> For the complete documentation index, see [llms.txt](https://future-ai-1.gitbook.io/future-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://future-ai-1.gitbook.io/future-ai/overview-future-ai/future-ai-executors/thesis-case-provider.md).

# Thesis case provider

#### A brief description of how to develop a test case for an AI service on Future-AI:

*As Future-AI currently supports only shell script, a provider cannot use popular programming languages such as Python, Java & Nodejs to develop their services.*

*When developing a test case, it must have at least three input arguments. The first one is used for the name of the data source that it needs to run, while the second and the third are the input and expected output respectively provided by the user. In some cases, the user's input may not be necessary, but we still need to reserve it for other cases. The expected output should be compared to the output of the data source, and if the output does not meet the requirement (of the test case) then we return **null**. This is very important, as currently, Future-AI only checks if the output of a test case is empty or equal to null. If it passes these conditions, the result from data source will be collected and considered valid. An example of a test case is:*

```
#!/bin/bash

# $2 should be reserved for test case input if necessary

func_result="`/bin/bash .futureaifile/"$1"`"
# $3 is the expected output
expected_output=$(echo "$3" |base64 --decode)
diff=$(echo "scale=2; $func_result - $expected_output" |bc) # |bc allows adding two 
# allow compare integer with float
if awk 'BEGIN {exit !('$diff' < 10000)}';
then 
  echo $func_result
else
  echo null
fi
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://future-ai-1.gitbook.io/future-ai/overview-future-ai/future-ai-executors/thesis-case-provider.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.