Waxell blog cover: dark panel with the words "Authority travels. The record doesn't." under a MULTI-AGENT label.

Multi-Agent Governance: Delegation Is a Trust Boundary, and the Handoff Is Where It Goes Unrecorded

Multi-Agent Governance: Delegation Is a Trust Boundary, and the Handoff Is Where It Goes Unrecorded

In multi-agent systems, authority follows the handoff. NIST's agent-security docket drew 535 comments; the record to build for is the delegation chain.

Logan Kelly

Waxell blog cover: Datadog vs Waxell — where the policy decision runs

Datadog vs Waxell: Where the Policy Decision Runs

Datadog vs Waxell: Where the Policy Decision Runs

Datadog AI Guard evaluates agent actions inside your app process. Waxell's MCP Gateway decides on the wire, before any upstream sees the call.

Logan Kelly

Waxell blog cover: dark panel with the words "The agent can't audit itself." under a COMPLIANCE label.

AI Agent Compliance: Two Federal Bills Disagree on Everything Except Where the Record Lives

AI Agent Compliance: Two Federal Bills Disagree on Everything Except Where the Record Lives

S.5051 would count each affected user as a separate FTC violation. Both 2026 agent bills need a record the agent cannot write itself.

Logan Kelly

Waxell blog cover: OpenAI's 53-image leak and the case for independent AI agent audit trails

AI Agent Audit Trails: What OpenAI's 53-Image Leak Proves [2026]

AI Agent Audit Trails: What OpenAI's 53-Image Leak Proves [2026]

OpenAI agents posted 53 user images online; it can't say when or why. Why agent audit records must sit outside the agent's own control plane.

Logan Kelly

Waxell blog cover: AISI finds GPT-6 Astra ignored explicit scope instructions in simulations

GPT-6 Astra Supply-Chain Attacks Survived Explicit Scope Instructions in AISI's Simulations

GPT-6 Astra Supply-Chain Attacks Survived Explicit Scope Instructions in AISI's Simulations

AISI: GPT-6 Astra ran unsanctioned supply-chain attacks in 29.2% of simulations. Why agent scope needs a gate in the tool path, not a line in the prompt.

Logan Kelly

Waxell blog cover: AI agent runbook and on-call operations guide 2026

74 Agents, 5.39B Tokens: Why AI Agent Cost Control Misses the Delegation Tree

74 Agents, 5.39B Tokens: Why AI Agent Cost Control Misses the Delegation Tree

One Codex task spawned 74 subagents and 5.39B recorded tokens. Agent spend is set by the call tree at runtime; a monthly account budget misses it.

Logan Kelly

Waxell

Waxell provides observability and governance for AI agents in production. Bring your own framework.

Compliance — NIST AI RMF · EU AI Act · SOC 2 compliant · HIPAA (in progress)

Governed continuously in Vanta.

SOC 2 Compliant badge

© 2026 Waxell. All rights reserved.

Patent Pending.

Waxell

Waxell provides observability and governance for AI agents in production. Bring your own framework.

Compliance — NIST AI RMF · EU AI Act · SOC 2 compliant · HIPAA (in progress)

Governed continuously in Vanta.

SOC 2 Compliant badge

© 2026 Waxell. All rights reserved.

Patent Pending.

Waxell

Waxell provides observability and governance for AI agents in production. Bring your own framework.

Compliance — NIST AI RMF · EU AI Act · SOC 2 compliant · HIPAA (in progress)

Governed continuously in Vanta.

SOC 2 Compliant badge

© 2026 Waxell. All rights reserved.

Patent Pending.