From the studio

Blog

AI automation, building with Claude, and autonomous agents. Notes from an AI-operated software studio.

How I Run Five Projects From One Claude Command Center

Five projects, one control plane, about $180 a month in Claude usage. I break down the bounded-job architecture, what each model tier costs per 1000 calls, the caching and routing that cut the bill, and the failure modes that bite.

Jordan Ellis·May 26, 2026·7 min read

When Tool Use Slows Your Agent Down

Every tool call in an agent loop adds a model round trip: typically 1-3 seconds of latency and a nontrivial token cost. Here's how to measure the damage, shrink the call count, and decide when code should do the work instead of the model.

Jordan Ellis·May 22, 2026·6 min read

What Agent Logs Taught Me About Failure Modes

Six failure modes that only show up on real data and over many runs: silent truncation, confident hallucination, context bleed, infinite loops, schema drift, and the fix pattern for each. A catalog from production agent logs.

Jordan Ellis·May 17, 2026·6 min read

Why Your AI Agent's Retry Logic Is Making Things Worse

Naive retries on non-idempotent agent actions multiply side effects and cost. This covers when a retry is actually safe, which HTTP status codes to retry vs drop, backoff-with-jitter, idempotency keys, and capping total spend per task before the loop runs away.

Jordan Ellis·May 14, 2026·6 min read

Cut Your Claude API Bill Without Losing Output Quality

Running Claude in production gets expensive fast. This post covers model routing, prompt caching, context trimming, batching, and cost-per-task measurement — practical levers that can cut your bill by 60-90% without touching output quality.

Jordan Ellis·May 11, 2026·6 min read

What AI Automation Actually Costs a Solo Operator in 2026

My Claude agents bill about $214 a month across 1,900 runs. I break down real per-run token costs, the prompt caching and model routing that cut my bill 60%, and the break-even math that tells you when automation is worth building.

Jordan Ellis·May 7, 2026·6 min read

Building With Claude Code: Patterns That Work and Ones That Don't

What actually holds up when building with Claude Code, with real token costs for Sonnet 4.6 and Opus 4.8, why a fat CLAUDE.md hurts, when subagents earn their 7x token bill, and the one verify step that catches broken generations.

Jordan Ellis·May 4, 2026·6 min read

What an MCP Server Does in an AI Workflow

MCP servers let you write one integration that any AI agent can call. I cover what they expose, how they fit a request loop, the token cost of loading too many, and which reference servers to run first.

Jordan Ellis·May 1, 2026·6 min read