> For the complete documentation index, see [llms.txt](https://jamiewen00.gitbook.io/ai-engineering-handbook/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://jamiewen00.gitbook.io/ai-engineering-handbook/building-ai-products/fuzzy-land.md).

# Fuzzy Land

> Inspired by [Rethinking how we Scaffold AI Agents](https://www.youtube.com/watch?v=-rsTkYgnNzM\&t=523s)

Turning apps into AI systems creates fuzzy lands. When should you add fuzziness to your app?

## Fuzzy Zero

All exact land. No fuzz. Every step is set. User input is strict. Output never changes.

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-01a2627adfdeb730d441126baaf4e52c7b6e9e25%2Ffuzzy-0.jpg?alt=media" alt="image"><figcaption></figcaption></figure>

## Fuzzy UI

A small UI part is fuzzy land. Users type free text. Backend stays strict.

* Pros: UI feels smart.
* Cons: User input is wild. Output is same old, so what's the point? 🤷‍♀️

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-02f3018ad943c89c180a24d82fc9e251b2068750%2Ffuzzy-ui.jpg?alt=media" alt="image"><figcaption></figcaption></figure>

## Fuzzy UI: Clarify

Add steps to clarify what users want. Bridge fuzzy UI and strict backend. Set clear rules up front.

* Pros: Less confusion. Clear rules.
* Cons: More steps for users.

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-63178bfa8d25af7faaf879614f13b5df243a2ad6%2Ffuzzy-ui-clarify.jpg?alt=media" alt="image"><figcaption></figcaption></figure>

## Fuzzy API

Add a small fuzzy land to the API. For example, click to get insights.

* Pros: Fuzz is small. Most of the app is clear. Users know what to expect.
* Cons: Output is safe. Less wow.

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-816751346cf95392e9d6afcb5a5c8fec420b092c%2Ffuzzy-api.jpg?alt=media" alt="image"><figcaption></figcaption></figure>

## Constrained Flow

Exact-led fuzziness.

* Pros: Reliable. Good for the right job.
* Cons: Feels like workflow or automation, not very agentic. (if it does the job, why bother?)

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2FjgPDXyT2YdaC7Sce3TQq%2Ffuzzy-constrained.jpg?alt=media&amp;token=6e10840d-b798-446a-81fa-712f521412ce" alt=""><figcaption></figcaption></figure>

## Fuzzy Flow

Make the whole app a fuzzy land. It may contain some exact lands but it's a fuzzy-led experience. AI runs it all.

* Pros: If it works, it's huge. My attempts stay as fun prototypes.
* Cons: Hard to steer. Costly. Wild.

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-7bdd60bbb8de6ff48d54593ea62e3c9172fb83ee%2Ffuzzy-100.jpg?alt=media" alt="image"><figcaption></figcaption></figure>

## Appendix

My main takeaways from [Rethinking how we Scaffold AI Agents](https://www.youtube.com/watch?v=-rsTkYgnNzM\&t=523s):

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-e1339d67f624e30d3ca2ce98edabd84dc9064202%2Ffuzzy-flow.png?alt=media" alt="image"><figcaption></figcaption></figure>

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-03b7583f0f2b9237af9cb28a66da659c21292e0a%2Ffuzzy-table.png?alt=media" alt="image"><figcaption></figcaption></figure>