The shared control surface between you and your coding agent

Your coding agent operates in its own context. So do you. ctlsurf is where you meet.

A persistent, inspectable coordination workspace that sits between you and your AI coding agent — so your intent survives every session, every context window, and every handoff.

See ctlsurf in Action

The Workflow: In our interactive demo, you'll see how ctlsurf transforms AI coding workflows:

  1. Highlight requirements in your documentation and instantly create tasks for your AI agent
  2. Attach Skills (playbooks) to guide agents through complex workflows with guardrails
  3. Watch agents work as they check out tasks, update progress, and document their decisions
  4. Review structured completions showing exactly what was done, assumed, and skipped

Example: An agent implementing "user authentication" documents: "Added JWT-based auth" (summary), "Used existing User model" (assumption), and "Skipped refresh token implementation" (simplified). No more mystery about what your AI actually did.

You've felt it.

You give Claude Code or Cursor a clear task. It works beautifully for twenty minutes. Then it drifts. It forgets your architecture decisions. It rewrites files you told it not to touch. You restart the conversation and now you're re-explaining everything from scratch.

The problem isn't the agent. It's that there's no shared surface between you and it. No place where your decisions persist. No place where you can see what the agent is actually working from and correct it in real time.

You're collaborating with an intelligent system that has amnesia.

And when this happens right before a demo, a review, or a handoff, you're the one explaining behavior you didn't control.

🧠 The Reframe

Full explainability of AI internals is an unsolved research problem. ctlsurf doesn't try to solve it. Instead, it does something more practical — it gives you and your agent a shared artifact you can both see, reference, and build on.

Think of it like a blueprint between two engineers who speak different languages. You don't need to understand each other's internal reasoning. You need a document you both trust.

What ctlsurf actually does

A persistent, inspectable coordination workspace where human intent and agent behavior stay aligned.

🧠

Persistent Context That Outlives the Session

Your architecture decisions, coding standards, and project knowledge live in a shared workspace the agent reads every time. No more re-explaining.

🎯

Highlight-to-Task

See something wrong? Highlight it, annotate it, turn it into an instruction. The agent picks it up immediately. You're steering, not starting over.

Real-Time Sync via MCP

ctlsurf connects directly to your coding agent through MCP integration. Changes you make are reflected instantly. No copy-paste. No workflow interruption.

👁️

Inspectable at Every Layer

You can always see exactly what instructions your agent is operating under. Not a black box. A legible, editable control surface that you own.

Explainability in Action

When an AI agent completes a task, it must document what it did, what it assumed, and what it skipped.

Structured Task Completion

No more guessing what the AI did. Every completed task includes:

  • Summary - What was actually done
  • Assumptions - What the agent assumed (required)
  • Attempted but failed - What was tried but didn't work
  • Simplified or skipped - What was quietly dropped

The "simplified or skipped" field is the most important - it catches when agents give up on parts of tasks without telling you.

✅ Implement user authentication
Completed by AI Agent
Summary: Added JWT-based auth with login/logout endpoints
Assumptions: Used existing User model, assumed bcrypt for hashing
⚠️ Simplified: Skipped refresh token implementation, used simple JWT expiry instead

🔄 Task Reopen Workflow

When you spot something the agent simplified or skipped that shouldn't have been, you can reopen the task with feedback:

  1. Click Reopen on any completed task
  2. Provide feedback explaining what needs to be addressed (e.g., "Actually implement refresh tokens - this is a security requirement")
  3. Agent receives context about why the task was reopened and what was missing
  4. Task completes properly with the full implementation this time

This creates an accountability loop - agents can't silently cut corners because you'll see exactly what they skipped and can push back.

How it works

Three steps to persistent AI context

1

Connect via MCP

Add ctlsurf to your MCP config. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible tool.

2

Build Your Knowledge Base

Create pages for architecture, decisions, and tasks. Your agents will reference these automatically.

3

Agents Remember Everything

Every session, agents check for tasks, read your docs, and work with full project context.

What is MCP (Model Context Protocol)?

MCP is an open standard created by Anthropic that allows AI assistants to connect to external tools and data sources. ctlsurf is built as an MCP server, meaning any MCP-compatible AI coding assistant can connect to it seamlessly.

Setup is simple: Add a few lines to your MCP configuration file, and your AI agent gains access to 50+ ctlsurf tools for managing pages, tasks, skills, and documentation.

No code changes required. Your existing AI coding workflow stays the same - ctlsurf just gives your agent a persistent memory and knowledge base to work with.

Works with your existing tools

Claude Code Cursor Windsurf VS Code Any MCP Client

Built for how you work

From solo developers to engineering teams

👥

Engineering Teams

Maintain shared context across sprints, agents, and tools. Everyone stays aligned on decisions and progress.

🎯

Founders & Tech Leads

Understand why features shipped a certain way, with a traceable history of decisions and trade-offs.

🤖

AI-Driven Workflows

Coordinate long-running tasks with evolving state instead of isolated prompts. Context persists across sessions.

Skills: Reusable Agent Playbooks

Define workflows with guardrails that guide AI agents through complex tasks consistently.

What Are Skills?

Skills are structured workflow templates that guide AI agents through complex, multi-step tasks. Think of them as playbooks or runbooks that ensure consistency and quality across your team's AI-assisted work.

Each skill contains:

  • Inputs - Variables the agent needs to collect before starting (e.g., endpoint URL, error message)
  • Workflow Steps - Sequential actions to follow, with optional checkpoints for human review
  • Guardrails - Safety rules the agent must never violate (e.g., "Never modify production database directly")

Example Use Cases: API debugging workflows, code review checklists, deployment procedures, security audit processes, feature implementation patterns.

🔧

API Debug Workflow

Systematic approach to debugging

Reproduce the issue
Check logs for errors
Identify root cause
Implement and test fix

Why Skills Matter

  • ✓ Consistent workflows across team members
  • ✓ Built-in guardrails prevent mistakes
  • ✓ Reusable across projects
  • ✓ Fork and customize from marketplace

🏪 Skill Marketplace

Browse and fork skills from the community marketplace. Find battle-tested workflows for common development tasks and customize them for your team's needs.

  • Personal Skills - Private workflows for your own use
  • Project Skills - Shared within a specific codebase/team
  • Public Skills - Published to the marketplace for anyone to use

Simple pricing

Start free, upgrade when you need more

Free

For individual developers

$0/month
  • 5 projects
  • 100 requests/min rate limit
  • 500 MB storage
  • 10 project skills
  • MCP access
Get Started

The deeper "why"

"AI agents reason differently than you do. We can't fully decode their internals yet, and maybe we never will. But we can build a shared workspace where human intent and agent behavior stay aligned. That's what ctlsurf is."

Built by an AI engineer with decades of experience building enterprise ML systems. ctlsurf came from the frustration of watching brilliant agents lose context every single session.

Get Started Free →