Platform
Platform features
BRAIAN by ÆTERION ships its capabilities in eight families: process execution, agent architecture, policy and governance, audit and observability, knowledge and conversation, integration, environments and security. Every capability below states what it does and whether it is available or in development, with a link to the page that documents it in depth.
Process execution
Read moreHow a business process is defined, run and completed inside the runtime.
Declarative process definitions
AvailableSteps, owners and conditions are configuration, readable by the people who own the process.
Versioned process runs
AvailableA running process keeps the version it started on; new runs use the new version.
Human approval steps
AvailableThe approver sees the step, its inputs, the proposed action and the governing policy, and can approve, amend or reject.
Retries and escalation
AvailableThe runtime retries a failed step and escalates to a person when confidence or policy requires it.
Agent architecture
Read moreHow agents are organised, authorised and kept attributable.
Domain agents
AvailableSpecialised agents cover eight business domains, from finance and legal to supply chain and procurement.
Step-scoped permissions
AvailableAn agent inherits only the permissions of the step it runs, for the duration of that step.
Pinned model and prompt versions
AvailableModel, prompt and policy versions are pinned and recorded, so every behaviour change is attributable.
Model provider choice
AvailableModel usage runs through the platform gateway or through your own provider contract, billed at cost.
Policy and governance
Read moreHow rules are written, versioned and enforced at runtime.
Policies as versioned configuration
AvailablePolicies carry authorship and history; you can diff two versions, promote one to production and roll back a change without touching process code.
Scoped policies
AvailablePolicies are scoped, so business units, regions or subsidiaries hold different limits under one platform.
Evaluation and release gates
AvailableA change reaches production only when the test suite passes the thresholds you set, compared version against version.
Incident-to-test capture
AvailableA wrong output in production is promoted into the test suite with one action, together with its inputs.
Audit and observability
Read moreWhat is recorded for every run, and who can read it.
Append-only run trace
AvailableInputs, outputs, cost, model version and approvals of every run are written to an immutable trace.
Cost attribution
AvailableCost is attributed per process, per team and per model, so budget reviews use measured numbers.
Policy-driven retention
AvailableTrace retention is a policy setting, aligned to your records-management rules.
SIEM and warehouse export
AvailableTraces export to your SIEM or data warehouse for long-term analysis.
Governed trace access
AvailableWho may read traces, and which fields they see, is decided by the control plane.
Knowledge and conversation
Read moreHow people query running processes and organisational knowledge through Carol.
Carol, the conversational layer
AvailableAsk a running process a question by voice or text, under the same permissions you hold in the console.
Permission-aware retrieval
AvailableAnswers are retrieved under the asker's permissions, so a question never reveals data the person cannot already see.
English, Italian and German
AvailableCarol answers in English, Italian and German, including mixed-language questions about the same process.
Microsoft Teams and Slack
AvailableCarol works in Microsoft Teams and Slack through the existing connectors, not only in the console.
Conversation context
AvailableA conversation keeps the process it is about, so follow-up questions do not need to repeat identifiers.
Integration
Read moreHow the platform reads and writes in your existing systems.
Connector catalogue
AvailableConnectors for 16 enterprise systems cover ERP, CRM, collaboration and document platforms.
Custom connectors
AvailableCustom connectors are built under the Scale plan for systems outside the catalogue.
Credential isolation
AvailableConnector credentials are held in the control plane and never exposed to agent prompts or process definitions.
Additional connectors
In development[DA COMPILARE]
Environments
Read moreHow development, staging and production stay separated, and where the platform runs.
Separate environments
AvailableDevelopment, staging and production hold separate credentials and separate limits.
Explicit promotion
AvailableMoving a policy or process version from staging to production is an explicit, recorded step.
Swiss or EU hosting
AvailableManaged hosting runs in Switzerland or the European Union, with data-residency options on enterprise plans.
Deployment in your own cloud
AvailableEnterprise plans deploy the platform into your own tenancy, under your operating responsibilities.
Security
Read moreControls against the risks specific to AI systems in production.
Prompt-injection isolation
AvailableUntrusted content is isolated from instruction context, and tool access is authorised by policy rather than by model output.
Redaction before egress
AvailableRedaction rules run before any request leaves the environment.
Model routing can be restricted by jurisdiction, so data stays within the legal regions you allow.
SSO and role mapping
AvailableUsers and service accounts authenticate through your identity provider; roles map to policy, not to individual scripts.