Ok so planning was good on Claude but after following @trq212's prompt on using the AskUserQuestionTool I will never plan any other way...will show a demo on this for a feature later.
@trq212@tejasmanohar@trq212 i'd love to chat with you. we've seen some cool use cases internally but would love to hear more for you about production use cases
the best way to understand where AI is heading is by both paying attention to what @signulll and @levie are saying here and seeing that both will be true.
I think there are lots of examples where generated software and UI will work on demand, in particular in a personal context when the stakes are low and it’s just a byproduct of a chat system’s response.
But I would have different expectations in an enterprise context. The point of much of the software that we use in the enterprise is largely to just keep our processes on track and moving forward reliably. With high SLAs.
These are some of the most foundational things to a business. How companies close their books at the end of a quarter, manage their client records, handle inventory, organize their contracts, pay their employees, build new products, and so on.
For any of these workflows and data sets, you need a high degree of stable patterns in your workflows that you know will work every single time. Also, importantly, you’re paying the software vendor to think about the underlying process so you don’t have to, keep the software up-to-date with new regulations or industry trends, and so on.
Most companies just simply don’t want to have to reinvent the wheel on HR, CRM, contract management, etc. And even when AI models could code these up on demand, they’ll do so just a literally differently every time, which would be quite chaotic for many of these workflows. And maintenance will be fully on you.
Now, what I do agree with is that we will interact with our software in very different ways in the future. We will begin to prompt most of our software to get answers back, and we will have agents running in the background of most software doing work for us. When we interact with those agents, they will certainly frequently render interactions that are relevant to the workflows customized to us.
But under the hood, there will still be deterministic systems for our core data and workflows, and that maintain the guardrails that AI agents adhere to. This is the future I’d bet on.
Love this conversation,, and hope it keeps happening. Also happy for any arguments as to why I’m wrong.
I think there are lots of examples where generated software and UI will work on demand, in particular in a personal context when the stakes are low and it’s just a byproduct of a chat system’s response.
But I would have different expectations in an enterprise context. The point of much of the software that we use in the enterprise is largely to just keep our processes on track and moving forward reliably. With high SLAs.
These are some of the most foundational things to a business. How companies close their books at the end of a quarter, manage their client records, handle inventory, organize their contracts, pay their employees, build new products, and so on.
For any of these workflows and data sets, you need a high degree of stable patterns in your workflows that you know will work every single time. Also, importantly, you’re paying the software vendor to think about the underlying process so you don’t have to, keep the software up-to-date with new regulations or industry trends, and so on.
Most companies just simply don’t want to have to reinvent the wheel on HR, CRM, contract management, etc. And even when AI models could code these up on demand, they’ll do so just a literally differently every time, which would be quite chaotic for many of these workflows. And maintenance will be fully on you.
Now, what I do agree with is that we will interact with our software in very different ways in the future. We will begin to prompt most of our software to get answers back, and we will have agents running in the background of most software doing work for us. When we interact with those agents, they will certainly frequently render interactions that are relevant to the workflows customized to us.
But under the hood, there will still be deterministic systems for our core data and workflows, and that maintain the guardrails that AI agents adhere to. This is the future I’d bet on.
Love this conversation,, and hope it keeps happening. Also happy for any arguments as to why I’m wrong.
I spent my Saturday (I know...) at the inaugural Agentic AI Summit hosted at UC Berkeley, and I am starting to hear the same refrain regarding the biggest hurdles for AI adoption in the enterprise.
TL;DR: the real blocker isn't the AI. It's the three usual suspects :
> Data: Enterprises deal with scattered, outdated, and poorly documented data. Many realize that their valuable knowledge lives in people's minds and is not documented, hence cannot be presented to AI.
> Governance: As May Habib from Writer put it, with AI, "you are really trying to contain behavior vs securing a workflow." Many enterprises know their current permissions aren't ready for AI, and worse, they fear AI will make it easier to surface sensitive data.
> Reliability: Drop-off across multi-step workflows is a major concern even with good data. Unacceptable for critical tasks, especially the ones taking mutative actions.
My takeaways : 1) enterprises will find the most immediate success by targeting greenfield use cases 🌱 and 2) they should probably start the work of mapping how work actually gets done for a smoother transition
Mocha (@get_mocha) is an AI-powered no‑code app builder that turns your idea into a live website in minutes.
It integrates everything: database, backend, UI, deployments— no coding skills needed. Just chat with Mocha and ship to production.
https://t.co/TpWxmwQGGW