Writing
Short pieces on terminal agents, choosing models and keeping token spending sensible.
- Embeddings Endpoints: When and How to Use Them
- Logging Model Requests Responsibly, Step by Step
- How to Rotate API Keys Without Downtime
- Keeping API Keys Safe Inside a Team
- Concurrency Limits and Request Queues: A Walkthrough
- Timeouts for Long Streaming Requests: A Walkthrough
- How to Call a Language Model API with curl
- Setting baseURL in the OpenAI Node SDK
- Counting Tokens Before You Send: A Practical Guide
- Function Calling Basics: A Step-by-Step Guide
- Retries With Backoff That Never Double-Charge
- What HTTP 402 Means on a Prepaid API
- What a 401 Error Is Telling You
- How to Handle 429 Rate Limit Responses Gracefully
- Gemini generateContent Explained, Step by Step
- Server-Sent Events: Stream Responses Step by Step
- Anthropic Messages API: A Beginner’s Walkthrough
- Prepaid Credit, Balances and Refunds Explained
- When a Bigger Model Is Actually Cheaper
- Cheap Drafts First, Expensive Polish Last
- Cost per Merged Pull Request: A Practical Guide
- Budget Planning for a Small Team Using AI
- The Hidden Cost of Very Long AI Conversations
- Streaming and Cost: What Changes and What Does Not
- Batching API Requests to Cut Overhead
- A Spending Ceiling for Every Project Key
- Quota Passes: The Official-Price Ratio, Step by Step
- Stop Runaway API Loops Before They Run Up a Bill
- Cheaper Models for Background Jobs: A Walkthrough
- Trim Prompts Without Losing Quality: A Practical Guide
- Keep Your Coding Agent Within a Daily Budget
- Claude Cache Reads vs Writes: A Practical Walkthrough
- Pay-as-You-Go vs. a Monthly Pass: A Practical Guide
- When a Quota Pass Makes Sense
- Estimate Monthly API Spend from One Week of Usage
- Opus and Sonnet on the Same Refactor
- One Model per Task: A Practical Routing Walkthrough
- MiniMax M3 for Lightweight Assistants: A Walkthrough
- Qwen Models for Multilingual Products: A Walkthrough
- Grok 4.7 for Open-Ended Questions: A Practical Guide
- GLM-5.3 for Bilingual Teams: A Practical Walkthrough
- Kimi K3: A Practical Guide to Very Long Context
- DeepSeek V4: Budget Reasoning with Vana API
- Gemini Flash Models for Quick Drafts
- GPT-6.1 Sol for Steady General Work
- Gemini 3.1 Pro: A Long-Document Walkthrough
- GPT-5.6 Sol in Coding Workflows: A Practical Guide
- GPT-6 Astra: A Walkthrough for Hard Reasoning Tasks
- Claude Sonnet 5.5 as Your Everyday Default
- Claude Haiku 4.5 for Fast, Small Jobs
- Claude Opus 5.5: When Deeper Work Pays Off
- How to Measure Coding Agent Cost per Task
- Several Repositories, One Coding Agent Setup
- Coding Agents on Windows, macOS and Linux
- Keep Secrets Out of Coding Agent Context
- Claude Code Slash Commands Worth Knowing
- Pair Programming With an Agent Without Losing the Thread
- Coding Agents in CI Pipelines: What to Allow
- Let a Coding Agent Read Logs Safely
- Planning Mode vs Doing Mode in Coding Agents