CAIPE Roadmap

YAML-based dynamic agent configuration — domain-centric personas (SRE, code review, incident), dynamic skills integration, and full Custom Agent infrastructure replacing hardcoded configurations.

• YAML-based agent configuration and runtime
• Dynamic skills & task builder integration
• Domain-centric personas: SRE Agent, Code Review Agent
• Dynamic agent visibility & access control
• Custom Agents as the default supervisor type

Role and team-based access control touching all features — OAuth 2.1, audit logs, and channel-to-agent assignment.

• OAuth 2.1 features: DCR, Token Exchange, three-legged auth for remote MCP servers
• Manage RBAC user/teams/roles from UI
• Assign Slack/Webex channels ↔ Custom agents
• Detailed authorization audit logs (OBO agent actor logs)
• Two-tier policy system for self-service workflow tool authorization

Per-user and per-agent LLM token budget enforcement using LiteLLM keys — track spend, set quotas, and prevent runaway inference costs.

• LiteLLM key integration for per-agent token tracking
• Dynamic LLM key creation for dynamic agents
• Budget dashboards and quota alerts in the admin UI

Sandboxed agent execution environments for safe testing, plus a deepeval-based evaluation pipeline for RAG precision/recall and agent response quality.

• Sandbox environment for agent testing without production impact
• deepeval pipeline: RAG precision, recall, F1 scoring
• Self-improving architecture feedback loop

Self-directed agents that proactively monitor, detect, and act on platform events without explicit user prompts.

AI agents integrated throughout the software development lifecycle — from planning and coding to review, testing, and deployment.