Blog
Notes on running agents without losing track of the bill.
Observability
What an AI coding agent's request ledger should actually record
Every call your agent makes is a row. Most people log too little of it.
Local models
Auto-retrying to the cloud when your local model gives a weak answer
Local models save money until the day they quietly return garbage and nothing catches it.
Caching
How to actually raise your cache hit rate with a coding agent
Cache hits are a property of how your session is shaped, not a setting you turn on.
Cost
ccusage alternatives that show live spend, not just history
A log reader tells you what a run cost. Something in the request path can change what the next one costs.
Cost
Does Claude Code's context management actually save money
Compaction buys you a longer session. The money question is what it does to your prompt cache.
Cost
How much does Claude Code actually cost per day
Token math, a worked day, and the three numbers that decide what you actually pay.
Observability
Claude Code latency vs cost: is the fast model worth the extra spend
The answer depends on whether a human is sitting there waiting, and almost nothing else.
Cost
Claude Code Pro vs Max vs API billing: which is cheaper for you
Stop guessing at your tier. Measure what you actually spend, then pick.
Agents
Why Claude Code subagents multiply your cost so fast
Fan-out looks like parallelism. On the invoice it looks like running the same job several times over.
Cost
Tracking Codex CLI costs across projects
Codex writes enough to its session files to rebuild a cost report. Here is how to do it, and where that method quietly falls apart.
Cost
Cursor vs Claude Code: which one burns more tokens
One tool shows you the meter. The other one turns it off. Neither of those is the same as being cheap.
Caching
Deduplicating simultaneous identical LLM requests in an agent workflow
Your cache only helps after the first response lands. This is about the gap before that.
Caching
Does compressing your context break prefix caching savings
Shortening a prompt looks like a saving until you check what it did to your cache hit rate.
Caching
Exact-match vs semantic LLM caching: which one is safe for agents
One replays a byte-identical request. The other guesses that two requests mean the same thing. Only one of those is safe to leave on by default.
Privacy
Why more dev tools are dropping email/password for Google or GitHub sign-in
Fewer passwords to leak, fewer forms to abuse, and a login flow that already knows who a developer is.
Agents
Installing a local HTTPS proxy certificate on macOS for dev tools
The five-minute keychain step that every local proxy setup guide skips.
Privacy
How to keep proprietary code off cloud LLM servers entirely
Three ways to stop coding agents from shipping your source to someone else's GPU, and where each one actually breaks down.
Observability
Langfuse vs a local request ledger: do you need a hosted observability stack
Tracing platforms answer questions about a product you ship. A local ledger answers questions about the bill you pay.
Local models
Pointing your coding agent at LM Studio instead of the cloud
The server part takes five minutes. The part where the agent still finishes the task is the interesting one.
Local models
When is a local model good enough for coding, and when isn't it
Skip the leaderboard. Here is the actual test I use before a request goes to Ollama instead of a frontier model.
Local models
Best local models for coding on an M-series Mac in 2026
Memory bandwidth, prefill speed and tool-calling reliability decide this, and the answer is very different at 16GB than at 128GB.
Privacy
What you give up (and gain) using a macOS-only private beta dev tool
Platform lock-in is a real cost. So is pretending it isn't.
Agents
Model tiering: routing to a cheap model first, only escalating on failure
Most agent turns don't need your most expensive model. Route cheap first, promote on evidence of failure.
Cost
Running Claude Code, Codex, and Cursor together: what it costs
Three subscriptions, three terminals, zero combined view of where the money goes.
Privacy
Why a local-only proxy is different from a hosted AI gateway
The trust model changes when there is no server to trust.
Local models
Using Ollama with Claude Code and Cursor to cut cloud costs
Local models are good at a narrower slice of agent work than people claim. The trick is knowing which slice.
Agents
One proxy for Claude Code, Codex, and Cursor: is it worth setting up
The honest version: worth it once you run more than one agent, and only if the proxy is local.
Observability
Attributing AI agent spend to the process that actually made the call
The invoice tells you what model. It never tells you which terminal tab.
Caching
Prompt caching vs response caching: what actually saves money
One is a discount on a request that still happens. The other stops the request from happening at all.
Cost
How to reduce Claude Code token usage without losing context
The tactics that actually move the number, and the ones that quietly make things worse.
Local models
Can you run an AI coding agent fully offline
The honest answer, not the marketing one.
Caching
Why semantic caching breaks agent tool calls (and how to avoid it)
A vector similarity hit above your threshold is still a guess. Guesses inside a tool call chain corrupt the whole run.
Privacy
What actually happens to your code when you send it to a cloud LLM
The request path, the retention window, the training question, and the parts your agent sends without asking you.
Cost
How to set a hard spend limit on an AI coding agent
Dashboards tell you what you spent yesterday. A cap stops the bleeding today.
Caching
Setting a similarity floor so semantic cache never corrupts an agent run
The threshold number matters less than what you refuse to match at all.
Agents
How do you detect a weak LLM answer well enough to auto-retry it
Confidence scores lie. Here is what actually works.
Cost
Why AI coding agents burn through API credits so fast
It isn't one big prompt. It's hundreds of small ones, and almost nothing is watching them.
Cost
Why is Claude Code so expensive all of a sudden
Your usage did not change. Your token economics did.