Try Scope Architect free, no card required. Try Free →

Pricing built for builders.

Two plans, flat pricing. Bring your own AI keys at any paid tier — pay providers directly, no markup.

Want to try it first? Start free, no card required →

Builder

$29/mo
  • MCP connection
  • 500 credits / moTypical month: 2-3 generations + heavy chat = ~200 credits. 1 generation = 50 credits, chat = 2, AI apply/edit = 5. BYOK removes the meter entirely.
  • Agent Handoff exports
  • Unlimited projects
  • BYOK - no credit limitsConnect your own API keys and pay providers directly at their published rate. No markup, no metering.
Get Started

MCP connection, BYOK, and the full toolkit for solo devs shipping with AI agents.

Team

$87/mo
$29/seat × 3 seats
Team seats3
  • Everything in Builder
  • Real-time collaboration on scopes
  • Role permissions
Get Started

Everything in Builder, shared across your team. Real-time collab, pooled credits, and role permissions.

Need more?

Let’s talk
custom billing
  • Everything in Team
  • Higher credit limits
  • Multiple Builder Profiles
  • Custom billing cadence
  • Dedicated onboarding
  • Priority support channel
Talk to us

Heavier usage, bigger team, or a more specific use case. Just reach out and we’ll figure it out.

Included in every plan.

The core workflow ships at every tier.

Scope Engine

Turn a vague idea into modules, features, and atomic tasks your AI can actually execute.

Architect Chat

Refine and direct your scope by talking to AI. Diffable change plans you preview and apply in one click.

Live Workspace

One real-time view of every task: status, owners, agents, and time in progress across the whole project.

Context Management

The context, memory, and docs your AI reads and writes as it builds, so nothing gets lost between sessions.

Builder Profile

Your stack, your target agent, your code style, your estimate unit. The engine calibrates to your defaults.

MCP connection

Live link to Claude Code and Cursor. Your AI reads the current plan directly and writes back, no copy-paste required.

Agent Handoff exports

Clean JSON, Markdown, or rules optimized for Cursor, Claude Code, Devin, or Windsurf. Copy, paste, ship.

Not sure yet?Start free →No card required. Feel the workflow first.
Why Scope Architect

Why not just write a long prompt in Cursor?

You can. And it'll work for a small feature. Here's what changes when the project gets real.

Raw prompting
  • Re-explain the project every session
  • Agent invents its own task boundaries (badly)
  • Acceptance criteria are vibes, not contracts
  • No shared plan between humans + agents
  • Edge cases discovered mid-implementation
Scope Architect
  • Project context lives in the plan, not the prompt
  • Recursive decomposition gives atomic, agent-sized tasks
  • Explicit acceptance criteria on every task
  • Dependency graph + shared Builder Profile
  • Edge cases surfaced before the agent starts spending tokens

FAQ

Scope Architect is the missing planning layer for the AI coding era. It turns vague ideas and discovery notes into structured, agent-ready specifications you can hand off cleanly to AI agents like Cursor, Claude Code, Devin, or Windsurf.
Any of them. Scope Architect produces a clean, agent-optimized export (JSON + Markdown) tuned per target: Cursor, Claude Code, Devin, Windsurf, or any LLM-driven coding agent. The same engine works with future agents too.
Generate a spec, refine it in Architect Chat, then export. You get a self-contained JSON or Markdown spec optimized for the LLM context window of your target agent. Copy to clipboard, drop into your agent, ship.
Yes. Connect your Anthropic, OpenAI, Google, or xAI keys and pay providers directly. No middle-man markups, no rate limits beyond the provider's. Your project context stays under your control.
Yes. Start free, no card required. Scope a real project, refine it, and run the workflow end to end so you can feel how it works before upgrading. When you're ready for unlimited projects, MCP, and BYOK, the Builder plan is $29/mo.
A reusable set of preferences: your tech stack, preferred agent (Cursor / Claude Code / Devin / Windsurf), code style notes, estimate unit (hours, story points, agent sessions), and testing preferences. The engine reads it on every generation so specs land in a context your agent already understands.
Yes. Tasks have statuses (To Do, In Progress, In Review, Done) and live on a shared plan. Humans pick tasks; agents pick tasks; both work in parallel against the same spec. Agent handoffs export per-task so you can scope just what you want shipped.