← Field notes
Complete archive

Browse all field notes

Search and filter the complete Ultrathink archive by category, series, title, and topic.

91 results

Field notes

Page 4 of 8

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
Agent Systems

Agent Observability Without Intervention: Why Dashboards Aren't Enough

Learn why seeing an agent's output is not enough, and which control points turn telemetry into the ability to stop bad work.

May 12, 2026 / 6 min read
Agent Systems

Pruning Stale Beliefs: When Agent Memory Becomes a Liability

Invalidate stored beliefs with time, contradiction, and outcome triggers before an agent applies outdated memory with confidence.

May 11, 2026 / 6 min read
Open Source Lab

We Run AI Marketing Agents. Here's What We Extracted Into a Free Tool.

See how a production marketing workflow became a reusable launch-strategy tool without pretending execution can be reduced to generic copy generation.

May 7, 2026 / 5 min read
The AI Business

We Let 10 AI Agents Run Our Startup for 90 Days β€” Here's the P&L

Review the architecture and operating rules that survived the first ninety days of running the company through a multi-agent system.

May 6, 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
Open Source Lab

The Ultrathink Agent Suite: 5 Open-Source Tools We Built to Run a Store with AI

Explore five reusable tools extracted from the production fleet and the failure each package is designed to prevent.

May 4, 2026 / 5 min read
Failure Files

How Our 24/7 Agent Pipeline Survived Three Silent Model Regressions

Detect silent model-quality changes with asymmetric tool checks and artifact verification instead of trusting unchanged model names or success reports.

Apr 30, 2026 / 6 min read
Build Log

Stripe Webhooks in Rails: The Gotchas Nobody Warns You About

Make checkout completion idempotent across webhook and frontend races while preserving signature verification and a reliable payment state machine.

Apr 29, 2026 / 5 min read
Agent Systems

Contract Tests for AI Agents: Testing Boundaries, Not Internals

Test deterministic tool and artifact boundaries around nondeterministic agents instead of pretending the model's internal behavior can be unit-tested.

Apr 28, 2026 / 6 min read
Agent Systems

The Missing Service Layer: What Agent Frameworks Don't Give You

Add the handoff, failure-propagation, and cross-session state layer that agent frameworks leave between spawning and actual operations.

Apr 27, 2026 / 5 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.