With how we build it, the content doesn't really matter. The AI and Typesense embedding model handles many of the relationships, so the AI tools don't need to do all the work. Mostly just calling "search_knowledge".
Most teams do not suffer from a lack of information. They suffer from context being scattered across notes, chats, docs, URLs, tickets, and AI sessions, with no reliable way to retrieve the right piece at the right time. Even a good search is not enough if the underlying memory layer is fragmented or opaque.
We have not seen many setups that preserve context and decisions well over time without ongoing cleanup. Usually, people fall back on some combination of repeated prompting, summaries, manual docs, or isolated memory within a single tool. That works for a while, but it decays.
Our view is that the better approach is not endless summarization. It provides teams with a shared memory layer where notes, decisions, URLs, and reusable context remain inspectable, editable, and portable, so retrieval has something durable to work with in the first place.
We have customers with the same requirements and they started using my system at https://helpmonks.com
They are conversing internally with it. You can also use Slack to get notified. If a conversation is worth it they then either use the Trello plugin to create a card there or link to a new conversation in Discourse.
I've looked at all the providers and couldn't find one that was flexible enough and also isnt overcharging, I.e. paying for the service, credit card charges, payment gateway, etc.
That said, I've found cheddargetter to work quite nice. Has an API, includes the payment gateway, and provides enough flexibility for custom prices per subscription. So far I've implemented three startups with it.
Helpmonks (https://helpmonks.com) is being used by a lot of startups. One of the main reasons is because the price is based on mailbox(es) and not on users.
I already did some time ago. I got a surface pro and until you own one you don't know what you are missing. The form factor is simply awesome.
Then I also used to have a xps13 with Ubuntu. Great machine.
I've recently switched to a T460s with 20gb ram, 1tb SSD and i7. Comes with all the ports you need and want. It's light and fast. Used to run Ubuntu for a while full time. Recently switched to windows 10 and the WSL is a game changer. Reminds me of the good old Mac days.
I don't think there is an issue with email per se. It's more that there hasn't been much "evolution" in its use.
Though, Google and other companies have definitely tried to make email "better".
After an elaborate phase of talking to hundreds of companies, I've created a platform that has the approach of "collaborative email". It's providing an additional layer to email that helps companies to keep track of all those customer emails (you can check it out at http://helpmonks.com).
In any case, I think in adding additional service around email is where the real disruption lies.
Most teams do not suffer from a lack of information. They suffer from context being scattered across notes, chats, docs, URLs, tickets, and AI sessions, with no reliable way to retrieve the right piece at the right time. Even a good search is not enough if the underlying memory layer is fragmented or opaque.
We have not seen many setups that preserve context and decisions well over time without ongoing cleanup. Usually, people fall back on some combination of repeated prompting, summaries, manual docs, or isolated memory within a single tool. That works for a while, but it decays.
Our view is that the better approach is not endless summarization. It provides teams with a shared memory layer where notes, decisions, URLs, and reusable context remain inspectable, editable, and portable, so retrieval has something durable to work with in the first place.