CoachDiscoverMapCompareSavedAI LearningAI WeeklyAbout
← Back to library
Guide 02 · Applied

Rename, Refine, and Iterate

Once the folder structure is right, the next pass cleans filenames. The AI proposes renames for the worst offenders, leaves the good ones alone, and lets you defer metadata to a separate step.

Takeaway 01
Renaming is a follow-up pass — you don't do it at the same time as organizing.
Takeaway 02
"Worst offenders" is a deliberate scope choice — don't rename what's already fine.
Takeaway 03
Defer metadata until structure and names are stable — handle one dimension at a time.

Asking for Rename Suggestions

After the AI organized the library, the narrator immediately spotted naming problems — filenames like cryptic IDs and inconsistent prefixes. The next move was to ask SharePoint AI to "suggest ways to better name" the files. The AI returned a list of rename proposals with both current names and recommended names side by side.

Renaming is a second pass, not a side effect of organizing. SharePoint AI treats structure and naming as separate problems so you can review each independently.

Each suggestion is auditable. You see the rule the AI applied (consistent prefix, date format, removal of internal codes) and can approve, edit, or reject it. The bulk rename happens after you confirm — there's no surprise mass-edit.

Rename Only the Worst Offenders

The narrator asked the AI to "rename the worst offenders" rather than renaming everything. This is a scope filter: it tells the AI to ignore files whose names are already acceptable and focus on the ones causing the most confusion — duplicates, cryptic codes, broken dates, missing context.

Scoping renames to "worst offenders" preserves files where the existing name has value (project codes that match external systems, legal references, established conventions).

After the run, the library showed consistent "014" prefixes where there had previously been a mix of formats — exactly the change the AI had recommended. Other filenames stayed untouched.

An obvious assumption is that the AI will normalize every filename to one rigid pattern. In fact it makes targeted edits where the existing name fails — and otherwise leaves the file alone.

Defer Metadata to a Later Pass

When organizing, the narrator deliberately said "I'm going to ignore metadata for now." Metadata extraction (risk levels, document types, dates, owners) is its own pipeline — it answers different questions than folder structure does, and mixing the two passes makes both worse.

Folders answer "where is it?" Metadata answers "what is it?" Do one at a time and each pass produces cleaner results.

Once folders and filenames are stable, the same library can be re-scanned with a metadata extraction skill — the topic of the next video in the series. Trying to do all three at once typically produces inconsistent results and harder-to-debug edge cases.

The reflex is to do everything in one prompt to save time. In practice, sequential passes (organize → rename → metadata) take fewer total clicks because each pass has less to second-guess.

The Iterative Cleanup Workflow

The whole demo follows a pattern: scan → review options → apply a subset → re-scan → fix the next layer. After the file moves the narrator immediately spotted naming issues and ran another pass. This is the workflow — not a single magic button, but a short loop of AI suggestions and human approvals.

A few minutes of AI-driven iteration produces what would otherwise take hours of manual cleanup. The structure emerges from a sequence of small, reviewable changes.

By the end of the demo the library had a real folder structure, consistent naming on the previously broken files, and a clean baseline for the next pass (metadata). All from inside the SharePoint UI, with no scripts or third-party tools.

Flashcards — Applied
02 · Applied
Rename Suggestions
tap to reveal →
The AI's proposed list of better filenames, shown alongside current names. You approve, edit, or reject each suggestion before the bulk rename runs.
← tap to flip back
02 · Applied
Worst Offenders
tap to reveal →
A scope filter telling the AI to rename only the files whose names cause the most confusion — leaving already-acceptable names untouched.
← tap to flip back
02 · Applied
Defer Metadata
tap to reveal →
The decision to skip metadata extraction during the structural pass. Folders and names get fixed first; metadata is a separate, later run.
← tap to flip back
02 · Applied
Iterative Cleanup
tap to reveal →
The loop of scan, review, apply, re-scan that drives SharePoint AI library cleanup. Each pass addresses one dimension and feeds the next.
← tap to flip back