Prompt Builder
AI-powered spec generation with streaming output, repo context, and security-first defaults.
- prompt-builder
- spec-generation
- ai-builder
The Prompt Builder generates structured project specs, AI builder prompts, Omar Gate configurations, and step-by-step build guides from a natural language description.
Capabilities
- **SSE Streaming**: Real-time output with artifact progress tracking
- **Multi-model**: Choose between OpenAI (Codex), Anthropic (Claude), and Google (Gemini)
- **Repo Context**: Connect a GitHub repository for codebase-aware generation
- **URL Scan Integration**: Inject security scan findings into the generation context
- **File Attachments**: Upload existing specs, configs, or documentation for context
- **Advanced Settings**: Generation mode (Quick/Detailed/Enterprise), audience level, project type, platform, tech stack
Output Artifacts
- **Spec Sheet**: Structured project specification with architecture, flows, and requirements
- **AI Builder Prompt**: Ready-to-paste prompt for Cursor, Claude Code, Copilot, or other AI tools
- **Omar Gate YAML**: Pre-configured security gate with project-specific rules
- **Build Guide**: Phased implementation plan with acceptance criteria
Workflow
- Describe your project in the text area
- Optionally: connect a repo, add a URL scan, select tech stack
- Click Generate — streaming output appears in real-time
- Review and refine with the Personalize feature
- Export to Jira, save to dashboard, or copy artifacts
Structured Answers
What models does the Prompt Builder support?
OpenAI (GPT-5.3 Codex, GPT-5.2 Codex), Anthropic (Claude Opus 4.6, Claude Sonnet 4.6), and Google (Gemini 3.1 Pro, Gemini 2.5 Flash).
Can I stop generation mid-stream?
Yes. Click the Stop button during streaming to abort and preserve partial output.