FOR THE AGENTIC ERA

AI agents can build. AuraBoot makes them safe to run.

Code-generating agents happily write straight to your database — no schema contract, no authorization boundary, no trail. AuraBoot is the runtime underneath: every write, from a person, an automation, or an agent, passes the same two gates and lands in one audit log.

TWO GATES, ONE PATH

Every write passes the same two gates

Verified mechanics, not aspirations — this is the exact behavior you can reproduce from the getting-started tutorial.

Gate 1 · The endpoint

All writes arrive at one endpoint, /api/meta/commands/execute. The endpoint itself requires meta.command.execute — a permission you grant per role. Deny by default: a role without the grant is refused before any business logic runs.

Gate 2 · The command

Past the endpoint, the command’s own declaration applies: its permissions, its input whitelist, its state guard. A value the command never agreed to accept is dropped — even when the API answers “success”.

A person clicking Save, an automation, a BPM node, an AI agent calling a tool: four identities, one path, the same two lines. There is no second way in — that is the design.

GOVERNED VS RAW

What a generated app does — with and without a runtime

Generated app, direct writesGenerated app, on AuraBoot
SchemaThe model guesses your tables; drift is discovered in productionDeclarations create and evolve the schema — columns follow the model file in Git
AuthorizationPrompt-level at best; any caller with network access writes anythingTwo hard gates per write: endpoint permission, then the command’s own role contract
InputWhatever the model emits is trustedDeclared whitelist per command — undeclared fields are silently dropped
StateNo guards; invalid transitions overwrite real dataState-machine guards and validation run inside the pipeline, per command
TraceConsole logs, if you wrapped themEvery accepted execution lands in the audit log — command, phase, duration, payload

Commands declare risk and intent

Commands carry machine-readable hints for agents: what the command does, which fields it accepts, its risk level, its idempotency. An agent does not have to infer intent from UI scraps — the contract is the declaration.

The audit trail is a property, not a feature

Every execution that gets past the gates is recorded — what the pipeline accepted, how far it got, how long it took. You did not turn it on, and you cannot turn it off for one caller and not another, because there is exactly one caller: the pipeline.

AI INSIDE THE SAME RUNTIME

Not a chat box bolted on the side

AuraBot

In-app copilot for natural-language queries, data operations and guided workflows.

Agent Control Plane

Orchestrate agents with skills, tools and memory (enterprise edition).

ChatBI

Ask questions in natural language; get charts and tables back.

RAG knowledge base

Upload PDFs, DOCX, MD, CSV — vector-indexed for retrieval.

Multi-LLM

OpenAI, Anthropic, Zhipu GLM, MiniMax through one provider interface.

Run the governed path yourself

Ten minutes, in the tutorial: add a field, watch the platform refuse an undeclared write, meet both gates, read the audit trail.