Valentina Akpan: Founder of Rellatech, providing administrative and operations support to executives, founders, business owners and teams. Her background combines technical support, customer success, administration and operations.
·
A client engagement came in with a detailed document request list: dozens of specific document types spanning over five years of business activity. Monthly financial reports, quarterly invoices, account statements, position reports, operational records.
By the time I assessed what was on hand, the folder contained well over a thousand files. The brief was to check what was there against the checklist and list what still needed review, quickly.
The Challenge
The traditional approach is painful: open the checklist, then open the folder. Click through files one by one, cross-referencing against each requirement, holding a running mental note of what is covered and what is still missing. With a thousand files spread across years of subfolders, that process can take days, and it is easy to miss things.
1,000+ files across 5 years of subfolders
40 distinct checklist requirements to satisfy
Generic file names hiding the real content
Manual review was estimated at about two days
The Solution
I built a lightweight desktop app using Python and Streamlit. Point it at a folder, and it searches every file for the terms tied to each checklist item.
File names alone are unreliable, so the app reads inside the files. For each file, it extracts readable text from PDFs, Word documents, Excel workbooks, and plain text, then searches that content for keywords tied to each checklist requirement. Each requirement is mapped to its own set of search terms, and the app works through every file against every requirement.
The result comes back as a dashboard: how many items have a candidate match, which ones have nothing matched yet, and which files matched each requirement's terms.
What I Built and Connected
Folder scanner
Point it at any folder. Recurses subfolders and indexes every file.
Multi-format text extraction
Reads PDFs, Word documents, Excel workbooks, and plain text.
Keyword mapping per requirement
Each checklist item is mapped to a set of search terms, run across every file.
Review dashboard
Categories, items with a candidate match and items with none, and which files matched each requirement's search terms.
Exports for follow-up
A list of items with no match, a list of candidate matches, and a ZIP of the matched files for the reviewer.
Streamlit interface
Lightweight desktop app the client can run themselves, no terminal required.
What the Output Looks Like
Results are grouped by category, mirroring the original checklist. Each category shows how many items have a candidate match out of the total. Anything without a match expands automatically so the items needing review are visible first.
Every candidate file gets a relative path and a download button. A bulk export produces a list of items with no match, a list of candidate matches, and a ZIP of the matched files for the reviewer.
Before and After
Before
- · An estimated two days clicking through subfolders
- · Mental tracking of 40 checklist items
- · Easy to miss a file or misclassify one
- · No clean handoff list for the client
After
- One scan in seconds
- Candidate matches grouped by category
- Items with no match listed for review
- ZIP and follow-up lists exported
Where It Falls Short
A tool like this is only as good as its keywords. Some matches come back as false positives because a relevant word appears in a document that is not what the checklist required. That is expected.
The app is not meant to replace human judgement. It replaces the manual work of opening and cross-referencing a thousand files. You still review the candidate matches and the items with none. On this project, the manual review was estimated at about two days, and the review of the structured report took about an hour.
The tool does the opening and searching. The judgement stays with the reviewer.
A Structured Starting Point for Human Review
The tool organizes candidate document matches against the checklist and exports lists for follow-up. A keyword match does not establish that a document satisfies a requirement, and an unmatched item does not prove the document is absent. A reviewer checks the candidate files and resolves uncertain results before confirming coverage.
The deliverable is a more organized review process, with evidence and open questions presented together.
- Candidate matches organized for the checklist items across years of financial records
- Items with no match listed as the follow-up list for the reviewer
- Delivered a ZIP of candidate files and a list of items needing review
- Manual review estimated at two days; the structured review took about an hour
The scan runs in seconds. The reviewer's time goes to checking the candidate files and resolving the uncertain results.
Tools Used
Who This Is For
This case study is worth reading if you are:
- ●Compliance, legal, or operations teams sitting on document backlogs of hundreds or thousands of files
- ●Businesses preparing for an audit, due-diligence review, or funding round
- ●Anyone with a clear checklist of required documents and a messy folder of what they have
- ●Businesses and startups that can describe the gap they need to find but don't want to spend two days clicking through PDFs
Need help with similar work?
Tell me which responsibilities or processes need attention, who is involved and any upcoming deadlines. I provide administrative and operations support, including the connected technical work within our agreed scope.
Book a free callRelated Services