.
How teams use it
Index catalog entity types and sync connector actions/triggers from the Context Lake Sources UI; bind sources to agents.
At runtime, agents call retrieve with agentId (or MCP tools) and get passages, entities, and citations grounded in your lake.
Capability checklist
Developer guide
Official documentation on docs.exemplar.dev for this capability.
Open developer guide (opens in a new tab)Contact sales
Harness Platform is scoped per deployment. Talk to us about this feature.
From the blog
Related posts on exemplar.dev.
- What is a Context Lake? How AI Agents Access Production Data
A Context Lake is a graph-backed data substrate that gives AI agents and engineers a shared, live view of the production environment. Why agents need it, what goes into it, and how it differs from a service catalog or data lake.
- Moving from prompt and context engineering toward harness engineering
Three layers behind production agents: shaping the ask, assembling the window, and building the runtime loop. Where each discipline stops and what to invest in next.
- Agents, context, and guardrails on a unified platform
From code completion to production actions; Context Lake, catalog, governance, and DevX Assist/MCP for safe automation.
- Knowledge Architecture for AI Coding Agents: Beyond the AGENTS.md File
How to structure what your AI coding agent knows — the docs directory, context boundaries, ownership, versioning, and the difference between a knowledge system that stays useful and one that silently rots.