Rolling Out Agent Behavior Changes Gradually with Feature Flags
When an unattended agent changes its prompt or behavior all at once, quiet regressions hide until morning. Here is a design for assigning new behavior to only a fraction of runs, keeping a control group, and adding deterministic bucketing, canary comparison, and automatic rollback.
Don't Accept an Agent's Numbers and Citations As-Is — A Verification Gate Built on a Dedicated Auditor Subagent
A design that verifies every number and citation in an agent-generated summary using a separate subagent before accepting it — with working TypeScript for deterministic recomputation and fail-closed source matching.
Every Tool Call Succeeds, Yet Nothing Moves Forward: Detecting Stagnation in Unattended Agents
No errors, yet the agent keeps replaying the same move while your budget quietly drains. Here is how to detect a success-but-no-progress loop using a progress oracle and action fingerprints, with a working Python implementation that halts safely.
When the Previous Run Hasn't Finished and the Next One Starts: Leases and Fencing Tokens for Scheduled Agents
A scheduled agent that runs on a fixed clock can overtake itself and start twice. From the moment a naive lock breaks to leases, fencing tokens, and bounded catch-up — worked through with the implementation I actually run.
An Unattended Agent That Wakes Up to a Blank Machine Every Time
A scheduled, unattended agent wakes up on a fresh disposable machine every run: paths it cannot write to, a filesystem that has not finished booting, a working directory that has vanished. Here is how to design state recovery into the first thirty seconds, drawn from real operational logs.
Reallocating My Automation Pipeline Ahead of the June 15 Billing Change
On June 15, the Agent SDK, headless Claude Code, and GitHub Actions move to monthly usage credits. I audited every stage of my publishing pipeline against measured token logs and rerouted each one across three execution paths. Here is the reasoning.
Guard Your Agent's Destructive Operations with Pre- and Post-condition Contracts
A design for wrapping an autonomous agent's writes in deterministic pre- and post-condition checks. A contract gate stops the destructive operations that better prompts can never reliably prevent.
Make Agent Failures Reproducible: Deterministic Replay and Event Sourcing
An autonomous agent that fails at 2 a.m. can't be reproduced by simply running it again. Record every nondeterminism boundary as an append-only event log and replay the failed run deterministically — with working code and operational lessons.
A Morning Digest Agent across App Store Connect, Play Console, Crashlytics, and AdMob — 30 days of running it on Claude Agent SDK
Opening four dashboards each morning across six apps used to eat 30 to 50 minutes of my day. Here is the Claude Agent SDK recipe that compressed it into one email, with the measured numbers from a full month.
Resolving Tool Name Collisions When Bundling Multiple MCP Servers in the Claude Agent SDK
When the GitHub MCP and Linear MCP both expose create_issue, Sonnet 4.6 cannot tell them apart. This article walks through the structure of MCP tool name collisions, a TypeScript reconciler implementation, and the production failure modes I hit running six sites at once.
Giving Claude Agents Long-Term Memory in Production — Seven Pitfalls and the Patterns That Fix Them
A production playbook for Claude agents with long-term memory — seven pitfalls that break memory agents live, and the design patterns that fix each one.
Building Fault-Tolerant Long-Running AI Workflows with Claude Agent SDK × Temporal.io — A Production Design Guide to Durable Execution and Saga Patterns
A complete production guide to combining Claude Agent SDK with Temporal.io to build AI workflows that survive crashes, restarts, and multi-day human approval gates. Durable Execution, retry policies, saga compensation, and signal integration patterns.