kushagrchitkar

This is an interesting edge case. When something similar happened, Almanac texted me asking for an update if I had followed up on email, and then I mentioned that I had followed up. So in this sense there was a HITL. A good solution could be to have account provenance for tasks, so that disconnection on accounts could update stale context

We have been debating what the best benchmark to show would be. I'd love to test it out on long horizon tasks, but then we're thinking of best to make the base wiki to test it out

Forgot to reply instantly, but its gone now: https://usealmanac.com/pricing

I agree with the take. This was on the roadmap, but given the responses today, we will make permissions inside the company a bigger priority. To brainstorm, would you want the ability to define teams inside a company as well? I was thinking admins/owners could create teams and select the people they want, and then their permissions

Hey, glad you found it interesting to work on. We're not looking for interns right now, but shoot me an email at [email protected], would love to keep people in mind

Its GPT-5.6-terra under the hood. Also we want to control the harness. Features like proactivity/long tasks are not possible the way Claude/Codex work today. We do plan on releasing our desktop app, which would have these things inbuilt.

Wiki updates happen once a day through. That is when the entire day's context is updated in the wiki. That is when the fact disappearance would take place

The current permission implementation is binary. It is either personal to you, or is shared with everyone in the company. Having more granular permissions is something that has been requested often, and it is on our roadmap. I'm curious, how does Microsoft WorkIQ handle these permissions?

Thank you

There is truly a lot of competition in the space. The reason we're confident we stand out is because of our wiki layer. We have seen both the benefits of having a detailed compiled wiki, and more importantly, actually using this layer to then power capabilities. Two such examples are written in the post as proactive agents and the handling long horizon tasks. I believe this is still just scratching the surface. Having the perfect context layer makes every single task you do with agents much moe powerful

Currently we don't allow for multiple model selection, but it is on the roadmap. We do have a cli, which allows you to use the wiki layer and the tools in whatever harness you prefer. Further, we want to allow users to also bring their own keys/subscription.

We do not have formal benchmarks to measure improvement in performance. A big reason is that most benchmarks are very "atomic facts memory" focused. They'd give a huge passage, conversations, and see which memory system could surface those facts. How we're different is agents could be simply given the markdown files, and they can pretty much get the perfect context themselves. Second, we are banking more on the fact that having this layer enables new capabilities of the models

I'd love to hear how you're approaching this problem, and what would you like to see on the website to convince you to try out Almanac

Thanks! I saw the video again and can't look beyond the low resolution now lol. We knew from day 1 that trusting agents is going to be the most difficult part of our product, so we take privacy and security with the utmost seriousness

The documentation is not just for lookup queries. Having this layer betters the quality of responses, but also enables a lot of features we have in Almanac/plant to add. I mentioned in the post how this layer enables proactive agents and long horizon tasks. I just came across a Google paper yesterday (https://arxiv.org/html/2608.27454v1) that use a similar wiki knowledge base to self improve agent skills. I think these are just scratching the surface of ideas of what's possible with this layer

Just checked out WorkIQ, the promise is quite similar. Spend compute and time upfront developing the knowledge base, which will later result in much better answers

For us, these two things have not been very different. We do make both, a personal and a company wide wiki, so Almanac is useful in both regards

Our browser is interactive, in the sense that one could click around the browser, as well as the agent. Usually for 2FA logins, Almanac would hand it over to the human, who'd complete login, and then continue.

We use Browserbase for the browser and session persistence is inbuilt.

For ToS violations, this is a limitation. Accessing sites that don't allow for bot access could result in account ban/suspension. Simply using Browserbase under the hood does not remove this risk.

It of course gets more magical the longer you use it, but we've felt it starts providing utility from first few days itself. It could identify things that are going on immediately in your life and help there