tldr the initial effort didn't seem to read the linked article so I copied and pasted the full text in

Luckily ChatGPt does a pretty good impression https://chatgpt.com/s/m_6a6662e9af6c81918523fb06d1384e74

My concern is that with all the bundling that the model labs are doing the lock-in becomes harder than anticipated to unwind

(It’s often easier to see what a feature does to reduce costs though)

We've started trying to do some comparison videos to capture more of the UX vs speed vs cost stuff e.g. https://www.linkedin.com/feed/update/urn:li:activity:7479891... which one of my team did for my LinkedIn account (disclaimer: marketing)

(In this particular case Deepseek was way slower than GPT 5.5 but I think that's because it installed Libreoffice half-way through the task!)

But that does make it more complex to build simple information retrieval use cases.

The Chrysler museum in Norfolk VA has amazing free demonstrations almost every day which are amazing if anyone happens to find themselves in Southern Virginia.

Honestly though we are finding that a little FDE to set up pre-bake stuff that’s sufficiently specific to the customer is needed. Otherwise people are like, “I don’t need to close the books, I need to do a per-working-day profitability analysis for 10 EU countries with different public holidays”, and they get stuck there.

I was skeptical but it gets a 68 NPS from users, even if we do get the occasional "why are you investing in AI I hate it" coming through the feedback channel.

As ever, the issue is "what problem are you solving". If it's that you want more people to put their hand up and talk to you/order something, chatbots seem like a bad solution. If it's that you have a ton of complex docs that people have to read in order to implement and use your product, it's not the solution but it's probably part of a solution.

We (harriethq.com) also have a somewhat similar insight, which is that setting up connectors is a drag for non-technical users, and a lot of systems don't support per-user connectivity so need an API shim.

The thing I like about this (Agent Vault) approach is that it's more extensible than what we're offering, which is a full managed service. But we've found that some features (e.g. ephemeral sandboxes to execute arbitrary e.g. uvx/npx based mcps) are just a big pain to self-deploy so it's easier for us to provide a service that just works out of the box.

Kudos to the team, this looks great and I'm looking forward to playing with it

All the Google Docs MCPs out there seem to be broken in annoying ways so I thought I'd make one. For instance they do character-offset-based editing and LLMs are reliably terrible at counting characters.

This one just works. (It uses the similar pattern-matching search and replace that code editor harnesses use for file editing to minimize token usage and latency).

There are some showstoppers still. The most annoying is that Google Docs comments API is has been broken for over a decade (sic). I (well, Claude) build a workaround that involves inserting a bookmark with the Apps Script API and linking to that bookmark from the comment. It's hacky but for a lot of LLM-based workflows like contract review or similar it gets you 80% of where you want to be - you can say something like "add comments and john@lawfirm.com for anything that you want their opinion on".

I hope people find it useful. Install involves the usual dance with Google Cloud API console; apologies in advance for taking some happiness from your day.

Comments URL: https://news.ycombinator.com/item?id=47865132

Points: 2

# Comments: 0

Sure, they could do that, but the cultural change required is an order of magnitude harder than just sticking an agent on top of their source-of-truth and believing that the problem is solved.

Maybe it works for areas where the application is a relatively self-contained island of productivity. Figma is somewhere that a designer spends a lot of their day, so it's going to be less vulnerable, but most pieces of softare fit into broader workflows. So for Figma the disruptor is less likely to be "AI-powered designer" and more "AI-powered web builder" - e.g. Lovable or even Claude Code itself that just generates great designs.

I assume we are talking

- China - maybe South Korea? - US (or is US not one of the 4?) - Russia (ok this is explicit)

I think there might be an interesting idea in here but there is some confusion that’s stopping it coming out

Can someone enlighten me?

IANAL but e.g. Claude Cowork is already good enough that it's hard to see how the legal tech startups are going to differentiate except around access controls, visual presentation of workflows, etc. And that's in a heavily enterprise/compliance-aware/security-focused context.

Don't get me wrong, that's still a big "except" - big enough for massive companies to be built. Personally the anxiety of being so close to being squashed by the foundation models would make me unhappy as an entrepreneur but looking at the market it seems like many people have a higher risk tolerance.

Now, that may not work in all jurisdictions for reasons of local taxation etc (and you'll have to work out payroll tax, benefits etc) but that's almost never anything to do with the legal entity type!

How is that different from trust erosion?

Re-read “The Art of Not Being Governed” by James C Scott which is really mind-expanding stuff.