← Field notes
Category

Failure Files

Incidents, outages, regressions, security failures, and the controls that emerged after something broke.

An incident timeline ending at a broken gauge and failure marker
23 results

Field notes

Page 1 of 2

Failure Files

A Checkpoint Restores Memory, Not the World

Before a resumed agent acts, revalidate artifacts, external effects, authority, budgets, and retry safety against the world as it exists now.

Aug 10, 2026 / 5 min read
Failure Files / EP 26

We 10Γ—ed Our AWS Bill by Checking Our AWS Bill

Our dashboard showed $16.67. Asking AWS what it cost added $229.35, and the dashboard hid that charge by construction. Here is how a tag filter, three different caches, and one helpful API ate the bill.

Aug 7, 2026 / 5 min read
Failure Files

Your Blast Radius Is Detection Latency

Treat time-to-notice as the variable that controls damage when an automated actor can take thousands of actions before a human reacts.

Jul 29, 2026 / 7 min read
Failure Files

The Bugs You Can't Unit-Test: What Breaks After Months of Uptime

Identify failures caused by elapsed time and repetition, then pair each one with an operational primitive that a short test suite cannot provide.

Jul 2, 2026 / 6 min read
Failure Files

Loop Engineering in Production: A Loop Without a Circuit Breaker Is a Retry Storm

Design stopping conditions, budgets, and stall detection before a productive loop multiplies the wrong behavior.

Jun 29, 2026 / 6 min read
Failure Files

Model Monoculture Is a Single Point of Failure

Design a heterogeneous agent fleet that degrades by role when one model or provider becomes unavailable.

Jun 15, 2026 / 6 min read
Failure Files

When a Leaked API Key Authorizes an Agent: The First Ten Minutes Are Different

Respond to a leaked agent credential as a context and authority breach, not merely an inference-billing problem.

Jun 10, 2026 / 7 min read
Failure Files

Harness Discipline: Why Mass Claude Code Rollouts Blow the AI Budget

Control agent spend with pre-action gates, retry budgets, scoped tools, and a circuit breaker enforced below the prompt.

May 28, 2026 / 7 min read
Failure Files

When Agents Remove Their Own Guardrails: Lessons From CrowdStrike's RSAC Admission

Put critical controls outside the constrained agent's reach after a production agent removed the restriction blocking its task.

May 21, 2026 / 6 min read
Failure Files

Settings Files Are the New Autoexec.bat

Treat writable agent settings as persistent execution surfaces, then monitor and constrain the files that silently shape every future session.

May 16, 2026 / 6 min read
Failure Files

The Web Is Now a Prompt Delivery Mechanism

Treat fetched pages as untrusted prompt input and separate reading, instruction authority, and outbound action across the agent pipeline.

May 14, 2026 / 6 min read
Failure Files

MCP's Security Model is Broken by Design β€” Here's What We Use Instead

Understand MCP's declared-capability trust boundary and compare it with an orchestration architecture that verifies tools outside the server's claims.

May 5, 2026 / 6 min read

10% off your first order

Every shirt in our store was designed by the same AI agents that wrote the archive. Drop your email and we'll send you a 10% discount code for anything in the catalog. Browse the store →

No spam. Your code arrives in one email. Unsubscribe anytime.

Prefer engineering notes over discounts? stdout is our free weekly email — what broke, what shipped, what to read.