Private beta · proof of execution

The platform

A good platform disappears. The work stays.

Underneath the app that answers on your WhatsApp runs a built multi-tenant platform — 39 engines across 10 layers, governed and verifiable by evidence. What the home page demonstrates, engineering delivers. This is the page that pops the hood: the substance, with the honest status of each part.

Proof by evidence, not by slidesReal status of every capabilityGovernance already in production

Stage honesty

We prove what exists — and say what doesn’t yet.

Every claim on this page carries a badge. That’s how you separate fact from bet without relying on our goodwill — proof, not promise.

Already in production Under construction Vision

Where we honestly stand right now: Next chapter: dogfooding — Fluxomind running its own sales operation inside the product, the living proof that the agent operates and evolves.

AI-first

AI is the execution flow — not a chatbot bolted on.

In traditional software, code calls the LLM when it needs to. Here it’s the inverse: an orchestrator receives the intent, consults memory and knowledge, plans and invokes tools — all governed by policy and visible as a state graph, auditable step by step.

Partial — multi-worker journey in hardening

Traditional software

  • Code defines a fixed path
  • Calls the LLM as an add-on
  • The response returns to the code

Fluxomind — AI-first

  • The orchestrator receives the intent
  • Consults memory + knowledge and plans
  • Invokes tools under policy, in a state graph
  • Every step governed and auditable

Multi-provider, no lock-in

Routing by cost/quality profile, automatic fallback across providers and cost measured per call.

Declarative composition

The agent composes existing primitives — it does not generate loose code. Execution is visible and reproducible.

Governed self-building

Extends the tenant’s model via governed tools (create-only), with the system’s base tables locked — dogfooding, not self-modification.

Architecture

39 engines, with machine-enforced boundaries.

All organized into 10 layers, verifiable in src/engine/. Every engine is an isolated module with strict boundaries — an improper import between internals is blocked by the boundary verifier, which runs on demand and in the deploy pipeline. Evolution by layer, no breaking changes.

Machine-verified, in the deploy pipeline
Core AI

the reasoning of the app

agentStudio · model · prompt · memory · rag
Tooling

the hands that act in the world

tool · mcp
Experience

the screens and the catalog

app · appStore · dataView · speech
Automation

what runs without you

workflow · code
Governance

the limits and the authority

security · policy · quota · auditTrail
Data

the memory of the business

atlas · data · metadata · cache · queue · file
Monitoring

the eyes on the operation

monitoring
CI/CD AIOps

the governed deploy

deployment · operations · validation
Ecosystem

the connections outward

api · plugin
Learning

the evolution over time

feedback · fineTune · eval · evolution

Flywheel + Atlas

Gets smarter the more it is used.

The platform doesn’t deliver value once — it spins. Two coupled loops over a single semantic brain: intent becomes an app, the app generates activity, the activity returns the next action — and each turn starts from a higher point.

Self-building loop

Intent becomes an app

You describe the intent; the platform creates object, fields and screens — with no engineering cycle in the way.

Insight loop

Operating returns the next action

Operating generates real data; the platform reads the activity and suggests the next step — more precise than the last. The full turn is what dogfooding proves.

Under construction
Atlas

The semantic brain

Classifies the business entities (embedding + LLM, aligned to Schema.org) — no manual ontology project.

Under construction

The thesis: the more you use it, the more Atlas knows — and the cheaper it gets to deliver the next thing. That’s what separates a flywheel product from a tool. The full turn is what dogfooding will prove.

Performance & scale

Designed for scale — observable and resilient.

The scale capabilities are in the architecture. Production numbers arrive with the pilots.

Partial — design capability

Observability and SLOs

Prometheus metrics, SLOs per tier, anomaly detection (z-score/IQR) and cost trace per execution.

trail: monitoringEngine

Asynchronous and resilient

Distributed queue with retries, backoff and DLQ; layered cache; connection pools and slow-query detection.

trail: queueEngine · cacheEngine · dataEngine

Continuity

Multi-region DR, auto-scaling and self-healing (designed), tier-based backup with RPO/RTO and distributed tracing (OpenTelemetry).

trail: operationsEngine
Honesty:“self-healing” and DR are design capabilities — still without measured scale numbers, because production is a brand-new platform. Load benchmarks come with the first pilots.

Quality & correctness

Correctness verified by machine, not by trust.

The principle is trust earned by evidence: the platform verifies itself by code — suites that prove isolation, integrity and contracts, not a checklist.

