The work moved from phrasing the ask well to writing down the procedure once, in a file.
The model stopped being the variable. Your briefing became the variable.
You stop re-explaining the same background every morning.
You review a decision instead of rewriting a draft's voice.
Two staff members asking the same thing get the same answer.
Think grant reports, donor thank-yous, board memos, and program updates.
Judgment, the final sign-off, and the disclosure.
The draft arrives done. The decision is still a person's.
Nothing here signs a grant report for you.
"Consistent, on-brand AI output does not come from better prompts; it comes from writing your standard down in a file the model reads every time, which is what turns a chatbot into a junior employee who drafts while you decide."
Why your instinct to open a chat window caps what you get
Phrase the ask well. Output changes when the phrasing changes, so nothing is repeatable.
Curate what the model sees. The material you give it matters more than the wording you use.
Write the procedure down once, in a file, and reuse it. The harness is what the AI can reach.
Define a goal and a check, then let it iterate until it passes the check.
The next step past loops: many loops wired into a dependency map, so work routes itself from one to the next without a person moving it.
The three layers underneath, the three doors in, and how a prompt becomes an agent
The written procedure for one recurring job at your organisation. It reads your brand files to apply the standard: your voice, your rules, your approved examples.
Your files and folders, plus Google Drive, Microsoft 365, and Slack, plus the ability to run several steps and check its own work before handing anything back.
The raw reasoning ability. The same for everyone who pays for it; a better prompt does not change it.
| What it is | What it can touch | Who it is for | What you get back | Where it breaks | |
|---|---|---|---|---|---|
| Claude (chat app) |
A conversation window | Only what you paste into it | Anyone, thinking out loud | An answer you copy elsewhere | Nothing persists, so you re-brief it every time |
| Claude Cowork |
Claude doing the work in your files, on desktop or web | Local files and folders, plus Microsoft 365, Google Drive, Slack and Amplitude1 | Staff who do recurring work, no coding required | A finished draft in the right place, with every step it took shown to you; can run on a daily, weekly or monthly schedule | It needs the standard written down first, or it guesses |
| Claude Code | An agent that runs in a terminal | A code repository | Engineers | Working software | The wrong door for programme staff |
A one-off ask, typed fresh. Useful, and it varies every time.
That same ask written down as a procedure in a file, with your voice rules and one example of good. Now the output repeats.
Intake, then draft, then check against the rules, then package for review. Each step is a small skill; the chain is the workflow.
A trigger plus a goal runs the whole chain without you starting it.
The engine, the refiner, and the three hard edges
Markdown is a text file with headings in it. That is the entire technology underneath everything on this slide. If you can write a Word document, you can write the thing that makes your AI output consistent.
Everything inside the conversation you are having right now: what you pasted, what it already said, the file you dragged in. Powerful, and it disappears the moment you close the window.
What the tool carries between sessions on its own. Convenient, and you did not write it. You cannot easily see it, edit it, or hand it to a colleague.
Plain markdown you own, in a folder: voice, boilerplate, approved examples, who signs off on what, read fresh by every person on staff. This is the standard.
The risk is not the model going rogue. It is an unattended process holding your logins and touching real records while nobody is watching.
Stay local until the output is boring. Boring is the signal that it is ready to run without you.
It will invent a number. A plausible participant count or success rate that appears nowhere in your files. Check every figure before it leaves the building.
It will use last year's facts. If the file says the program runs Tuesdays and it moved to Thursdays, it will keep saying Tuesdays. Your files are only as current as you keep them.
It will sound certain either way. Confidence is not a signal of accuracy. The tone is identical when it is right and when it is wrong.
New Claude models launching on or after 2 August 2026 support machine-readable marking at launch. Existing models are being retrofitted during a transition period.
An imperceptible watermark is woven into generated text and survives copying and pasting. Generated .svg, .png and .jpg files also carry a signed record showing they came from Claude (an open standard called C2PA).
The API (the developer connection), the Claude app, Claude Code, Claude Cowork and Claude Tag (Claude inside Slack). Worldwide, not only in Europe.
EU AI Act Article 50(2) requires generative AI output to be marked and detectable as artificial. The obligation to mark it sits with Anthropic, not with you; your call is how you disclose when AI helped.
A detected mark says content was processed by Claude. It does not say who wrote it, and it can disappear when text is heavily edited, paraphrased or translated.
Write your disclosure sentence now, while how it reads is still your choice.
Stop re-explaining yourself every morning to something with no memory of yesterday.
Otherwise it walks out the door when they do.
Chat is for thinking out loud, Code is for engineers, Cowork is for the work you actually repeat.
It is not a smarter model, and waiting for a smarter model will not get you there.
Both of those are cheap now and expensive later.