Back to Home

Roadmap

What We're Building

The Hub is actively growing. Here's what's live now, what's coming next, and our long-term vision.

Phase 1Live

Text & Vision Firewall

  • 28+ PII entities with configurable actions (block / redact)
  • OCR-based image PII scanning (Base64, max 5MB)
  • Context-aware full conversation history DLP
  • Smart routing + managed credits + BYOK hybrid billing
  • Policy versioning with restore & audit trail
  • Custom regex IP Guard rules
  • Prompt injection / jailbreak heuristic blocking
  • Multi-provider failover with automatic fallbacks
  • Image generation support (FLUX, DALL-E, Stable Diffusion)
Phase 1.1Building

Budget Enforcement & Cost Control

The AI Spending Circuit Breaker

Take total control of your AI OpEx with granular project-level quotas.

Multi-Provider Quotas

Set one budget that applies across OpenAI, Groq, and Together.ai simultaneously.

Threshold Alerts

Get notified via Webhook or Slack when a team hits 50%, 80%, or 100% of their monthly limit.

Recursive Loop Protection

Our proxy identifies and kills runaway 'Agent Loops' before they drain your credits.

Policy-Based Routing

Force a 'Budget Mode' that restricts usage to low-cost models once a spending threshold is crossed.

  • Project-level spending quotas across all providers
  • Threshold alerts at 50%, 80%, 100% via Webhook / Slack
  • Recursive agent-loop detection and auto-kill
  • Policy-based 'Budget Mode' routing to low-cost models
  • Real-time per-project cost dashboard with per-model breakdown
  • Per-request token caps with pre-flight balance enforcement
Phase 2Next

Document Sovereignty & Streaming

  • 50MB+ PDF/Docx processing via secure upload endpoints
  • Async document worker with enterprise PII reporting
  • Buffer-based output scanning for streaming responses
  • BYOK Smart Vision Routing — auto-select vision-capable models within the user's provider when images are detected
  • ML-based jailbreak classifiers (beyond regex heuristics)
  • Webhook notifications for policy violations
  • Team & organization management
Phase 3Vision

Managed RAG & Long-Term Memory

  • Vector database integration for conversation memory
  • Secure Gateway for RAG pipelines
  • Content classification and anomaly detection
  • SOC 2 compliance dashboard
  • Self-hosted / on-premise deployment option
Available Now

The AI Intelligence Suite

Stop guessing which model is best for your specific prompts. The world's first Financial & Quality Optimizer for production AI is here.

Smart Model Selection

Automatically pick the best model for each prompt based on quality, latency, and cost.

Cost Optimization

Cut AI spend by up to 60% without sacrificing output quality on production workloads.

Quality Benchmarking

Continuous evaluation of model responses against your quality criteria in real time.

Join the Stealth Beta
Get 1,000,000 Free Credits

No credit card required · Start in 60 seconds