nip

like that, but (and I might be ignorant) can't you just change it's all in browser to something else and the users would be oblivious?

Excellent question! The answer is simple: we're known on the market, and trusted by our customer for this secure handling of PDFs. Should we decide to change that (unbeknownst to them), we would effectively kill our reputation and the company by extension.

Is it possible to download as an app and disable internet (not sure if it's a feature of any browsers).

Back in the days, SimplePDF used to work offline. However maintaining that in conjunction with our paid customers features (where the online connectivity is mandatory) was too big of a maintenance burden. We decided a year ago to drop this support (silently), and no one has complained since then, confirming our hunch that it is not a high-demand feature.

Thanks! We have plans to improve it further (file support), possibly also voice, but for now in the backlog!

And if you’re French, don’t worry, you didn’t miss it.

It’s the 31st of May

Thanks! You caught a real bug: the form labels fed to the LLM were mangled. Now fixed: values land in the correct field.

On "what are we trying to solve":

Forms (PDFs, scanned paper) are still everywhere and aren't going away. SimplePDF Copilot exists to make the transition less painful. A few concrete use cases:

- Pre-filling repetitive forms from existing data sources (CRM, EHR, etc. via MCP/RAG). In most industries, employees fill forms by copy-pasting or retyping. With AI + tool calling, most of the form arrives pre-filled and the employee just corrects or adds the missing bits.

- Filling foreign-language forms. If you've moved to a new country, or know someone who has, you've had to fill out forms in a language you don't master.

- Understanding a contract before signing it. "Can I actually trust all the clauses here?" Reading proficiency changed the world by giving people a way to understand what they were signing. This extends it to legalese and odd clauses.

On Claude Cowork:

Different shape, and a different privacy model. Cowork drives a sandboxed virtual desktop: you can't see exactly what it's doing while it fills, and correcting a wrong value means another back-and-forth with the LLM.

Copilot works inside your editor: every change is visible as it happens, you can amend any field with one click, and the document never leaves your browser + it's LLM agnostic: bring your own (local or hosted).

Absolutely not insulting! In fact an excellent question!

Preview was an inspiration when I started SimplePDF, my goal was to make the "Preview" of the web, so that people without a Mac would benefit from a software matching Preview in ease of use and overall polish.

Adobe Acrobat: SimplePDF has "Simple" in the name as the philosophy is to keep it simple (both in ease of use, and features): I don't intend to support everything that Adobe Acrobat does. There's a lot of features that I could build that I intentionally do not, as they would bloat the UI and hard the overall usability. Most people have very simple needs and don't need advanced features (like scripting, etc).

It already does! More specifically, SimplePDF supports "WebMCP": the tools that the LLM is using are exposed as WebMCP tools

We offer both:

- A privacy-focused PDF editor, free for individuals, used by 200k users monthly: https://simplepdf.com/editor

- The same editor, embeddable into one’s app for companies, with the same privacy guarantees (everything happens in the browser) + the resulting PDF is stored in their own storage (« bring your own storage »).

The majority of our paid customers are in healthcare where privacy is non-negotiable. Co-pilot extends that to the AI world (« bring your own AI »)

What are you using the PDF editor for?

I was not able to reproduce it, so I made a small video, hopefully I better understand your problem once you've seen it: https://cdn.simplepdf.com/simple-pdf/assets/hn-reply-tyingq....

In the video I let the chat fill my name, then have it skip the second field (business), then fill LLC, it makes a mistake and I correct it

Have you tried telling the LLM to just skip the field and move to the next one?

I tried with various: "Skip it", "None, leave blank", "Skip this field" and all worked for me, but if may very well be missing something very obvious?

Hey Kiney!

It supports AcroForms (like in the example) but not XFA.

Why are you asking? gov forms support?

Thanks!

Anything you see missing in Copilot to achieve that?

Not sure if you noticed, but there's an arch-diagram in the info popup [1].

[1] https://copilot.simplepdf.com/?share=a7d00ad073c75a75d493228...

I tried to make it clear with the popup message that appears when you start chatting: "Public demo. Use sample data only. Messages are processed by the selected AI provider."

But you're right that it's not as evident as I wanted to, I'm making a small copy update to make it clearer: "Public demo. Your chat messages leave your device and are sent to the selected AI provider. Use sample data only."

(Since there's support for local models, the popup is only displayed when NOT using your own model)

Thanks!

EDIT: the copy update is live, thanks again!

Just to be clear, this is a technical demo showing what's possible with client-side tool calling + local models: LLM-assisted form filling where no document data has to leave the user's machine.

Use cases range from:

- Filling foreign-language forms

- Navigating a contract before signing: "can I trust ALL the clauses here?"

- Pre-filling repetitive forms from existing data sources (CRM, EHR, etc. via MCP/RAG)

Copilot is designed to be embedded; our customers ship it white-labeled inside their own products.

Just to be clear, this is a technical demo showing what's possible with client-side tool calling + local models: LLM-assisted form filling where no document data has to leave the user's machine.

Use cases range from:

- Filling foreign-language forms

- Navigating a contract before signing: "can I trust ALL the clauses here?"

