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.
The Line That Disappears at 100K: Measuring What Tool-Output Spill Actually Keeps
When agent tool output passes 100,000 characters, the full text spills to a file and the model sees only a head-truncated preview. Here are measured survival rates from a real repository, and the output envelope I built to push decision-relevant lines to the front.
Stabilizing Claude API Structured Responses in Production — Notes on tool_use, JSON Schema, and Layered Validation
Getting Claude to return JSON takes a few lines. Keeping that JSON usable in production is a different problem. Here is the layered design I landed on after running a wallpaper classification pipeline through Claude API, built around tool_use, JSON Schema, and domain validation.
Why tool_result could not be submitted Keeps Coming Back, and How to Build a Recovery Handler That Actually Holds
Run a Claude agent long enough and one day it starts: 'tool_result could not be submitted', back to back, and retries change nothing. The error message hides four completely different root causes. Here is what I learned debugging it on the always-on agent jobs I run as an indie developer, with the TypeScript recovery handler I now ship in production.
Shipping Generative UI on Claude API: A Production Pattern for Streaming Dynamic Components with Tool Use and JSON Schema
Combine Claude's Tool Use, JSON Schema, and partial JSON streaming to render AI-assembled UI components safely. We cover registry design, type-safety, fallback, and the pitfalls you only learn after running this in production.
Using tool_choice to Cut Wasted Inference: Four Modes and Cost Patterns for Production
tool_choice is one of the most underused parameters in the Claude API. The four modes — auto, any, tool, and none — each change both behavior and token cost. Here are the patterns I reach for in production, with runnable code.
Running Claude API Parallel Tool Use in Production — Controlling Concurrency, Designing for Partial Failure, and Cutting Latency
Claude API's parallel tool use can halve perceived latency, but partial failures and duplicate writes arrive just as fast. Concurrency control with asyncio.gather and a Semaphore, three partial-failure policies, idempotency, observability, and a way to measure your real parallel degree.
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.
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.
Generating localized App Store listing metadata within character limits using the Claude API
Raw translations overflow App Store Connect's character limits. Generate per-locale listing metadata within them using Claude API structured output and a repair loop.
Putting a Ceiling on the pause_turn Loop: Running Long Server Tools Safely Unattended
A production design for continuing pause_turn safely in unattended runs, where long server tools like web_search and code execution are involved. Covers branching all four stop_reason values in one loop, capping continuations and wall-clock time, and accumulating usage across paused segments.