The prompt is what you tell the AI to do each time the task runs. The quality of the prompt determines the quality and consistency of the results. A specific prompt produces consistent results. A vague prompt produces inconsistent ones. And if the prompt is too vague for the AI to determine what it is supposed to do, the task will produce no result at all. The AI will not guess. If it cannot find a clear instruction to follow, it stops.

A vague prompt is not just a risk of getting no output. Because AI Tasks run unattended and no one reviews the plan before it executes, a prompt that does not clearly scope what to act on, whether that is a file, a folder's settings, a user or group, or a site-wide setting, can cause the AI to change or remove the wrong thing, with no chance to catch the mistake first. This applies to more than file operations: a poorly scoped prompt for an onboarding or offboarding task can just as easily grant or revoke the wrong person's access. Precision matters more here than in the AI Assistant, where every action waits for your approval before it happens.

What a Good Prompt Covers

A well-written prompt covers four things:

What to act on. Tell the AI exactly what to look at: a folder, a file, a user, a group, or a site setting. Include the full path or the specific name rather than a general area. If you are using a File Action trigger and want the AI to process a specific file type, name it in the prompt. "When a new CSV file is uploaded to /Intake/Partners..." is more reliable than "Look at the folder and see what arrived," and "Check the members of the Contractors group" is more reliable than "Check who has access."

What to do with it. Describe the task clearly. If you want the AI to validate content, tell it what a valid file looks like. If you want it to check a permission or a configuration, tell it what the correct setting is. The AI does not know your business rules unless you write them into the prompt.

What to produce, or what to change. Tell the AI the output format and where to write it. If you want a markdown file, say so. If you want the file in a specific folder with a specific naming convention, include that. If the task also makes a change, like removing a user from a group or revoking a folder permission, say so explicitly rather than leaving it implied by the goal. Without a clear output instruction, the AI may respond in the chat session only and not write a file.

What to do when something goes wrong. Tell the AI what to do if the data is missing, a permission conflicts with what you expect, or the target cannot be found. "If the file is missing required columns, write a report to /Exceptions explaining what is missing" is better than leaving the error case undefined.

Prompt Structure That Works

A prompt that follows this structure produces reliable results:

The trigger context: what just happened or what the AI should start with
What to act on and what to check
What to produce and where to write it, or what change to make
What to do if something does not meet expectations

Good Prompt vs. Weak Prompt

The examples below show the same task written two ways. The weak version is not obviously bad. It describes what you want at a high level, but leaves out the specifics the AI needs to produce consistent results.

Invoice validation

Trigger: File Action on the /Intake/Invoices folder. Add a source pattern like invoice_*.pdf to limit which uploads fire the task.

Weak prompt

When a new invoice arrives in /Intake/Invoices, validate it and move valid ones to /Processing/Ready. If something looks wrong, flag it.

This sounds reasonable but "validate it" gives the AI nothing to check against. The AI does not know which fields are required, what format they should be in, or what "looks wrong" means for your invoices. "Flag it" is also undefined. Flag it how? The AI may leave a note in the chat session and stop, or produce a different result on every run.

Prompt:

When a new file is uploaded to /Intake/Invoices, open it and check that it contains all of the following fields: vendor name, invoice number, invoice date, line items with quantities and unit prices, and a total amount. If all required fields are present, write a summary to /Processing/Ready named [original filename]-validated.md listing the extracted values. If any required fields are missing or cannot be read, write a report to /Processing/Exceptions named [original filename]-error.md that lists exactly which fields are missing and what was found in their place.

Partner delivery report

Trigger: Interval (daily) or a Custom Schedule set to your preferred time each day.

Weak prompt

Check /Transfers/Inbound for partner deliveries and create a daily summary report. Group by partner.

The folder is specified, which is a start. But "daily summary" does not tell the AI what time window to look at, what to include for each file, or where to write the report. The AI will pick a format and location on its own, which may differ every run. There is also no instruction for what to do when no files arrived.

Prompt:

Look at the /Transfers/Inbound folder and list every file that was created in the last 24 hours. For each file, record the filename, file size, and the time it arrived. Group the files by the top-level subfolder they are in (each subfolder represents a partner). Write the summary as a markdown file to /Reports/Daily named delivery-report-[today's date].md. If no files arrived in the last 24 hours, write the report anyway and note that no deliveries were received.

Sensitive content screening

Trigger: File Action on the /Intake/External folder. Leave the source pattern blank to screen every file that arrives.

Weak prompt

When a file is uploaded to /Intake/External, scan it for PII or confidential data. If anything is found, hold it for review. Otherwise let it proceed.

"PII or confidential data" is too broad. The AI will decide what counts, and that judgment will vary. "Hold it for review" and "let it proceed" do not tell the AI where to move the file or what to write. There is no audit trail. A file that triggers a false positive and a file that is cleanly cleared leave no record of what was found.

