Blog

Guides, tutorials, and insights on AI coding tools and API providers.

· 9 min read

I Spent $3,600 Testing 7 Memory Strategies for AI Agents — Here's What Actually Works

Last year I almost bankrupted my team building a customer service agent. First week in production, our token costs were 3x the budget, and my boss's face was gr

Read more →
· 10 min read

I Configured Cursor Rules for a 200-File Project and My Team's Efficiency Doubled

Last Friday at 4:23 PM, I stared at the 47th Pull Request rejected for formatting issues and realized something painful — our team was spending enough time each

Read more →
· 7 min read

Your AI App Is Bleeding Money—Here's How I Cut Our API Bill by 48%

Last month, I did something that made my stomach drop: I actually audited our AI API costs. $17,800. That's what our customer support system burned through in a

Read more →
· 7 min read

I Let an AI Agent Loose on My Terminal — Here's What Happened After 3 Weeks

Last Tuesday at 3pm, I typed claude "refactor this 2000-line Python script" into my terminal and wandered off to make a pour-over. Before the coffee finished dr

Read more →
· 7 min read

I Compared 2025's Multimodal AI API Prices—Some Are 10x Cheaper Than Others

Last week, our team was building an image moderation pipeline and decided to benchmark a few multimodal large language models. We pulled the API pricing from ha

Read more →
· 8 min read

I Spent $5,400 on GPT-4 Last Month — Here's What I Should Have Used Instead

Last Wednesday, during our weekly retrospective, our tech lead threw a number on the screen that made the entire room go dead silent. $5,400. That was our API b

Read more →
· 8 min read

I Let GPT-5.1 Fix 236 Real GitHub Bugs — Here's What Actually Happened

Last Tuesday night, I was debugging a payment module concurrency issue. Two hours staring at logs. Nothing. You know what it was? A missing zero in the database

Read more →
· 7 min read

I Plugged AI Into My CI/CD Pipeline—Here's What 4 Months of Pain Taught Me

Last Wednesday afternoon, our intern Xiao Zhang submitted a PR. I glanced at it and—bloody hell—200 lines of code with three SQL injection risks, a hardcoded AP

Read more →
· 7 min read

When Your RAG System Lies to You—and You Almost Believe It

Last week, our team was building an internal knowledge-base Q&A system, and the accuracy was stuck at 73%. Properly stuck. My boss wandered over asking what was

Read more →
· 7 min read

I Let AI Edit 18 Files at Once and Nearly Deleted My Career

Last Tuesday, I told Cursor to refactor a logging library across my entire project. Eighteen files. One click. What could possibly go wrong? Everything. Nearly

Read more →
· 7 min read

I Tested GPT-5.1-Codex-Max on Real Algorithm Problems — Here's What It Actually Got Right (and Wrong

Last Wednesday, 3pm. I'm staring at our A100 server, fans screaming like a jet engine, GPU pinned at 99% utilisation. Four hours into training an image segmenta

Read more →
· 7 min read

I Audited a Friend's AI API Bill and Found £1,200 Going Up in Smoke — Here's How to Avoid the Same T

Last week I did a quick cost audit for a mate's startup. Three developers, one project, and a monthly bill of £1,200 for a large language model API. *Three peop

Read more →
← Previous 1 ... 14 15 16 17 18 ... 42 Next →