Implemented

Quality invariants, machine-verified

Isolation (cross-tenant probes + RLS via pgTAP), integrity, contracts, resilience, compliance and evolvability. Boundaries, tests and the eval gate run on demand and in the deploy pipeline; the isolation suite in a dedicated workflow.

trail: validationEngine

AI quality as a gate

LLM-as-Judge and property-based tests block regressions before a flow is promoted.

trail: evalEngine

Contracts and tests

API contracts (OpenAPI) and event contracts (AsyncAPI) verified; tests co-located with the code.

trail: validationEngine · co-located tests

Governance

Governance isn’t a feature — it’s the product.

Limits in the architecture, not in each app’s code: declarative policy the runtime enforces across the platform, with a person in the loop when it matters.

Partial — core implemented; self-service on the roadmap

Declarative policies + HITL

Versioned guardrails (checksum), evaluated with cache and explain; human approval (human-in-the-loop) on sensitive actions.

trail: policyEngine

Quotas and entitlements

Rate limiting, usage tracking and enforcement per tenant; atomic reservation and approved overrides.

trail: quotaEngine

Consent and audit

GDPR/LGPD consent lifecycle and an immutable hash-chain audit trail (see Security).

trail: securityEngine · auditTrailEngine

Security

Security and privacy in the foundation.

Strong multi-tenancy, encryption and masking — from day one, with nothing for the customer to configure. Enterprise-grade capability, delivered to people who aren’t technical.

Implemented

BYOK — the key is the customer’s

Bring your own KMS key (AWS/GCP/Azure). Crypto-shredding: revoke the key and the data becomes unreadable immediately — independently of the platform.

trail: securityEngine · spec-byok

Multi-tenant isolation

Dedicated schema per customer + RLS as backstop. The tenantId never comes from the payload — it derives from the request context.

trail: securityEngine · dataEngine

PII masking and content safety

Sensitive data masked (4 strategies) before reaching the LLM; guards against prompt-injection and jailbreak.

trail: securityEngine · spec-content-safety

Auth + hash-chain audit

Dual token + RBAC; SHA-256 append-only trail — tampering is cryptographically detectable and verifiable per tenant.

trail: securityEngine · auditTrailEngine · spec-hash-chain

Distribution & connections

Operates where the business already lives — and distributes the method.

The platform connects to what you already use and operates through the channel where the business already lives. The App Store engine exists in the Experience layer — the motor ready for the catalog of self-operating apps the vision describes.

Channels

First-class WhatsApp

Operation over WhatsApp at the platform level — a governed channel, not a personal number tied to one app. Voice and text on the same trail.

Under construction
Connectors

Integrates what you already have

Email, API, MCP and plugins — the app absorbs spreadsheets and systems and hands back a single, governed operation, without dropping your way of working.

Under construction
App Store engine

From method to catalog

Whoever masters a problem packages the method; your company installs it and adopts it already running. The engine exists; the public catalog is the vision.

Vision

Maturity & compliance

What is ready, honestly.

The platform has automated scanners for SOC2 controls (CC6/CC7/CC8) and GDPR (Art. 17/20/30/32) — verification by code, not a manual checklist. Today they run on demand; scheduled continuous execution is on the roadmap.

PillarWhat we already deliverStatusNext step
SecurityBYOK, PII masking, RBAC, hash-chain audit ImplementedBroad fail-closed + external pen-test
QualityQuality invariants, LLM-as-Judge, contracts ImplementedLoad coverage at scale
AI-firstGoverned multi-agent orchestration; multi-provider with fallback and measured cost PartialMulti-worker journey in hardening; more autonomy patterns
GovernancePolicies + HITL, quotas/entitlements, consent PartialBilling/payment + self-service governance panel
PerformanceSLOs, cost trace, multi-region DR, self-healing (design) PartialProduction scale numbers (post-pilot)
ComplianceAutomated SOC2/GDPR scanners (on demand) PartialContinuous execution + SOC2 Type II certification (external audit)
Transparency: the controls are already scanned by the platform, but the formal SOC2 certification (third-party audit) and the scale numbers are on the roadmap — we are a new platform. We prefer proving to promising.

The next step

Pop the hood with us.

The platform is in private beta. Join the list to operate with the team right alongside you — and, if you’re technical, ask for the data room (arch docs, specs, evidence) and an architecture session.

Team alongside you · no card to start · proof, not promise