Platform

How BotAris governs what an agent may decide

One model of authority, enforced in every agent's action path, accounted for in one ledger.

Agent layer

Agent Platforms

copilots and orchestration frameworks

Custom Agents

in-house autonomous workflows

Embedded AI

agents inside SaaS applications

Non-registered Agents

undiscovered and unmanaged

proposed actions

Control plane

BotAris Authority Governance Control Plane

Authority Model

decision rights and constraints expressed as governed policy

Decision Authority Enforcement Point (DÆP)

runtime evaluation of each proposed action against delegated authority in the agent's action path

Governed Authority Knowledge Base

policies, decision taxonomies, authority templates, process constraints, escalation rules, approved control narratives

Accountability Ledger

tamper-evident record of decisions, delegations, and outcomes

Governance Console

oversight, management, administration

AllowConstrainEscalate to humanDeny

context and evidence

Enterprise fabric

Identity and IAM

IdP, PAM, IGA, non-human identity

Approvals and ITSM

human-in-the-loop escalation paths

SIEM and GRC

evidence for audit, risk, and compliance

The control plane

Five components. One definition of authority.

Authority Model

Decision rights and constraints expressed as governed policy. The source every evaluation is checked against.

Decision Authority Enforcement Point (DÆP)

Patent pending

Runtime evaluation of each proposed action against delegated authority, in the agent's action path. Deployed where your agents already run.

Governed Authority Knowledge Base

Policies, decision taxonomies, authority templates, process constraints, escalation rules, and approved control narratives, versioned and human-approved.

Accountability Ledger

A tamper-evident record of decisions, delegations, and outcomes. Built to answer who authorized an automated decision and on what basis.

Governance Console

Oversight, management, and administration for the people accountable for agent authority.

Every evaluated action resolves to one of four outcomes

Allow

The action is inside the agent's delegated authority. It proceeds, and the ledger records that it did.

Constrain

The action proceeds with limits applied, for example a reduced amount, a narrower scope, or added conditions. The ledger records the constraint and the reason.

Escalate to human

Patent pending

The action needs a human decision. It is routed to the named escalation path with the context attached, and the human's answer is recorded.

Deny

The action is outside authority. It does not proceed, and the ledger records the reason.

A new surface can start in event-only ledger mode, where BotAris records what the outcome would have been without blocking anything, then move to enforcement once the authority model is validated.

Enforcement

Six ways to put the enforcement point in the action path

Patent pending

Pattern	Where it sits
Decision Authority API	The agent or its framework calls BotAris before a consequential action. In-process, for agents you build.
AgentGate Enforcement	BotAris's own inline gateway for agent traffic. It terminates the agent's outbound connection, resolves the caller to its governed authority, evaluates the requested action against decision rights, constraint ceilings, and the delegation chain, then forwards, transforms, or rejects it. Enforcement is synchronous and in the path. Protocol-aware for MCP and common tool-calling patterns, so it evaluates the action, not just the destination.
API Gateway or Reverse Proxy	A required check at the API tier, or a proxy in front of an application that cannot be integrated. Governs by protected surface, whatever is calling.
Sidecar or Service Mesh Enforcement	Beside the agent in its pod or mesh, so the agent has no path to enterprise systems except through BotAris.
Tool Broker or MCP Gateway	Every tool call an agent makes passes through a broker that evaluates it first.
Event-Only Decision Ledger Mode	Observe and record every decision without enforcing. The starting point for a surface you have not governed before.

Every pattern evaluates against the same Authority Model and writes to the same Accountability Ledger. Use one or several. Where deeper integration is possible, prefer it; the proxy and broker patterns exist so that nothing falls outside governance because its caller could not be instrumented.

Where it sits

Actions are evaluated at the authority layer whether or not the agent is registered.

Accountability

Built to answer an auditor

Every allow, constrain, escalate, and deny produces a ledger entry. Entries are tamper-evident. Each one records the agent, the proposed action, the decision rights and constraints that applied, the outcome, and any human escalation or override. The ledger is a record of authority, not an action log: it answers who authorized this decision and on what basis.

Scope

What BotAris is not

Not an identity provider or access control system. It does not authenticate agents, manage secrets, or decide what an agent can reach. It works with your IdP, PAM, and IGA.
Not an inventory tool. It does not discover non-human identities across your estate. It governs the decisions of agents whose authority is modeled in it.
Not a runtime. It does not host or run your agents. It governs them wherever they run, on agent platforms, in custom code, or inside SaaS applications.

See the architecture on one of your own agents

We walk design partners through the control plane and map it to an agent they already run.

Request early access