Start free trial
Blog

Stories from the gateway

Guides

Building a PR Summariser Reviewers Do Not Skip

Most PR summary bots restate the diff and get ignored within a fortnight. What reviewers actually need, how to select the diff, and how to keep cost per PR predictable.

· 9 min read
Guides

Building a Prompt Library People Actually Reuse

Most prompt libraries become a graveyard of untested snippets. What makes one worth maintaining: ownership, discoverability, contracts and a deletion policy.

· 9 min read
Guides

Building an Incident Assistant On-Call Engineers Trust

· 10 min read
Guides

Building an LLM Code Review Bot People Do Not Mute

· 9 min read
AI Agents

Building an MCP Server: A Working One in an Afternoon

· 9 min read
Fundamentals

Byte-Pair Encoding Explained: How Tokenizers Are Built

· 9 min read
Guides

Calling an LLM API from Jenkins Without Leaking the Key

· 9 min read
Fundamentals

Chain of Thought: Why Thinking Out Loud Actually Helps

· 8 min read
Cost & Pricing

Chargeback Models for AI Spend That Teams Accept

· 11 min read
Models

Choosing a Model for Non-English Codebases

· 9 min read
Guides

Circuit Breakers for LLM APIs: Failing Fast on Purpose

· 9 min read
Cost & Pricing

Comparing Provider Pricing Models Without Getting Fooled

· 8 min read
Guides

Connection Pooling for LLM APIs: Sizing the Client Right

· 8 min read
Fundamentals

Constitutional AI: Alignment From Written Rules, Not Labels

· 9 min read

Ready to start?

Every model, one key. Start free and upgrade when you are ready.

Start free trialSee pricing