I'm optimistic that the ease of enforcing rules like this and better customer data (maybe via the apps) will lead to a better format. The annoyance grows from the rules causing us to be prompted to do or respond to things we don't want or need. When the taco bell guy asks if I want to add sour cream for the third time, I am getting pretty annoyed. I don't like sour cream, period. But every time they hit me with "would you like to double the chicken", even if I wasn't a yes upon driving to the window, I cave when they ask and both parties are probably happier for it. Management isn't totally wrong here because there are upsells that all of us would take when presented at the right time. It's a bit like ad targeting. Its just happening in realtime at the window.
So the problem in my mind is the format. How do you not ask 3 questions with every dish? Maybe the screens can help. Now that you have an AI that can follow the rules always and likely follow more complex decision trees quickly "at the window", it reasonable chains could start to dial in how this works to be more targeted and active vs passive at the right times.
I wish I was optimistic that data and compliant robots will be used to make things better for customers.
I think it's far more likely that they will, at best, be used to do whatever horrible and unpleasant things that temporarily juice sales numbers. Across our economy we'll see this play out in every customer service interaction. And a wave of perniciously persistent upselling attempts will wash over us all.
After a while, we won't stop noticing that the simple process of buying a soda requires saying no to 15 different requests to subscribe to a service, put our credit card on file, sign up for notifications, and consider buying cookies, a burger, and some fries. But our lives will be worse for it.
Anthropic just dropped “Claude for Financial Services”
-New models scoring higher on finance specific tasks
-MCP connectors for popular datasets/datastores including FactSet, PitchBook, S&P Global, Snowflake, Databricks, Box, Daloopa, etc
This looks a lot like what Claude Code did for coding: better models, good integrations, etc. But finance isn’t pure text, the day‑to‑day medium is still Excel and PowerPoint.Curious to see how this plays out in the long to medium term.
Devs already live in textual IDEs and CLIs, so an inline LLM feels native. Analysts live in nested spreadsheets, model diagrams, and slide decks. Is a side‑car chat window enough? Will folks really migrate fully into Claude?
Accuracy a big issue everywhere, but finance has always seemed particularly sensitive. While their new model benchmarks well, it still seems to fall short of what an IBank/PE MD might expect?
Curious to hear from anyone thats been in the pilot group or got access to the 1 month demo today. Early pilots at Bridgewater, NBIM, AIG, CBA claim good productivity gains for analysts and underwriters.
LLMs speak programmer well - they don't speak finance that well. To get much useable retraining or super agressive context / prompting (with teaching of finance principles) is needed otherwise the output is very inconsistent.
I find it helpful. Just drop a soup of numbers and ask "Is this business viable" and go from there. I have not used LLM specific for financial services, but ballpark figures and ideas were very useful for planning. Definitely a time saver and helps to iterate quicker.
I gave it a shot to iterate on our current UI. It did try to solve the problem we were focused on, but it also randomly removed other features that we hadn’t touched or even talked about. This makes me believe there will be a lot of back and forth that is low value just correcting small details. In UX/UI details really matter. I'd probably opt to just move pixels around my self in this case.
If this were a brand new project with no existing UI at all and we just needed to spin up a quick prototype, I think it’d be great for that. And honestly, I do think LLMs will end up playing a big role in UX design over time—so this is definitely in the right direction.
But for real-world use cases where the UI already exists and quality or timesaving matter, it doesn’t feel like the right fit yet.
Our largest customers generally use us to prototype brand new UIs versus existing ones, so you're spot on.
We're certainly better at new UIs versus existing UIs. Existing UIs are tough because you need to first recreate what you have in the codebase first. This is a large reason why we built a Figma-like canvas (https://www.magicpatterns.com/docs/documentation/projects/ge...), so that you can reference existing designs to make new ones.
So, for example, you could make your navbar, button, dashboard, and then click on that and reference it to make another design.
P.S. if you're open to it, open a support chat or DM me? Would love to help you get more value and see what prompts are causing it to remove stuff. It can also be really frustrating when it removes features — what can be helpful is going back a version or also editing the code by hand. We've had code edit since day 1. Totally aligned everything needs to be a prompt to get the small details right.
So the problem in my mind is the format. How do you not ask 3 questions with every dish? Maybe the screens can help. Now that you have an AI that can follow the rules always and likely follow more complex decision trees quickly "at the window", it reasonable chains could start to dial in how this works to be more targeted and active vs passive at the right times.