Don't Hand Your Agent the Tool That Commits — Sorting Tools Into Advise, Prepare, and Commit
Before you wrap irreversible actions in an approval gate, decide which ones never belong in the tool list at all. A three-tier inventory, a rewritten tool definition, and a small script that flags commits hiding in your schema.
Same Output, Different Path — Guarding Agent Trajectories with Invariants
When the default model changes, your final output can stay correct while the path your agent takes quietly shifts. Here is a trajectory regression harness built on recorded tool traces and deterministic invariants, with working code and measured numbers.
When Context Editing Made My Agent Re-run the Same Search — Field Notes on Clear Boundaries and Cache Invalidation
After turning on Context Editing to auto-clear tool results, the agent forgot what it had just read, re-ran the same tool, and the cache rebuilt every turn so costs went up. Field notes on instrumenting the silent regression and setting trigger, keep, and clear_at_least from measured data.
The Day a Non-Responding MCP Call Swallowed an Entire Unattended Run — Owning the Stop With Your Own Deadline
When a remote MCP tool call stops responding, an unattended scheduled run just keeps waiting. Instead of leaving the cutoff entirely to the platform, here is how I designed my own deadline and a per-connector circuit breaker to own the stop — with working code.
Routing the effort Parameter Per Stage to Balance Claude's Output Cost and Latency
Claude's effort parameter governs all output tokens — thinking, prose, and tool calls. This guide replaces a blanket high setting with per-stage tiers and a dynamic router, grounded in measurements from a solo developer's automation pipeline.
When Your Claude × Playwright Browser Agent Fails While Reporting Success — Verifying Actions and Catching UI Drift
A vision-driven Claude + Playwright browser agent fails quietly: it reports success while nothing actually changed. Here is how to stop trusting self-reports, verify each action against the goal, and detect UI drift before it breaks you.
Building an Autonomous Research Agent with Claude API: Web Search, Summarization, and Knowledge Management
A complete guide to designing and implementing an autonomous research agent using Claude API and web search tools. Covers budget control, quality assurance, and knowledge base storage for production use.
Building a 'Think-and-Search' AI Agent — Claude API Extended Thinking × Tool Use
A deep dive into combining Claude API Extended Thinking and Tool Use. Covers frequent errors, a complete research agent implementation in Python, plus cost estimation, timeout design, and error recovery for production use.
Inserting Approval Gates Into Your Agents — A Production Design for Human-in-the-Loop With the Claude API
Once you put an agent in production, the requirement 'please get a human to approve just this specific decision' appears within days. This guide walks through the design patterns for retrofitting approval gates and handling suspend/resume correctly, with working code.
Building a Custom Autonomous Agent Loop with Claude Code SDK — Beyond the CLI
Understand the internals of the Claude Code SDK and build custom autonomous agent loops in Python and TypeScript. Covers tool permissions, error recovery, and streaming, plus the cost instrumentation and monthly model audits I rely on in real operation.
Claude Managed Agents: Anthropic's New Agent Infrastructure (April 2026)
Anthropic launched Claude Managed Agents in public beta on April 8, 2026. This guide covers everything: sandboxed execution, authentication, checkpoints, scoped permissions, pricing, and how to get started building production-ready AI agents 10x faster.
Building a Persistent Memory Agent with Claude API, pgvector, and Redis: A Complete
A complete guide to building production-ready persistent memory for Claude API agents using PostgreSQL + pgvector + Redis. Learn vector search, layered memory architecture, session management, and GDPR-compliant data handling.