Turn AI-generated code into shippable products
Agent-Dev manages the full lifecycle from requirement to production. You own the product decisions; Agent-Dev turns them into a shippable, verifiable, maintainable engineering system.
Golden Path
The complete pipeline from requirement to delivery report
- Requirement
Describe goal and scope in natural language
- Clarification
Ask only about real uncertain decisions
- Spec
Acceptance criteria and implementation tasks
- Codex implements
Execute in isolated worktree
- Local verify
lint / typecheck / unit / build
- PR
Create PR with quality gates
- Vercel API Preview
Deploy API first
- Cloudflare Pages Preview
Deploy frontend after getting API URL
- Joint smoke test
CORS / Auth / env var validation
- Manual acceptance
Preview Gate passed
- Delivery report
Evidence chain and residual risks
Why Agent-Dev
Not a faster code generator, but accountability for the full delivery
User-owned
Code, repos, data, domains, cloud resources, and Blueprint belong to the user. After leaving Agent-Dev, the product still builds, deploys, and maintains independently.
Neutral and portable
Models and providers are replaceable. No lock-in to a specific Agent Runtime or cloud platform. Switching databases or deploy providers is a controlled migration, not a setting change.
Real gates
An LLM may propose, but cannot obtain production permission via prompt. Deterministic Policy, GitHub Rulesets, and Environment Approval are the final constraints.
Evidence-based delivery
Delivery status is grounded in GitHub Checks, Deployment Records, Preview URLs, database state, smoke tests, and manual acceptance, not the Agent's natural-language summary.
Compared to adjacent products
Agent-Dev doesn't compete on who generates pages faster
| Dimension | Agent-Dev | Replit Agent | Lovable | GitHub Spec Kit |
|---|---|---|---|---|
| Unit managed | Product lifecycle | Single session | Single generation | Specs and tasks |
| User-owned resources | Yes, own GitHub/cloud | No, Replit-hosted | Partial | Yes |
| Replaceable Agent | Yes | No | No | Partial |
| Portable providers | Yes, controlled migration | No | No | N/A |
| Production permission | Policy + manual gate | Platform-managed | Platform-managed | Manual gate |
| Delivery evidence | External fact chain | Platform logs | Preview | Task status |
| Long-term maintenance | Drift detection + fix policy | Limited | Limited | N/A |
Responsibility Boundary
Transparent split between user and platform builds trust
User is responsible for
- →Who the product serves and what problem it solves
- →Feature scope, experience, aesthetics, and business priority
- →Cost, privacy, data, and external-impact decisions
- →Preview experience acceptance
- →Production release and final Approval
Agent-Dev is responsible for
- →Provide verified product Blueprints and default standards
- →Turn requirements into specs, acceptance criteria, and tasks
- →Call replaceable Agent Runtimes to implement, test, and fix code
- →Orchestrate GitHub, Supabase, Cloudflare, Vercel, and more
- →Enforce deterministic Policy to constrain Agent permissions
- →Aggregate real CI, deploy, test, and manual-acceptance evidence
- →Detect drift, expired config, and maintenance tasks
- →Report clear delivery status and residual risks
Agent-Dev guarantees process and evidence integrity, not market success.
Product Constitution Excerpts
Core principles that constrain platform behavior
Defaults over choices
Beginner mode decides ~90% of engineering questions for the user, asking only about product, cost, privacy, or risk. Options are escape hatches, not the default experience.
AI reasons, Policy authorizes
An LLM may propose, but cannot obtain production permission via prompt. Deterministic Policy and provider permissions are the final constraints.
External facts over Agent self-report
Delivery status is grounded in GitHub Checks, Deployment Records, Preview URLs, and smoke tests, not the Agent's natural-language summary.
User owns the product
Code, repos, data, domains, cloud resources, and Blueprint belong to the user. Models and providers are replaceable.
Frequently Asked Questions
Key questions about ownership, security, and automation
What is Agent-Dev?
Agent-Dev is an Agentic Product Delivery Platform. It is not a replacement for Codex or Claude Code, nor a source-code-only app builder. It manages the full product lifecycle from requirement to production.
Who owns my code and cloud resources?
Code, repos, data, domains, cloud resources, and Blueprint all belong to the user. After leaving Agent-Dev, the product still builds, deploys, and maintains independently. Models and providers are replaceable.
How does Agent-Dev control AI production permissions?
An LLM may propose, but cannot obtain production permission via prompt. Deterministic Policy, GitHub Rulesets, Environment Approval, and provider permissions are the final constraints. Autonomy scales per project and per action; there is no single risk-blind "full auto" switch.
How is delivery actually verified as complete?
Delivery status is grounded in GitHub Checks, Deployment Records, Preview URLs, database state, smoke tests, and manual acceptance, not the Agent's natural-language summary. Unexecuted verifications cannot be marked as passed.
How is Agent-Dev different from Replit Agent or Lovable?
Replit Agent and Lovable focus on conversational generation and one-click hosting on platform-owned resources. Agent-Dev's minimum unit is the product lifecycle: it uses user-owned GitHub/cloud resources, with replaceable Agents and providers, and is accountable for full delivery and long-term maintenance.
What tech stack does the first version support?
The first version fixes a Web SaaS Golden Path: React + Vite + TypeScript frontend, Hono API, Supabase DB and auth, Cloudflare Pages for frontend hosting, Vercel Functions for API hosting, GitHub Actions for CI, and local Codex as the Agent Runtime.
Start your first product delivery
Get a Web product baseline you own in 60 minutes