Features
AI-powered requirement extraction from legacy code and documents (ReqSpell)
Inline AI code suggestions and auto-completion in IDEs (VS Code, IntelliJ, Eclipse)
Smart code generation with multi-file edits (CodeSpell)
Design-to-code conversion via Design Studio and Spellbox
Reverse-engineering legacy codebases into structured specifications
Mapping requirements to test plans and automated test case generation (TestSpell)
Agent Mode: plans tasks, builds TODO list, awaits approval, then executes autonomously
Figma to code generation pipeline (screens and component selection)
Task Completion engine for complex multi-step coding tasks
Saved prompts for consistent code generation across projects
Usage tracking reports at team and org level
Team collaboration through shared spells and design studios
Chat history (local) for code sessions
Spell credits for on-demand design generation
User management console with role-based access
Live knowledge graph from code, commits, issues, and docs
Feasibility analysis: flags buildable vs risky items
Technical design document generation grounded in service topology
Impact assessment maps services, APIs, and dependencies across repos
Auto-scoping epics into Jira/Linear stories with effort estimates
One-shot production code generation grounded in service patterns
AI code reviews with cross-repo impact analysis
Production issue triage via MCP
Conversational learning from Slack and Jira
Accelerated onboarding via system-level Q&A in coding agents
Create Jira tickets and merge requests from Slack
MCP server for integration with Cursor, Claude Code, Codex
On-prem or cloud deployment
No code storage or model training
