The governed execution layer
for AI agents.
Intent, policy, execution - Formael handles the three-phase lifecycle of every outbound agent action. One protocol, any external system, zero credential exposure.
Intake
Normalize semantic intent into a governed transaction
Governance
4-axis policy evaluation - every action, every time
Execution
Credential-safe adapter execution with full trace
Platform capabilities
Governance infrastructure
built for the agentic era.
Not middleware. Not a proxy. A complete execution boundary - with policy enforcement, connectivity, fiscal control, and dual-trace observability in one platform.
Four-Axis Policy Engine
Every intent evaluated across Identity, Semantic, Fiscal, and Risk axes before any action reaches an external system. All four must pass. There is no bypass path.
Dual-Trace Audit Ledger
Every IEC carries two linked traces: the agent's reasoning (why it acted) and the platform's execution record (what exactly happened). Append-only. Tamper-proof. Recoverable forever.
Provider-Agnostic Connectors
Agents express intent against semantic capability contracts - never provider APIs. Swap DocuSign for PandaDoc, Jira for Linear, without changing a single line of agent code.
Human-in-the-Loop Approvals
High-risk actions pause for human review without blocking the agent. The agent receives a deferred receipt and continues reasoning while a domain approver resolves the request.
Dual-Ledger Fiscal Control
Two independent ledgers - platform spend in USD and action value in any currency - checked synchronously on every IEC. Define limits per org, per agent, or per domain.
MCP-Native Protocol
Agents that speak MCP need zero Formael-specific code. Connect via the MCP server and every installed capability appears as a scoped tool - with risk metadata embedded in the description.
How it works
Intent in.
Authorized action out.
The Intent Execution Cycle is the atomic unit of the platform. Every agent action is one IEC - one intent evaluated, one outcome recorded, one immutable truth.
Intent Submission
The agent speaks intent. Never implementation.
The agent submits a structured IntentEnvelope - a three-part semantic tuple, typed parameters, and its own reasoning context. No credentials. No provider name. No API schema. The envelope has no field for secrets by design.
Intent Envelope
contracting·send·for-signature
“Finalize partnership agreement before Thursday's call”
Four-Axis Policy Evaluation
Governance happens here. Every time.
Before any action reaches an external system, the policy engine intercepts and evaluates it across four independent axes. Every axis must pass. The verdict is the conjunction - no axis compensates for another's failure. No exceptions. No fast paths.
Identity
Is this agent authorized for this capability in this context?
Semantic
What does this intent mean - and is that permitted?
Fiscal
Can the org and this agent afford the consequences?
Risk
If this goes wrong, how bad is it?
Authorized Execution
Approved. Executed. Permanently recorded.
Once approved, Formael resolves the organization's provider binding, injects credentials from the secure vault - exclusively, for this execution only - and executes against the external system. The result is normalized and written to the immutable ledger alongside the full dual trace.
Supported adapters
34+ connectors across 10 domains. Declarative YAML specs for ~90% of integrations.
Observability
Not just what happened.
Exactly why it was allowed.
Every IEC carries a dual trace - the agent's reasoning and the platform's execution record, linked by a single ID. Two questions answered together that no other tool can answer at all.
Policy axis summary · last 30 days
pass rate
pass rate
pass rate
HITL triggered
“When an agent acts, two questions matter: why did it want to do this, and what exactly did the platform do about it? Formael answers both - permanently, for every single execution.”
Formael · Dual-Trace Design Principle
Early Access
Build the AI agents
you actually want to ship.
Join the Formael early access program. Get the boundary infrastructure your agent fleet needs - governed execution, immutable audit, and 34+ connectors - before you need to build it yourself.
Your Agent
Semantic intent envelope
Formael
Govern · Execute · Trace
External APIs
DocuSign · Jira · Slack…