Skip to main content
KVL GrowthOS is now live — automate your first pipeline in 15 minutes.Get started
Enterprise Grade

An AI runtime built for reliability

Every AI request runs against a real, multi-provider fallback chain — Anthropic Claude as the primary provider, with Groq, Google Gemini, and OpenRouter as automatic free-tier fallbacks. If one provider fails, the next is tried immediately, in the same request. Real token usage is tracked on every call. Here is how it actually works, described plainly.

Anthropic ClaudeGroqGoogle GeminiOpenRouter
Architecture

A real, priority-ordered provider chain

Four real providers, tried in this exact order on every request — not a wishlist of integrations we plan to add someday.

Anthropic Claude

Primary provider

Groq

Free-tier fallback

Google Gemini

Free-tier fallback

OpenRouter

Free-tier fallback

This is the real fallback order used on every request: if the primary provider fails, the next provider in the list is tried automatically, within the same request. These four are the only AI providers this runtime has — nothing else is wired in.

Request lifecycle

What actually happens on every AI request

From authentication to the response reaching you — the real sequence, in order.

  1. 1

    Authentication

    The request is authenticated before anything else runs.

  2. 2

    Validation

    Inputs are validated before being sent to any provider.

  3. 3

    Routing

    The fallback engine selects the next eligible provider in priority order.

  4. 4

    Execution

    The request runs against the selected provider.

  5. 5

    Response Validation

    Structured responses are checked against an expected schema, with one automatic repair attempt on a malformed response.

  6. 6

    Cost Tracking

    Real token usage from the provider's own response is recorded against the organization's AI credit balance.

  7. 7

    Client Response

    The result is returned to the caller.

Automatic failover

Real fallback, honestly described

No idealized health-monitoring pipeline — just a working mechanism, described as it actually runs.

Automatic fallback, not idealized health-monitoring

If a provider fails, the next provider in priority order is tried immediately — synchronously, within the same request, not via a separate background health-check process.

A provider that fails is skipped for 60 seconds afterward, so a request doesn't repeatedly retry a provider that's currently down — it becomes eligible again automatically once the cooldown passes. This is a real, working mechanism — a simple cooldown, not a formal multi-state circuit breaker.

Failure cooldown

A real cooldown, not a textbook circuit breaker

We describe what's actually built, not the idealized version of it.

A real cooldown mechanism — simpler than a formal circuit breaker

Each AI provider that fails is temporarily skipped for 60 seconds before being retried again. This prevents wasted time repeatedly calling a provider that just failed.

We're not going to claim a textbook closed/open/half-open state machine we haven't built. What's real: a per-provider cooldown timer, checked before every attempt. We're honest about the difference because we'd rather you trust what we say elsewhere on this page.

Queue management

7 real background queues

Every queue below is a working BullMQ worker in this codebase — not a mock.

Workflow ExecutionRuns Automation Builder workflows.
Configurable per workflow
SchedulerRecurring and scheduled jobs.
Configurable per job
Webhook DeliveryDelivers outbound webhooks.
Exponential backoff
RAG EmbeddingGenerates embeddings for the knowledge base.
3 attempts, exponential backoff
AI Fallback RetryDurable retry when every AI provider fails on a request.
5 attempts, exponential backoff
Company DiscoveryBackground company research jobs.
2 attempts, exponential backoff
Billing RecurringSubscription renewals, dunning, trial reminders.
3 attempts, exponential backoff

All 7 queues run as real BullMQ workers today, in the same process as the application. Failed-job review and manual retry is available for the Scheduler queue; the others report aggregate health (active/waiting/failed counts) but don't yet have a dedicated retry UI of their own.

Rate limits

Real limits, honestly described

No live quota dashboard — just the real limiting that's actually enforced today.

Real rate limiting on sensitive endpoints; provider quotas are respected, not internally dashboarded

Authentication and abuse-prone endpoints are protected by a real, Redis-backed distributed rate limiter. Free-tier AI providers each enforce their own request/token quotas — when one is hit, the fallback chain moves to the next provider automatically.

We don't yet expose a live 'quota remaining per provider' dashboard internally — that's on our roadmap, not built yet.

