As Circuitte's monorepo grew across multiple apps and packages, AI assistants drifted — re-reading the wrong files, missing conventions and producing inconsistent changes. Project knowledge was scattered, undocumented and quickly went stale.
ACE — AI Context Environment
A four-layer AI context system that keeps an AI assistant fluent in a large monorepo — a live manifest, an in-app dashboard, specialized sub-agents and slash-command skills that make AI-assisted engineering reliable at scale.
AI ToolingDeveloper ExperienceInternal Platform Internal · Verisay
4
context layers
8
specialized agents
20+
slash-command skills
The challenge
Problem
What we built
Solution
ACE (AI Context Environment) structures project knowledge into a four-layer pyramid — root rules, package rules, category summaries and detailed design docs — backed by a live manifest, an in-app dashboard, specialized sub-agents (audit, context-refresh, inventory, security) and slash-command skills. Freshness thresholds, smoke tests and a technical-decision-record (TKD) workflow keep the context accurate as the codebase evolves.
TypeScriptNode.jsSvelteKitClaude