grouchy

It's been fun using this in our standups. Thanks for building this.

I have to keep asking the same questions. Do you think it could remember what I typically ask and generate or suggest it?

Glad you like the approach. When you give it a spin or look into the implementation please let us know what you think.

We are constantly improving tambo. It's crazy to see how much it's improved since we first started.

It get's it wrong sometimes but I think the alternative is the user getting it wrong trying to navigate your site.

I like to think how much time I spend clicking different nav links, clicking different drop downs trying to find the functionality I need.

It's just a new way for the app to surface what the user needs when they need it.

It does!

import { z } from "zod";

inputSchema: z.object({ query: z.string() });

or

import * as v from "valibot";

inputSchema: v.object({ query: v.string() });

or

import { type } from "arktype";

inputSchema: type({ query: "string" });

I'm curious what would make you say that? Because we haven't experienced this. We are being used a fortune 1000 fintech in production.

Any specific experience you had? or more specifics of where batteries included went to far?

Yeah, we've been following it closely. We already support the majority of the MCP spec and plan to add support for UI over MCP.

But our use case is a little different. MCP Apps embed interfaces into other agents. Tambo is an embedded agent that can render your UI. There's overlap for sure, but many of the developers using us don't see themselves putting their UI inside ChatGPT or Claude. That's just not how users use their apps.

That said, we're thinking about how we could make it easy to build an embedded agent and then selectively expose those UI elements over MCP Apps where it makes sense.

There's overlap for sure. I'd say we've built a more drop-in solution. We actually migrated to AG-UI events under the hood, and we have plans to expand cross-compatibility across standards.

The major difference is we provide an agent. You don't need to bring your own agent or framework. A lot of our developers are using our agent, really happy with it, and we have a bunch of upcoming features to make it even better out of the box.

Awesome to meet another tambonaut.

We love zod, we also support standard schema and thus most other popular typing libraries.

I'm curious how you found us?

Thank you. I just sent you an email. Looking forward to learning more about what you are building.

You install the React SDK, register your React components with Zod schemas, and then the agent responds to users with your UI components.

Developers are using it to build agents that actually solve user needs with their own UI elements, instead of text instructions or taking actions with minimal visibility for the user.

We're building out a generative UI library, but as of right now it doesn't generate any code (that could change).

We do have a skill you can give your agent to create new UI components:

``` npx skills add tambo-ai/tambo ```

/components

This had me laugh out loud.

I'd love to see a version of this that adds voice. Both input and telling the story.

This is cool. I wonder what it would like today with LLMs?

I'm not from the era of these games, but I remember trying them and finding them frustrating for the same reason.

But when I tried this, I literally couldn't stop. I could just write some random action.

It's actually amazing to me how many situations they were able to consider in the game, but having the LLM translate my language into the right action made the game feel way more natural.

I'd be interested in seeing how people can dress up these games with images, or more complex interactions. It could be a whole sub-genre.

Interesting, I'd love to figure out how we could do something like this in tambo.

Basically, listening to the user's interactions and suggesting different interfaces or tasks they could use for the assistant.

Thanks for sharing.

Has anyone found techniques to improve Claude's spatial/layout understanding?

It seems Nano Banana Pro can understand the layout/spatial well.

These apps will likely require extensive documentation.

The question is: Why expose it to the user if you can use an LLM to surface only the relevant information, contextualized to what they are doing?

We use this in our app, and it reads our docs to provide context when rendering the UI. I hope that most users never actually read our docs, and eventually learn to ask our app.

It can generally show the right UI, help them configure it, and use docs to ground it.

Interesting. I tried the demo and couldn't get it to work.

What are you using to modify the site for each person?

I can see how you personalize software with use, but how do you personalize a landing page before you have any user context?

Why do we need documentation?

I agree that the basic vs. advanced or persona A vs. persona B distinction is usually too rigid.

What makes you skeptical that AI will excel at this?

I guess what if you had Claude in the app, and it didn't just tell you what to do, it could even surface ephemeral UI for each task?

This is really what generative UI would enable.

Clippy!

The gamelike progressive tutorial idea is interesting. But games have a fixed learning path. Professional tools don't generally have that linearity.

Doesn't that suggest the "curriculum" has to be personalized? And if it's personalized, aren't we back to something generative?

I don't disagree that simple and repeatable wins—but isn't there a tension between "simple" and "capable"?

Excel is neither simple nor explicit, yet it's the most successful end-user programming tool ever made.

Could generative UI be a path to creating powerful tools feel simple by hiding complexity until needed, rather than dumbing down the tool itself?

I'll be honest, I don't remember this.

I'm suggesting you don't generally need menus. The pattern is closer to search like Apple Spotlight or Chrome New Tab... I think most people do that now instead of bookmarks or clicking through menus? Am I wrong?

I understand the anxiety, but isn't this already the reality with most complex software?

Photoshop has thousands of possible panel arrangements, yet users develop their own workflows.

The question isn't whether permutations exist—it's whether the system helps you find your optimal permutation faster. Do you think the problem is unpredictability itself, or the lack of a predictable meta-pattern for how changes occur?

Good wordplay. It's for sure a toy. It's hard to re-implement an entire spreadsheet.

What about it did you not like?

I'm curious what makes you say this? I feel like I discover how most sufficiently complex apps work by googling, or youtube.

I'm also not convinced this makes traditional methods: walkthroughs, support videos, trainings etc impossible?

My friend just discovered coding agents (lol), and he's constantly finding new things it can do for him...

"Oh it can ssh into my raspberrypi and run the code to test it. Wow"

That was an emergent property of the cli coding agent that had no "traditional" discoverability.

Forcing chat for every action when direct UI interactions worked fine is definitely not what I'm advocating.

I'm arguing for isn't chat-only interfaces. It's giving users both options: use the UI directly for quick changes you already know how to make, chat when you don't know where to find something or you have a complex multi-step task.

Different users will prefer different methods for different tasks. The goal is software that works how the user wants it to work, not just optimized for one interaction style.

Remote LLMs is a real constraint right now.

I'm hoping for a class of generative apps that can be run entirely locally. I believe it will exist, just not right now.

Good question. When I think about how people actually discover features, it's usually:

1) clicking through menus 2) reading docs/watching tutorials 3) getting hands-on help from a coworker or support person

Some apps try to do progressive disclosure as you get better at using them, but that's really hard to scale. Works okay for simpler apps but breaks down as complexity grows.

With generative UI, I think you're basically building option 3 directly into the app.

Users learn to just ask the app how to do something or describe their problem, and it surfaces the right tools or configures things for them.

Still early days though. I think users will also have to adopt new behaviors to get the most out of generative apps.