exact.works
RepositoriesRegistryThe AgreementDevelopersTrust
Platform-Native Agent Observability

Oath

Behavioral observability for AI agents you don't control. Conformity scoring, pre-execute gates, and court-admissible evidence for agents running on Salesforce, OpenAI, Microsoft, and more.

Start ObservingIntegration Guide

The Problem

When you deploy AI agents on third-party platforms, you lose visibility. The agent runs in someone else's environment. You can't see what it's doing. You can't stop it from going rogue. You have no evidence if something goes wrong.

Behavioral Envelope

Define what your agent is authorized to do and what is prohibited. Oath scores every action against the envelope in real-time.

APEX-BG Scoring

Continuous conformity scoring from 0.0 to 1.0. Drift detection when behavior deviates from baseline. Violation alerts for prohibited actions.

Pre-Execute Gate

Block terminal actions before they execute. Hold destructive actions for human review. Allow read-only actions to proceed automatically.

Evidence Packages

Cryptographically signed evidence bundles for disputes. Court-admissible PDF reports with attestation statements and hash verification.

Pre-Execute Gate

Actions are classified by irreversibility. The gate enforces policy before execution, not after.

NONE

Read-only operations

get, list, search, query

Gate:ALLOW
RECOVERABLE

Can be undone

create, add, send

Gate:ALLOW
DESTRUCTIVE

Hard to undo

update, modify, delete (soft)

Gate:HOLD_FOR_HITL
TERMINAL

Cannot be undone

delete (hard), terminate, destroy

Gate:BLOCK

Platform Support

Oath integrates with major AI agent platforms via webhooks, polling, or native SDKs.

Salesforce AgentForce

Available

Native integration with AgentForce telemetry events

OpenAI Assistants

Available

Tool call and run status webhooks

Microsoft AGT

Available

Azure AI Services agent governance

Anthropic Claude

Available

MCP server integration for Claude agents

Custom Agents

Available

Any agent with webhook or polling support

Pricing

CORE

Deterministic APEX-BG scoring

$49/mo
  • Behavioral envelope definition
  • Real-time conformity scoring
  • Pre-execute gate for terminal actions
  • Telemetry ingestion (100 events/sec)
  • JSON evidence packages
  • $0.01 per observation
Get Started
MOST POPULAR

REVIEW

Local LLM conformity analysis

$149/mo
  • Everything in CORE
  • vLLM-powered observation analysis
  • Drift detection with reasoning
  • Enhanced telemetry (500 events/sec)
  • PDF evidence with attestation
  • $0.05 per observation
Get Started

DETERMINATION

Full dispute-grade evidence

$499/mo
  • Everything in REVIEW
  • Deep behavioral analysis
  • Expert determination support
  • Unlimited telemetry
  • Court-admissible evidence
  • $0.15 per observation
Get Started

Ready to observe?

Get visibility into your platform-native AI agents in minutes.

Start Free Trial