FINDOC

Find the contract terms and policy clauses inside your documents.

A desktop document search app in development for local folders and NAS shares, for people who need to locate conditions, dates, and clauses across HWP, PDF, and Office files.

In development · Preparing for release

Local document engine

From a folder to an answerable result set.

The desktop workflow keeps extraction, indexing, and search on the device. The planned Claude API feature is separate and will only use passages a user explicitly selects.

  1. 01 · SelectLocal folders or a configured NAS share
  2. 02 · ExtractHWP, PDF, Office, image, and text content with OCR where supported
  3. 03 · IndexLocal keyword and semantic indexes
  4. 04 · InspectFiltered results linked back to the source file
Implemented local processing flow · desktop release preparation

Search where work is actually stored

Findoc is designed around folders, shared drives, scanned papers, and office files people already use.

Document extraction

The development scope includes HWP/HWPX, PDF, Office files, images, text, and email. OCR is used for supported image-based material.

Local search

After indexing, keyword and semantic search can run on the user’s device. A network connection is not required for local searching.

Practical narrowing

File type, date, and path filters help users move from a broad result list to a document they can inspect.

What has been checked, and what comes next

Recorded checks cover document extraction; full search-workflow evaluation comes next.

Checked on 8 October 2026

A Codex run produced non-empty extraction for one fixture each of PDF, DOCX, HWPX, Markdown, TXT, HTML, JSON, and EML. It also found the expected keywords in the TXT and Markdown fixtures, and 12 selected parser tests passed.

Still to validate

This does not validate the full GUI search flow, search accuracy, or real user use. Those need separate evaluation with permitted samples.

Next Claude Code milestone

We plan to run one Findoc document-to-search task through requirements, implementation, independent QA, and founder approval. With permitted samples, we will assess search accuracy, task completion, and cost before reusing the workflow for other products and custom software projects.

A deliberate search flow

The path from file to result stays visible.

  1. 01

    Choose folders

    Select local folders or a configured shared location.

  2. 02

    Index content

    Extract available text and prepare it for search.

  3. 03

    Search and inspect

    Review results, filters, and the original document.

Illustrative planned workflow

Question: “When is the renewal notice due?”
Answer: cited clause from a selected contract, or withheld if unsupported
Next: open the original file to verify context

Claude use is scoped for reviewable answers

Findoc is currently developed with Codex. We are evaluating a move to Claude Code for selected development and verification work; a Claude API feature remains a separate, opt-in cloud query flow.

Current: development with Codex

Codex supports requirement structuring, implementation and documentation review, and verification steps. Claude Code is under evaluation for selected workflows. Release decisions remain with the founder.

Planned: grounded document questions

A user would search relevant passages locally, see the proposed transmission range, and consent before a server sends a question and the minimum selected text to the Claude API. The app would reconfirm the scope before sending, apply a request-cost cap, and keep local search available if the request fails.

Answer with evidence

The planned response will cite a file and passage, reducing time spent comparing several files while keeping the original source one click away. When selected material does not support an answer, it should withhold an answer.

Questions

Will Findoc send all documents to a cloud service?

Local search is designed to work offline. Any future cloud question flow is separate, shows its scope, and requires a user choice before sending selected text.

How will the planned Claude feature be evaluated?

Before expansion, we plan to assess source accuracy, appropriate “I don’t know” responses, latency, and request cost. Other Claude API ideas will wait for this evaluation. No performance level is promised here.

Product conversation

Discuss a sample document-search workflow.

tkddyd420@jinsongtech.com