Sign InOpen Brain
Back
AI EngineerVideoSource LinkedcontextNew

Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblocked

Retrieve code alongside decisions, incidents, tickets, and conversations so the agent does not repeat a known outage trigger.

AI EngineerAI EngineerAI EngineerAug 21, 20262 min
Open SourceOpen MarkdownOpen JSON
Source Summary

A coding agent with repository access still recommended a known outage trigger. Background agents need reconciled decisions and incident context, not just more raw MCP results.

Practical Implication

For unattended coding agents, retrieve decisions, incidents, tickets, conversations, and code together. Reconcile conflicts, rank relevance, enforce permissions, and provide a synthesized task view rather than making each agent resolve raw MCP output.

Agent-Ready Context
An agent investigating QA latency of **3–4 seconds** versus an expected **hundreds of milliseconds** recommended re-enabling async dispatch. It missed a later Slack discussion and Linear postmortem showing that setting had caused an outage.

For unattended coding agents, retrieve decisions, incidents, tickets, conversations, and code together. Reconcile conflicts, rank relevance, enforce permissions, and provide a synthesized task view rather than making each agent resolve raw MCP output.

The example demonstrates one corrected recommendation, not a measured reliability gain. Building and maintaining an organization-wide context model also introduces access-control, freshness, and conflict-resolution work.
Context Map
contextcoding#context-engineering#retrieval#mcpGeneric AgentPrepare Coding Session
Rate This Item
Personal Note

No note yet. Notes are included in exported bundles.

Related — Every Edge Explained

No approved edges yet for this post.