Worker infrastructure

Real workers, honestly scoped

Seven background workers run today — described as they actually run, not as they might scale.

7 real background workers, running today

Seven independent BullMQ workers process jobs concurrently, each with its own concurrency limit.

Today these run in-process alongside the application on a single instance. Kubernetes autoscaling manifests (2–10 replicas) and a PM2 cluster-mode config both exist in this codebase for a future multi-instance deployment — real files, but not what's actively running in production yet. We're not going to claim horizontal scaling that isn't live.

Reliability

Built to recover, not just built to run

Backups, a real disaster-recovery process, and incident tracking — described honestly, with an estimate instead of a guarantee where a guarantee wouldn't be true.

Automated Nightly Backups

A verified, SHA-256 checksummed database backup runs automatically every night — a real scheduled job, not a manual or occasional task.

A Documented Disaster-Recovery Runbook

A concrete, runnable runbook with real backup and restore commands, and an honestly-stated estimated recovery time — not a guaranteed SLA, and not a vague promise.

Real Incident Tracking

Incidents are logged, tracked to resolution, and reviewed — not handled ad hoc — with customer-facing incidents disclosed publicly on our status page.

Real historical uptime, publicly visible

Live health checks and incident history — not a marketing claim.

View real-time system status
AI security

Every AI request runs inside the same real controls

AI features don't get a separate, weaker security model — they run through the same code-verified controls as the rest of the platform.

Encrypted Secrets

Connected integration credentials and platform secrets are encrypted at rest with AES-256-GCM.

Request Validation

Every AI request's input is schema-validated before it's sent to a provider.

Hash-Chained Audit Logs

Sensitive actions are recorded in a tamper-evident audit trail.

Role-Based Access

AI features respect the same tenant-isolated, role-based permission model as the rest of the platform.

Rate Limiting

Sensitive endpoints are protected by a real, Redis-backed distributed rate limiter.

Tenant Data Isolation

Every AI operation is scoped to its own organization — no cross-tenant data access.

Cost tracking

Real cost tracking, honestly described

No public cost preview here — your real usage lives in your account once you're signed in.

Real, per-request token and cost tracking

Every AI call records real token usage from the provider's own response — not an estimate — against your organization's AI credit balance.

See your own usage in Billing → AI Credits once you're signed in.

Developer APIs

Build on top of the platform

Some developer surfaces are live today; others are on the roadmap and honestly labeled as such.

REST APIAvailable

A real, authenticated API for programmatic access.

API KeysAvailable

Create and revoke bearer API keys from your account settings.

Manage API keys →
WebhooksAvailable

Real outbound webhook delivery with automatic retry.

Streaming APIComing Soon

Token-by-token streaming responses.

SDKsComing Soon

Official client libraries.

API PlaygroundComing Soon

Interactive in-browser API explorer.

OpenAPI SpecificationComing Soon

A machine-readable API spec.

Coming soon

What isn't real yet

These aren't ready yet — we'd rather tell you honestly than fake it.

AI Health Dashboard

Coming soon

A live, per-provider latency and success-rate view is on our roadmap.

This isn't built yet — check back in a future release.

Live Observability & Tracing

Coming soon

Distributed tracing infrastructure exists in code but isn't turned on yet.

This isn't built yet — check back in a future release.

AI Response Caching

Coming soon

No response, prompt, or embedding cache exists yet — every request currently reaches a real provider.

This isn't built yet — check back in a future release.

Roadmap

What's next

None of this is built yet — it's where we're headed, told to you honestly instead of dressed up as already live.

  1. Per-Provider Health Dashboard

    Real-time latency and success-rate tracking, broken down by provider.

  2. AI Response Caching

    A caching layer for repeated prompts and embeddings, to cut cost and latency.

  3. Distributed Tracing

    Turning on the OpenTelemetry scaffolding already in the codebase for full request tracing.

  4. Multi-Instance Worker Scaling

    Activating the Kubernetes/PM2 configs already in the codebase for horizontal scaling.

  5. Full Dead-Letter-Queue Management

    Extending failed-job review and retry to all 7 background queues, not just one.

Put your growth engine on autopilot

Start qualifying, engaging, and converting pipeline with AI agents today. No credit card required, and your first workflow can be live in under fifteen minutes.