Prompt:

When a new file is uploaded to /Intake/External, open it and scan for the following patterns: Social Security numbers (format: XXX-XX-XXXX), credit card numbers (16-digit sequences), and email addresses from outside the files.com domain. If any of these are found, write a report to /Screening/Flagged named [original filename]-flagged.md listing each match, its location in the file, and the pattern it matched. Do not copy the full value. Record only the first and last two characters with the middle masked. If no patterns are found, move the file to /Intake/Cleared and write a one-line confirmation to /Screening/Cleared named [original filename]-cleared.md.

Configuration audit

Trigger: Interval (weekly) or a Custom Schedule set to a specific day and time, like every Monday morning.

Weak prompt

Check each folder under /Partners to make sure it is configured correctly and send me a report.

"Configured correctly" has no definition here. GPG enabled? Correct permissions? A notification set up? The AI will check whatever it decides is relevant, which will differ from run to run. "Send me a report" is also a problem. AI Tasks write files to folders. They do not send email, and "me" is not defined.

Prompt:

Look at each subfolder inside /Partners. For each partner folder, check the following: the folder has at least one user assigned with read and write permissions, GPG encryption is enabled, and a Notification is configured to alert on file uploads. Write a report to /Admin/Audits named partner-config-audit-[today's date].md. For each partner folder, list the folder name and whether each check passed or failed. If a check cannot be determined, note it as unknown. At the end, summarize how many folders passed all checks, how many had at least one failure, and list the folders that need attention.

User access cleanup

Trigger: Interval (weekly).

Weak prompt

Check the Contractors group and remove anyone who shouldn't have access anymore.

"Shouldn't have access anymore" has no definition. Does that mean the account is disabled, inactive for some period, or the contract has ended? "Remove" is also undefined: remove from the group, revoke folder permissions, or disable the account entirely? Nothing is written down, so there is no record of who was changed or why.

Prompt:

Look at the members of the Contractors group. For each member, check whether the account is disabled. If it is, remove that user from the Contractors group and revoke their permissions on the /Projects/Active folder. Write a report to /Admin/Access-Cleanup named cleanup-[today's date].md listing each user changed, what was revoked, and any accounts that could not be processed.

User offboarding verification

Trigger: Ad-Hoc, run manually each time someone is offboarded. Use Ad-Hoc when the work is not on a fixed schedule but you want to run the same prompt on demand. Offboarding is a good example: it happens when it happens, and you want a consistent verification every time without relying on memory or a manual checklist.

Weak prompt

Make sure [username] no longer has access after they were offboarded.

"Access" could mean folder permissions, group memberships, share links, or all three. The AI will decide what to check. There is also no output. No report is written, so there is no record of what the AI found or confirmed.

Prompt:

Check whether the user [username] still has access anywhere on the site. Look at folder permissions, group memberships, and active share links. For each area, list what was found and whether the access has been removed. Write a report to /Admin/Offboarding named offboarding-[username]-[today's date].md. If no active access is found, note that and confirm the account is fully removed.

What Makes a Prompt Fail

Too vague. "Analyze the file and do something useful" gives the AI too much latitude. If it cannot determine what it is supposed to do, it will produce no result. The output will also vary run to run when the task is underspecified.

No output instruction. If the prompt does not say where to write the result, the AI may respond only in the chat session and not produce a file. Always specify the output location and format.

Assumes the AI knows your business context. The AI does not know what a valid invoice looks like for your organization, what your partner naming conventions are, what counts as inactive for a contractor account, or what your compliance requirements are. If it matters, write it into the prompt.

Too many tasks in one prompt. Asking one task to validate, classify, summarize, and route a file produces unpredictable results. Each of those is a separate job. Break complex workflows into multiple tasks, or use an Automation to route files to folders where separate, focused tasks pick them up.

No source pattern on a high-volume File Action trigger. If the trigger folder receives many files and the prompt is designed for a specific file type, the task will run on every file including ones it cannot process. Set a source pattern like *.pdf or report_*.xlsx to limit which files trigger the run.

Vague scope for a change. A prompt that says "remove access" or "clean up permissions" without naming the specific group, folder, or permission to touch can cause the AI to change more, or less, than you intended. Be as specific about what to change as you are about what to read.

No error handling. A prompt that only describes the happy path leaves the AI without guidance when something goes wrong. Always include instructions for the exception case.

When a run fails or produces no output, open the chat session in Chat Logs. The transcript shows exactly where the AI stopped and what it encountered. Fix the prompt and use Ad-Hoc to re-run manually before putting it back on a schedule.

Tips for Getting Good Results

Start with Ad-Hoc trigger when building a new task. Run it manually several times on real files to confirm the output matches what you expect before switching to a schedule or file action trigger.

Use a workspace to test new tasks before running them on production folders. This limits the impact if the prompt needs adjustment.

Review the chat log after each test run. The transcript shows exactly what the AI did, which files it accessed, what decisions it made, and where it got stuck. This is the fastest way to identify what the prompt is missing.

Keep one prompt focused on one job. A task that does one thing well is easier to test, easier to debug, and produces more consistent output than a task that tries to do everything.

If the AI is not producing what you expect, the problem is almost always in the prompt. Make the instructions more specific, add the missing context, and test again.

Writing Effective Prompts