Back to News
Advertisement

Show HN: Give your AI agent on-screen guides that show users where to click

ppancomplex about 3 hours ago 4 comments

DE version is available. Content is displayed in original English for accuracy.

Hey HN. I'm Christian, one of the founders of Frigade (YC W23). I've noticed that a lot of in-app AI agents struggle to actually understand the products they exist in.

For instance, let's say a user asks an agent how to do something in a given SaaS product. In an ideal case, maybe that agent replies saying it has a tool to do the task and just automates that work entirely for the user. That's a great outcome.

But often that's not the case. Maybe there is no tool call for that exact task, or maybe the user's question is best solved by a specific UI workflow or interface. In these cases, many agents tend to fall back on basic RAG on their help center, or sometimes even searching the internet for an understanding of their own product. This can be a very slow process and most of the time help center articles are outdated as products evolve faster than them today. Even worse, no one likes reading a long list of bullets and mapping that back to a UI.

My tool (Assist API) solves this gap with a single tool call defined like this:

  const frigade_guide_tool = {
    description: 'Call this tool to answer product questions or guide the user through a task.',
    parameters: {
      query: {
        type: 'string',
        description: 'What the user is asking or wants to do',
      },
    },
    run: ({ query }) => frigade.assist({ query }),
  }
Here's a demo I recorded on how to set it up with the Vercel AI SDK: https://www.youtube.com/watch?v=9WQ0UbLjC6I

When called, the tool will do the following:

1) Gather context on what the user is seeing on screen, their permissions, feature flags, and more. Then one of the following:

2a) If solvable: Generate an on screen guide for how to fix a given problem

2b) If conceptual: Return text describing to the parent agent how to solve the problem

2c) Reject (i.e. unable to help)

How does the tool know what to do?

The tool learns a given application UI by using a browser-based agent. You provide a test account to your software (i.e. staging og preview), and a browser agent logs in and works its way through the entire product. It then builds its own map of how the application works which can the be queried about any product-related question or how to get from A to B in the UI. It also writes its own documentation from this map. The agent re-runs on a schedule or can be triggered through CI/CD.

Docs and more details: https://frigade.com/assist-api

Advertisement

⚡ Community Insights

Discussion Sentiment

50% Positive

Analyzed from 126 words in the discussion.

Trending Topics

#improve#itself#llm#projects#actually#build#product#shit#top#blog

Discussion (4 Comments)Read Original on HackerNews

mox1•about 1 hour ago
Could this be utilized to improve the actual UI itself? As a somewhat naive LLM user, I have often found that when coding up projects, when you get into the area of the UI (in projects with a web-front end), the LLM immediately reaches for curl...which feels like a very inefficient way of debugging or changing a UI....
pancomplex•32 minutes ago
Yes for sure. We actually use the map we build of the UI + the questions people ask to automatically identify product gap patterns. These are the presented in a dashboard where you can use these insights to improve the product itself.
doot•34 minutes ago
What if we just built less shitty software instead of layering more shit on top of shit on top of…
pancomplex•22 minutes ago
Very much agree with the sentiment here - I actually even wrote a blog post about this specific issue lately. There's an entirely separate issue of AI slop ruining well-defined clean applications: https://frigade.com/blog/easier-to-build-not-easier-to-use