BentoPDF - free PDF editor replacement for Acrobat

I have tested out more than one free PDF editor when I did not have Acrobat available. BentoPDF an online PDF editor, is the best of the bunch, and it includes many functions Acrobat users will be familiar with.

Some of the functions do not allow you to process multiple PDF files.

It does however include a Bates stamp tool which can apply Bates numbers to multiple PDFs.

There is no option in the 'Bates padding' field to apply stamps with leading zeros for numbers greater than six digits, but this limitation is easily overcome by adding zeros in the 'Customize Style' field which uses the identifier [BATES] for the starting number you select for the production. The only available fonts are Times New Roman, Courier, and Helvetica

As always, I'm testing the solutions I'm posting about with real data and can confirm that Bento gave results as promised.

It has an effective redaction tool which can be used with one PDF at a time, but does give you a way to select text to be redacted before those redactions are applied.

Tests confirm that Bento can convert multiple Word documents to PDFs, and it includes options to convert Excel, PowerPoint, JPEGs, and other formats.

Sadly, it will not OCR multiple PDF files.

Its tool to extract information from charts included in PDF files won't be making me abandon Abbyy FineReader's far superior tool, but it gives usable results. From this PDF:

. . . it extracted this data to a .csv file.

BentoPDF's promotional materials tout its rigorous privacy policy which ensures users that their PDFs will remain in their browsers.

However, you should note that it does offer a commercial version for a $79 fee which allows for it to be used in an application without disclosing the source code of the application.

Files Cut and Paste to New Directory Retain Rights from Original Directory

It's important to keep in mind that a set of files cut from a folder on a Windows network which have rights to one matter (or user group) which are then CUT and pasted to a folder for a different client/matter (and other users) will inherit the rights of the origin folders. Users who only have rights to the destination folder will not be able to access the files.

In order to get around this problem, you can copy the files into another folder in the directory with the same rights as the intended destination folder; delete the files in the intended destination folder; and then copy the files back into the intended destination folder. If you don't delete the files in the intended destination folder, and instead overwrite them when copying back in, the rights will not get updated.

So if files are saved here:

F:\A0100\0002\Johnson Exhibits

. . . .and are then CUT and pasted here:

F:\C0200\0004\Johnson Exhibits

If you check the Properties for F:\C0200\0004\Johnson Exhibits on the Security tab, you should see this:

Note the difference between the client matter name (C0200.0004) used in the object name, and that for the Group with rights, A0100.0002. Obviously, there's a problem. The solution is to do the following:

COPY: F:\C0200\0004\Johnson Exhibits TO: F:\C0200\0004\GeneralFolder

DELETE CONTENTS OF: F:\C0200\0004\Johnson Exhibits

COPY F:\C0200\0004\GeneralFolder TO F:\C0200\0004\Johnson Exhibits

But what if you're worried there may be additional files in a directory with the wrong rights assigned to them? How can you check the rights of all of the files in a directory?

This PowerShell script will generate a list of the rights for all files in the directory that you specify:

Get-ChildItem -Path "C:\Your\Directory" -Recurse | Get-Acl | Select-Object Path, Owner, AccessToString

However, if you run this script you may get an error message:

This comes up when there are filepaths longer than 255 - 260 characters - the Windows Explorer limit.

So, before you run the script to get a list of the rights for a directory, you want to run this script to search for any files with a path of 260 characters or longer.

Get-ChildItem -Path "C:\Your\Directory" -Recurse -Force -ErrorAction SilentlyContinue | Where-Object {$_.FullName.Length -gt 260} | Select-Object FullName

Rename those filepaths, and then run the script to find the rights of all files in a folder:

You can then copy the results into Excel and filter for matter numbers other than those which files in the directory should have. Just be sure to filter so that you're only excluding the permissions listed on the right, and not the file paths on the left. So in this example, filter for Does Not Contain 'cg_F:\C0200\0004', not just 'F:\C0200\0004'.

Relativity Guide to Prompt Engineering for AI

The key to getting AI systems like Harvey AI to generate effective drafts of legal briefs, and solve other problems is to devise a good prompt to get AI to give you the result that you need. In the AI for Legal Basics certification course, Harvey emphasizes that its system will not work well if given ambiguous instructions, and that projects should be divided into discrete tasks. A good prompt will indicate what should not be done, and the prompt should specify which authorities should guide it.

As a new addition to its extensive array of electronic discovery training materials, Relativity has prepared a guide, The Legal Professional’s Guide to Prompt Engineering, which can be downloaded here: https://resources.relativity.com/legal-professionals-guide-prompt-engineering-lp.html

The core idea is to alter the language often used in legal documents to phrasing that provides AI with better guidance about what to generate:

Here are some key takeaways:

1. Having the ability to write well is key. Prompt engineers often have degrees in English, rather than in fields related to technology.

2. Relativity references OpenAI's tips for engineering effective prompts which include:

   1. Use the latest LLM.

   2. Clearly distinguish between the instructions for what the AI system should do and the information it should be reviewing. OpenAI marks text to be analyzed with 3 quotation marks """:

   3. 

      Be specific about the outcome. Give examples of the results that the system should generate. You want to avoid 'zero-shot prompting', which provides instructions without demonstrating the desired result.

      
      

      

3. Much like the tried and true EDRM model, Relativity recommends thinking of prompt engineering as an iterative process. It's necessary to interact with the system to refine the result that it produces.

4. AI can be instructed to indicate its own reasoning. CoT - chain-of-thought prompting is when a prompt tells the system to explain how it is reaching a conclusion. A prompt can, for example ask that the system identify an issue, the relevant rules, and state how the rule applies to the facts, showing how a conclusion is reached.

5. Use role-based prompting: a prompt can specify that a system answer a question as someone working in a specific position would.

6. Contextual prompting is when a prompt includes the text cited to for the facts of a case or the relevant law. The content of a contract or a statute is added to the prompt.

7. AI systems are also guided by system prompts which users can't see that restrict the possible results. They may be prevented from giving answers with a political perspective.

8. Relativity's aiR for Review is limited to 15,000 characters. Compare this to the much higher token / page limits in Harvey discussed in the March 20, 2026 Tip of the Night.

9. Algorithms should be used to optimize prompts. They cite a research study conducted at VMware, Rick Battle and Teja Gollapudi, The Unreasonable Effectiveness of Eccentric Automatic Prompts, arXiv:2402.10949v2 (2024), which found that optimized prompts will give higher exact matches on average than prompts which merely encourage the system to arrive at a solution.

Relativity has its own prompt optimizer, or kickstarter.

It's possible to upload up to 10 documents (which can't have more than 300K characters), such as complaints, memoranda summarizing a case, or requests for production, to prime this function so that it can autogenerate criteria for a prompt.

10. The active voice should be used in prompts, and double negatives should always be avoided.

11. Boolean operators can be used in prompts, and even putting certain phrases in ALL CAPS or adding exclamation points can lead to a better result.

12. AI systems may get confused by some legal terms which are too vague such as 'reasonable' or 'substantial'.

13. There is currently some debate as to whether prompts should be regarded as work product, or if they ought to be disclosed in ESI protocols just as search terms are.