AI Engineering

Expert articles on building production AI systems, covering system design, architecture, observability, and real-world implementations.

AI Bytes

Practical insights for production AI systems

AI Engineering

Circuit breakers for LLM calls: stop cascading failures

How circuit breakers prevent LLM outages from cascading through your agent. The 3 states, the failure window, and the 50-line implementation.

AI Agents LLM Production AI+2 more

Read Article

11 min

AI Engineering

Context window management for production AI agents

How to manage context windows in production AI agents. The 4 strategies that keep long sessions bounded without losing critical context.

AI Agents LLM Production AI+2 more

Read Article

11 min

AI Engineering

Persistent memory for coding agents: cross-session context

How coding agents remember context across sessions. The memory store, the recall pattern, and the 3 kinds of memory every agent should keep.

AI Agents AI Engineering Architecture+2 more

Read Article

11 min

AI Engineering

Custom tools for coding agents: beyond the built-ins

How to design custom tools for coding agents that are not read, edit, or bash. The naming rules, the schema patterns, and the 3 custom tools that pay off.

AI Agents AI Engineering Tool Calling+2 more

Read Article

12 min

AI Engineering

ripgrep for coding agents: fast code search at scale

Why ripgrep is the right code search tool for coding agents. The speed, the flags, and the wrapper that turns rg into a safe agent tool.

AI Agents AI Engineering Tool Calling+2 more

Read Article

10 min

AI Engineering

Edit tool design: how coding agents modify files safely

How to design an edit tool a coding agent can use without wrecking files. The string-match rule, the dry-run pattern, and the 50-line safe edit function.

AI Agents AI Engineering Tool Calling+2 more

Read Article

11 min

AI Engineering

Designing modular tool integrations for coding agents

How to structure tool integrations so an agent stays clean as it grows. The registry pattern, schema-first design, and the 80-line dispatcher that scales.

AI Agents AI Engineering Tool Calling+2 more

Read Article

12 min

AI Engineering

bash tools for coding agents: safe shell execution

How coding agents run shell commands safely. The bash tool design, the denylist trap, and the sandbox that keeps rm -rf away from your home directory.

AI Agents AI Engineering Tool Calling+2 more

Read Article

11 min

AI Engineering