◆ Software · Work Atlas

The real work of Extensible markup language XML

Forget the menus and the buttons. This is what people actually get done in Extensible markup language XML at work — the real tasks, sorted by the kind of work they are, each with a prompt you can use tonight.

67evidenced tasks
4kinds of work
See the tasks ↓Open the interactive atlas

What kind of work is it?

tap a kind to filter the tasks

Which one is you, right now?

Pick the moment · no score, no sign-up
Where are you standing with your work today?
Whichever you pick, the four prompts below cover it.

The work, task by task

67 tasks
hands on the workAnalyse library users' queriesopen it → hands on the workApply archival theory, methods, and appraisalopen it → hands on the workApply their findings for the improvement of societyopen it → hands on the workAssist in developing and updating HR policiesopen it → hands on the workBalance and adjust gameplay experiencesopen it → hands on the workBreak systems into components and analyzeopen it → hands on the workCapture electronic contentopen it → hands on the workCompile lists of books, periodicals, articles, and audio-visual materials on particular subjects.open it → hands on the workComputer programmingopen it → hands on the workConsult with multiple stakeholders to define requirements and implement online features.open it → hands on the workCoordinate the energy use in an organisationopen it → hands on the workCreate and maintain design documentationopen it → hands on the workCreate information systemsopen it → hands on the workCreate metadata and finding aidsopen it → hands on the workDetermine supplementary virtual features, such as currency, item catalog, menu design, and audio direction.open it → hands on the workDevise or evaluate methods and procedures for collecting data, such as surveys, opinion polls, and questionnaires.open it → hands on the workEdit and revise technical documents for clarity and accuracyopen it → hands on the workElectricity consumptionopen it →

Questions people actually ask

honest answers, no sign-up

Every task here was seen in the real world. Someone doing the job named it, a real job ad asked for it, or a lot of people asked about it online.

If nothing real showed a task, it is not on the page. That is the whole rule.

They are the same job approached four ways, because what you need depends on where you are.

Get it done today. Make it easy for the next person to say yes to. Work out the right move when you are stuck. Learn the pattern so the job stops coming back.

For most of these jobs it can carry the heavy thinking - draft it, sort it, check it, rehearse it with you.

It cannot sit in your chair, take the blame when a number is wrong, or notice what nobody wrote down. Let it do the first 80%. Keep the last 20% that is truly yours.

No. Copy any prompt and paste it into the AI you already use. No account, no score, no wall in the way.

Any of them. The prompts describe the work rather than naming a product, so they are not tied to one assistant.

That is also why they keep working when you switch.

Change it freely. Every prompt is a starting line, not a rule.

Put in your real numbers, your real names and your real deadline. The more you make it yours, the better the answer comes back.

The tasks come from real job ads, published job data and the questions people ask in public forums.

The steps come from Extensible markup language XML's own documentation, with practitioner sources for the traps the manual does not mention.

Push once. Ask it to sharpen the weakest part and to say what it assumed.

Most wrong answers come from a missing detail rather than a bad prompt - tell it the thing it could not know.