- Pre-filling repetitive forms from existing data sources (CRM, EHR, etc. via MCP/RAG)

Copilot is designed to be embedded; our customers ship it white-labeled inside their own products.

Very likely, but you don’t need to be so aggressive and dismissive.

Anyone who has achieved “distribution” knows. Anyone else is just lacking experience.

Answering like you did is akin to gatekeeping. The world is better with more builders. We should encourage anyone who wants to give it a shot

I was approached twice to add « a search and tracking script » to my 35k+ user-based extension.

Now I know what would have happened if I had accepted.

Agree on Smart-ID but the answer is to fix those flaws, not to replace the entire approach with one that depends on Google Play Integrity verdicts that even the German architects admit they can’t fully trust.

SIM-based solutions on their way out is a non-issue. For eSIM to support that use case, political will only is needed: the EU got Apple to abandon the lightning cable, this is not any different.

It is, mandated by the EU commission.

Instead they could have mandated the use of eIDAS 1 to all countries + extend it with attribute/credential support, and let countries choose their implementation (cards, SIM, server-side).

Instead we’re back to the drawing board with the big shortcomings highlighted in this thread.

I’m sorry to lash out at you but I keep getting disappointed in European countries (more precisely the ever disappointing EU commission) all suffering of the NIH syndrome instead of collaborating and learning from each other

In light of all of these shortcomings with platform attestation, why go with the eIDAS 2 wallet approach at all? eIDAS 1 already solved this with Mobile-ID (SIM-based, no Google/Apple dependency) and Smart-ID (server-side key management with minimal platform reliance). What does the wallet model give you that justifies this level of dependency on two American corporations’ proprietary backends?

Especially considering that mobile-ID has been around since 2007.

The web was initially meant to be browsed by desktop computers.

Then came mobile phones with their small screens and touch control which forced the web to adapt: responsive design.

Now it’s the turn of agents that need to see and interact with websites.

Sure you could keep on feeding them html/js and have them write logic to interact with the page, just like you can open a website in desktop mode and still navigate it: but it’s clunky.

Don’t stop at the name “MCP” that is debased: it’s much bigger than that

The reason is simple: the TUI is the fastest way to provide any form of UI over the file system.

Want to do that with web technologies? You’ll need a browser AND a server or build an app using electron or tauri.

I still haven't figured out MCP or how/why to use them or why to bother. You run servers. I guess. It's too complex for my smol brain to understand

I know this is self-deprecating humor, but you do NOT have a smol brain: MCP servers are not as needed anymore now that Claude Code supports "Skills". They are also very token hungry as their spec is not lazy-loaded like the skills.

It was / and still is very useful if you collaborate with other engineers or want to perform operations in a non-stochastic fashion.

MCP servers are a way to expose a set of APIs (openAPI spec) to an LLM to perform the listed operations in a deterministic fashion (including adding some auditing, logging, etc). LLMs are fine-tuned for tool calling, so they do it really well and consistently.

Examples:

- Documentation / Glossary: MCP server that runs somewhere that reads a specific MD file or database that is periodically updated: think "what are my team members working on" / "let me look up what this means in our internal wiki".

- Gating operations behind authentication: a MCP server that is connected to your back office and allows you to upgrade a customer's plan, list existing customers, surface current. Super useful if you're a solo-founder for example.

It’s easy to pick on logic that failed and for which you have a very detailed and great post mortem write-up.

Yet you omit to acknowledge that the remaining 99.99999% logic written that powers Cloudflare works flawlessly.

Also, hindsight is 20/20

A website was set up to inform and facilitate contacting MEPs: https://fightchatcontrol.eu

Additionally, keep in mind that controversial laws or proposals, at least in France, are often announced or passed during summer vacation when people are away, limiting scrutiny and attention.

Expect to hear more outrage come September

Thanks for the thorough reply!

I'm all in with Postgres, but the job isolation + built-in dashboard seem really appealing. I'll definitely give it a try!

Keep up the great work, love to see such high quality codebase / documentation / tooling!

Looks really neat! Starred on GitHub!

If you have heard of pg-boss [1], how does sidequest compare to it? I’m about to embark on some « jobification » on some flows and I’d love to have your opinion (possibly biased, but still)!

[1] https://github.com/timgit/pg-boss

We do something similar that we call « Office a la Zoom »:

Two times a week, the weekly standup is extended by an hour, from 15min to 1h15.

People are welcome to jump in and out of that open zoom that acts as a water cooler corner: any topic goes, from work to personal hobbies, etc

We’re fully remote (US / EMEA / APAC)

Brilliant work!

From another fellow « pdf’er »

Indeed very easy to code!

My point is about the need for a spec of this mechanism: without a spec, every company / org will roll out their own and result in 500 flavors of the same concept.

That’s where MCP shines: tool calling and tool discovery is already 1.5 years old (an eternity in ai land).

The MCP spec ensures that we can all focus on solving problems with tool calling rather than wasting time in cobbling together services that re not interoperable (because developed without a common spec / standard)