{"id":14018,"date":"2025-10-20T04:58:14","date_gmt":"2025-10-20T04:58:14","guid":{"rendered":"https:\/\/prizmlaw.com\/site\/?p=14018"},"modified":"2025-10-20T16:31:25","modified_gmt":"2025-10-20T16:31:25","slug":"from-scanned-pdf-to-formatted-word-doc-a-lawyers-ai-drafting-experiment","status":"publish","type":"post","link":"https:\/\/prizmlaw.com\/site\/2025\/10\/20\/from-scanned-pdf-to-formatted-word-doc-a-lawyers-ai-drafting-experiment\/","title":{"rendered":"Using AI to Create Formatted Word Documents from PDFs"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t

Introduction<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

As a practicing attorney, I’m very excited to see how drafting legal documents will continue to evolve in this age of AI language models. Today, I conducted an experiment that is likely to make my own drafting workflow significantly more efficient. Currently, if I use AI to help me draft a document, I use the following workflow:<\/p>

  1. Put a prompt into the ChatGPT website such as, “Draft a letter for XYZ situation.”<\/p><\/li>

  2. Get a bunch of text back (that may include inaccurate hallucinations).<\/p><\/li>

  3. Check the substance of the text output to see if it is legally accurate.<\/p><\/li>

  4. Correct or rewrite portions of text.<\/p><\/li>

  5. Copy and paste that AI text into Microsoft Word.<\/p><\/li>

  6. Spend a significant amount of time on font, layout, or styling.<\/p><\/li>

  7. Save\/Print the new Word document.<\/p><\/li><\/ol>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t

    Wouldn't it be great if I could instruct AI to create the document I need and it generates the properly formatted Word document for me without my ever having to open MS Word?<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    I decided to put this idea to the test…<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t

    The Starting Point \n(A Sample Petition for Instructions)<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    I recently had to prepare a “Petition for Instructions” (under Cal. Prob. \u00a717200) for the court regarding a trust administration matter for a client. I needed a starting point for my draft and a way to quickly prepare a document that met the local court’s requirements for this petition.<\/p>

    Submitting this particular type of petition to the probate court is new for me, and so I wanted to review an example petition to be sure my draft included all the necessary elements for the court. My more experienced mentor was unavailable to provide an example. I did, however, find such an example in my copy of The California Probate Paralegal<\/i><\/a> in Appendix 10B.\u00a0<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t
    \"Image<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    Extracting the Text of the Sample Petition<\/strong><\/p>

    My normal process here would have been manually type the text from the sample into Word and use that as a template starting point for my own draft.\u00a0 The sample is only four pages so the transcription would be tedious but possible. However, it occurred to me that it would probably be much faster to scan the relevant pages to a .pdf and then use OCR or an AI model that accepts PDF as an input to extract the text to a text file.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t
    \"Image<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    I decided to use Claude Code<\/a> for this. Claude Code is a tool that allows me to interact with Anthropic’s Claude AI models from my desktop instead of going to their website. It is meant to help coders write code, but I’m finding some other interesting use cases for it. For example, on my own computer I was able to use it to organize files in a folder by their content and then rename those files automatically.\u00a0<\/p>

    In this case, I launched Claude Code from the directory on my computer where the scanned .pdfs of the sample petition were saved. I then asked Claude to extract the text. I gave it the following instruction:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t

    My Prompt: \"Please extract the text from the pdf file SamplePetitionForInstructions.pdf that includes a non-OCRed scan of some pages from a book about California probate that is an example petition for instructions. Save the text (and if possible formatting and layout) of this to a new document.\"<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t
    \"Image<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    The first text file output was pretty good; it gave me a clean text file, but it included more text than I actually wanted. To refine this, I decided I needed to be more specific in my instructions, so gave a follow-up instruction:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t

    My Prompt: \"I intend to use the extracted text as a starting point for drafting my own Petition for Instructions on a matter I am working on. Therefore, there are some text elements that I do not need. This includes things like page numbers and titles like \"Appendix 10B\", etc. Please provide a new file that contains only the elements that are necessary and useful for me to use as a starting template for my own petition.\"<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t
    \"Image<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    This resulted in a much cleaner file. Claude also highlighted the changes it made:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

    \n\t\t\t\t
    \n\t\t\t\t\t\t\t

    Claude: “I’ve created a cleaned-up template file at PetitionForInstructionsTemplate.txt that removes:<\/p>