Screenshot: The CTO tab main view showing the five sub-tabs (Chat, Team, Memory, Linear, Settings) with Chat selected, the CTO status panel on the left, and an active chat thread on the right.
What is the CTO Agent?
The CTO (Chief Technical Officer) is ADE’s persistent, project-scoped AI agent. Unlike agents you spawn for a specific task, the CTO is always running in the background — watching commits, monitoring lane status, tracking PR progress, and building a cumulative understanding of your project over time. Think of the CTO as the single intelligence that holds your project together. It knows your architecture, your conventions, which lanes are stuck, which PRs are at risk, and what has changed since you were last looking. When you need a quick project status, a code review, or to delegate a large task, the CTO is your first stop. The CTO ships with a rich default persona: a persistent technical lead who holds the complete mental model of your codebase, coordinates worker agents, and ensures consistency across all development efforts. Its system prompt includes a baked-in Memory Protocol (search memory before acting, save important findings immediately), a Daily Context routine (orient at the start of each conversation by checking recent decisions and worker activity), and a Decision Framework (make autonomous decisions when safe, escalate when risky). These protocols are part of the CTO’s DNA — they are always present in the system prompt, even after compaction.Always-On Awareness
Runs on a configurable heartbeat, checking for new commits, PR status changes, Linear issue updates, and stuck lanes — even when you are not looking.
Org Chart Model
The CTO sits at the top of an agent hierarchy. It spawns and coordinates specialized Worker agents (Employees) to handle specific tasks.
Bidirectional Linear Sync
Reads from and writes to Linear. Creates issues from code changes, updates issue status when PRs merge, and adds analysis comments automatically.
Deep Memory
Maintains multi-scope persistent memory across
project, identity, daily-log, run, and runtime-thread scopes. The CTO remembers what happened yesterday.CTO vs. Regular Agents
Understanding how the CTO differs from the agents you spawn manually (in chat sessions or missions) helps you know when to use each.| CTO Agent | Regular / Worker Agent | |
|---|---|---|
| Lifecycle | Always on; persistent across sessions | Ephemeral; lives for one task or session |
| Scope | Entire project | Specific lane, task, or mission |
| Memory | Accumulates over weeks/months | Within the current session or run |
| Triggers | Heartbeat schedule + events + manual chat | Explicit user action or automation trigger |
| Authority | Can spawn lanes, create missions, delegate to workers | Operates within its assigned lane/context |
| Linear access | Full bidirectional sync (owner) | Read-only via MCP tools, if granted |
| Primary UI | CTO tab | Lane terminal, Chat pane, Missions tab |
The Org Chart Model
The CTO implements an org chart model for AI work delegation.- A name and specialization prompt that defines their role and constraints
- An assigned lane (optional; some workers operate across lanes)
- A tool palette — a subset of MCP tools they are permitted to use
- A budget limit — a token/cost cap enforced by the CTO
Screenshot: The Team sub-tab showing an org chart or card grid of workers with name, specialization, assigned lane, status indicator, and budget usage.
Explore CTO Features
Setting Up the CTO
Walk through onboarding, heartbeat configuration, and verifying the CTO is active.
CTO Memory
Understand multi-scope persistent memory, memory tiers, and the memory review surface.
Linear Integration
Connect Linear for bidirectional issue sync, status updates, and intelligent triage.
Workers & Budget
Hire workers, manage budgets, configure practical workflows, and troubleshoot issues.