Posts tagged "Best Practices"
8 posts
Claude Code Token Costs: Why So High and How to Cap Them
Why Claude Code burns so many tokens — context re-sends, subagents, test loops — and the levers that cut the bill: model mix, short sessions, a maxSpend cap.
LLM API 429 Errors: The Three Causes and How to Fix Each
HTTP 429 from an LLM API hides three failures: upstream rate limits, per-key caps you configured, and exhausted quota. How to tell them apart and fix each.
Track LLM API Costs: One API Key per App, Agent, Environment
LLM cost attribution on a gateway ledger: one API key per app or agent, weekly per-key review, and spend caps that stop runaway loops.
LLM Fallback Strategies: Production Failover That Holds
LLM fallback strategies: what triggers fallback, provider vs model changes, how to read the final request outcome, and how request_id aids incident review.
Reselling LLM API Access Safely with Spend-Capped Keys
Resell LLM API access safely on a managed upstream: one key per customer, per-key spend caps and rate limits, and per-request usage data for billing.
Multi-Agent Orchestration: Patterns for Production AI Systems
Sequential, parallel, hierarchical and human-in-the-loop multi-agent patterns — when to use each, how to handle failures, and how to control cost and latency.
Claude Skills Explained: Building Custom Agent Capabilities
Claude Skills explained: how agents pick up capabilities on demand, how to write your first skill, and how to ship skills safely in production.
AI Agents in Production: Observability, Cost Caps, Recovery
Learn how to run AI agents safely in production with observability traces, budget guardrails, and automatic fault recovery. Practical patterns and code.