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 + Budget Enforcement

  • 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)
  • Streaming chat completions (SSE) with full DLP on input
  • Per-request token caps with pre-flight balance enforcement
  • Real-time per-project cost dashboard with per-model breakdown
  • Wallet balance enforcement — requests blocked when balance hits zero
Phase 1.1Shipped

Developer Experience & Compliance

Integrate Faster, Stay Compliant

A native SDK, real-time security alerts, agentic cost protection, intelligent caching, and compliance-ready audit logging.

Official SDK ✅

pip install aisg — live on PyPI. Native Python client with typed metadata, structured errors, and model discovery.

Recursive Loop Protection ✅

Shipped. Detects and kills runaway agent loops before they drain your credits. 60s window, 30s cooldown.

Semantic Caching ✅

Shipped. Cache identical DLP-cleaned prompts. Cache hits eliminate the LLM call entirely — zero cost, zero latency. Backed by a low-latency distributed cache.

Webhook Notifications ✅

Shipped. HMAC-signed webhooks for PII blocks, prompt injection, redaction, budget alerts, and loop detection. Up to 5 per project.

EU AI Act Logging ✅

Shipped. Hash-chained, tamper-evident audit records with input/output fingerprints, JSONL export, and chain verification API. Ready for August 2026 enforcement.

  • ✅ Official Python SDK (pip install aisg) — shipped, live on PyPI
  • ✅ Recursive agent-loop detection and auto-kill before credits drain — shipped
  • ✅ Webhook notifications for DLP violations, prompt injection, budget alerts — shipped
  • ✅ EU AI Act compliance logging — hash-chained append-only audit trails with JSONL export — shipped
  • ✅ Semantic caching for DLP-cleaned prompts — 100% cost savings on cache hits, zero latency — shipped
Phase 2Building

Cost Intelligence & Advanced Detection

Cut AI Spend Without Sacrificing Security

Granular budget controls and next-generation prompt injection defense.

Multi-Provider Quotas

Set one budget across all providers. Get alerted at 50%, 80%, and 100% via Webhook or Slack.

ML Jailbreak Detection

Deep learning classifiers that catch attacks regex can’t — semantic similarity, encoding exploits, and novel patterns.

Policy-Based Routing

Automatically restrict to low-cost models when a project crosses a spending threshold.

  • Project-level spending quotas across all providers with threshold alerts
  • ML-based jailbreak classifiers beyond regex heuristics
  • Policy-based ‘Budget Mode’ routing to low-cost models when spending thresholds are crossed
Phase 3Next

Hybrid Deployment & Team Management

Run the AISG proxy entirely inside your own infrastructure while managing policies, budgets, and observability from the cloud dashboard. Built for regulated industries — healthcare, finance, defense, government — where prompt data must never leave your network.

The Best of Both Worlds

SaaS convenience meets on-prem data sovereignty. Manage everything from the cloud, but keep sensitive data processing inside your own firewall.

Cloud-Managed Policies

Create, version, and deploy DLP policies from the AISG dashboard to all proxy instances.

Self-Hosted Data Plane

The proxy runs inside your infrastructure. Prompts and responses never leave your network.

Zero Prompt Exposure

The cloud control plane never sees prompt content. Full separation of control and data planes.

Team Management

Role-based access, multi-seat enterprise accounts, and per-team policy assignment.

  • Hybrid Deployment — Cloud Dashboard + Self-Hosted Proxy
  • Deploy the proxy on your infrastructure — prompts never leave your network
  • Zero-trust: cloud control plane never sees prompt content
  • Response-side DLP scanning for streaming output
  • Large document processing with enterprise PII reporting
  • Team & organization management with role-based access
  • Centralized observability across cloud and self-hosted deployments
  • Docker and Kubernetes deployment support
Phase 4Vision

Agentic AI Governance

As enterprises move from chatbots to autonomous AI agents, governance shifts from static prompt filtering to real-time behavioral verification.

Governing Autonomous AI

When AI agents call tools, execute code, and make decisions autonomously — who’s watching?

Agentic Governance

Monitor and control multi-step agent workflows. Enforce policies on tool calls, not just prompts.

MCP Security Layer

Intercept and validate Model Context Protocol tool calls before they execute.

Human-in-the-Loop

API hooks to approve or deny high-risk agent actions in real time.

Behavioral Monitoring

Anomaly detection for agent behavior — catch loops, data exfiltration, and scope creep automatically.

  • Secure governance layer for RAG and agentic workflows
  • MCP security layer for tool-calling agents
  • Human-in-the-loop approval hooks for high-risk requests
  • Advanced behavioral monitoring and anomaly detection
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

Reduce redundant AI spend through semantic caching and smart routing on production workloads.

Quality Benchmarking

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

Get notified when new features launch:

Get 1,000,000 Free Credits

No credit card required · Start in 60 seconds