News & guides
Writing Database Migration Scripts With an LLM
How to use a model for schema and data migrations safely: supply both schemas, demand reversibility, verify with dry runs and row counts, and know what not to delegate.
· 9 min read
Zed Setup Guide: Wiring Up a Custom Model Endpoint
Point Zed's agent panel at any OpenAI-compatible endpoint — the JSON provider block, the model metadata you have to declare yourself, and how to verify it.
· 8 min read
Agent Cost Control: Patterns That Bound the Worst Case
Agent spend is not a per-call problem, it is a per-loop problem. Budgets, caching, tiering and circuit breakers that cap what a bad run can cost you.
· 9 min read
Agent Error Recovery: Patterns That Keep the Loop Alive
Errors are the normal case in an agent loop, not the exception. These are the recovery patterns that separate agents that finish from agents that spiral.
· 9 min read
Agent Memory: Managing Context Before It Manages You
Long agent sessions fail because context fills with noise. Here are the practical strategies for deciding what an agent should remember and what to drop.
· 8 min readAgent Observability: Tracing a Loop You Cannot Reproduce
Agent failures are rarely reproducible, so logs are not enough. What to record per step, how to span a tool loop, and which metrics predict a bad run.
· 9 min read
Agent Planning Strategies: From ReAct to Explicit Plans
Reactive loops drift on long tasks and rigid plans break on contact with reality. Here are the planning strategies that work, and how to choose between them.
· 10 min readAgent Sandboxing: Containers, gVisor and microVMs
An agent that runs code needs a blast radius, not trust. How containers, gVisor and microVMs differ, and the network and credential controls that matter.
· 9 min read
AI on a Student or Solo Developer Budget
You do not need a frontier model for most of what you do. A practical guide to getting real work done on AI when the budget is small and the meter is scary.
· 8 min read
AI vs AI Agent: What Actually Changes When You Add a Loop
A model answers. An agent decides, acts, and checks its work. The difference is a loop and a set of tools — here is exactly what that means in code.
· 8 min read
Aider Setup Guide: Any OpenAI-Compatible Endpoint
Configure Aider against a custom base URL — the openai/ prefix, .aider.conf.yml, model metadata for unknown models, and picking the right edit format.
· 8 min read
Automating Code Review With LLMs Without Drowning in Noise
Automated review fails on precision, not capability. How to budget comments, give the model the context a diff omits, and measure whether anyone is acting on the output.
· 9 min readReady to try it?
Every model behind one key. Start free and upgrade when it sticks.