Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: tool-use
Moving to Claude Opus 5.5: Five Breaking Changes Behind the Model ID
A ship-gate for switching to claude-opus-5-5: always-on thinking, forced tool_choice, model-bound thinking blocks, computer-use tools and a silent progress stream.
10 min readTool Calling Explained: How Models Ask Software to Act, and Where It Breaks
A practical tour of function calling and tool use: the request loop, schemas, read versus action tools, agents, MCP, prompt injection, tracing and common failures.
16 min readClaude tool_use End to End: The Agentic Loop in Three Iterations
Claude tool_use end to end: one Messages API request through the agentic loop, with tool definitions, tool_choice, parallel calls and tool_result rules.
19 min readHandling Limited Context Windows in AI Agents: 7 Practical Strategies
Seven proven ways to keep long-running AI agents inside their context window: compression, pruning, tool offloading, system prompts, handles, condensed output and sliding windows.
5 min readPractical notes: MTG Bench: Why Testing LLMs on Magic: The Gathering is a
Operable walkthrough of Practical notes: MTG Bench: Why Testing LLMs on Magic: The Gathering is a: contracts, checks, and drop-in code slots for teams shipping this pattern.
11 min readGuidance tools make agentic RAG take three steps instead of one flashy call
Salience summaries, clause diffs, and counting verification stay inert until a callable guidance tool, tool search, and incomplete returns teach the model the sequence.
28 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.