Blog
Practical articles for creators and small service teams on choosing, setting up, and checking AI tools.
GPT-6 Sol in Codex: budget credits and reviewer time together
A Codex credit rate is not a per-task bill. Compare Sol and Luna on accepted work, retries, review time and actual account usage.
Claude Opus 5.5 pricing: calculate the whole agent run
Opus 5.5 has lower API token rates than Opus 5. Here is how to count cache use, retries and accepted work before predicting an agent's real cost.
GPT-5.5 retires from Codex on October 14: check these model settings
Before the GPT-5.5 Codex retirement, find saved model selections in defaults, agents, scheduled tasks and scripts, then test an available replacement.
Ten cases to test before an AI client-intake workflow goes live
Download ten synthetic intake cases and a pilot log. Rehearse duplicates, missing details, old prices and human handoffs before an AI workflow goes live.
Claude Opus 5.5: what to check before switching a production agent
Opus 5.5 changes more than the model ID. Check thinking, tool choice, fallback conversations and computer use before moving an agent to production.
Opus 5.5 or GPT-6 Sol for a coding agent? Run a pilot that can change your mind
A head-to-head coding-agent pilot should measure accepted changes, recovery, review time and actual cost under comparable task conditions.
GPT-6 Sol or Luna in Codex? Choose by the work you need checked
Sol and Luna serve different jobs. Here is a practical way to route complex coding and focused repeatable work while measuring review time and retries.
Make or n8n for client intake? Choose the recovery path first
For a client intake handoff, compare Make and n8n by who notices a failed run, how the team repairs it and whether a retry creates a duplicate task.
Run an AI workflow pilot that can end with a decision
A useful AI pilot has a baseline, an owner, explicit review and stop rules, and a decision date. This guide shows a small team what to record before expanding a workflow.
Choose a first AI workflow by counting the work around it
Before comparing AI tools, count the source preparation, review, handoff and recovery work around the demo. A five-question worksheet helps a small team choose a bounded first workflow.
Audit the sources before you share an AI notebook
A shared AI notebook can help a team explain a new service, prepare a proposal or hand over background research. It can also expose more material than the sender meant to show. Check the source list before sharing the link, not after a recipient asks a question about a document they were never meant to receive.
Control source changes before asking AI for a customer-facing brief
An AI brief can drift out of date even when the original prompt was careful. A small service business changes its cancellation policy, service area or package terms, while an old PDF or copied paragraph remains in the workspace. The next draft may sound clear and still promise the wrong thing.