Waxell blog cover: dark canvas with the title "Safe to retry? That's just a hint."

Agentic Architecture: Retry Safety Is a Hint, Not a Contract

Agentic Architecture: Retry Safety Is a Hint, Not a Contract

In MCP, whether a tool is safe to call twice is a hint the client must distrust. Waxell MCP Gateway decides it per call, before dispatch.

Logan Kelly

Waxell blog cover: Warp breach exposing AI agent trace logs through a third-party vendor

Warp Breach: The Attackers Came for the Agent Traces

Warp Breach: The Attackers Came for the Agent Traces

Warp says a vendor exploit exposed agent traces for up to roughly 1% of users. Why attackers want agent logs, and how payload-free audit design helps.

Logan Kelly

Waxell blog cover: dark panel reading "The deadline moved. The data didn't." under a PII / PRIVACY label.

AI Agent Log Retention Moved 16 Months — The PII in Your Traces Did Not

AI Agent Log Retention Moved 16 Months — The PII in Your Traces Did Not

The AI Act's six-month agent log duty now starts 2 December 2027. GDPR did not move, so what your trace store keeps is an architecture decision.

Logan Kelly

Waxell blog cover: DeepSeek V4.1 shutdown-resistance findings and external kill paths

DeepSeek Disabled a Shutdown Script in 39% of Tests. Your Kill Path Shouldn't Be a File the Agent Can Edit

DeepSeek Disabled a Shutdown Script in 39% of Tests. Your Kill Path Shouldn't Be a File the Agent Can Edit

DeepSeek V4.1 disabled its shutdown script in 39% of warned runs in new tests. Why kill paths belong in the execution environment, not the prompt.

Logan Kelly

Waxell blog cover: the run completed, nothing says it worked

AgentOps: What an Agent On-Call Rotation Can Actually See

AgentOps: What an Agent On-Call Rotation Can Actually See

Agent telemetry measures duration, tokens and tool calls. A run that completes and does the wrong thing still looks healthy.

Logan Kelly

Waxell blog cover: the token says who, something else says whether.

Agent Security: The Authorization Layer Drew Its Boundary, and the Decision Sits Outside It

Agent Security: The Authorization Layer Drew Its Boundary, and the Decision Sits Outside It

An OAuth agent-authorization draft moved policy, audit and budgets out of scope. What that leaves a deployer to build, and where the control belongs.

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 · ISO/IEC 27001:2022 certified · 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 · ISO/IEC 27001:2022 certified · 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 · ISO/IEC 27001:2022 certified · HIPAA (in progress)

Governed continuously in Vanta.

SOC 2 Compliant badge

© 2026 Waxell. All rights reserved.

Patent Pending.