Document how to use Tilebox with LLMs

ai-assistance.mdx

@@ -0,0 +1,49 @@
+---
+title: AI Assistance
+description: LLMS are a powerful tool for exploring and learning tools such as Tilebox. This section covers how to easily provide them with Tilebox specific context to get tailored and up-to-date responses.
+icon: brain-circuit
+---
+
+## Providing Tilebox specific context
+
+AI Assistants and Large Language Models (LLMS) can help you answer questions and provide guidance on how to use Tilebox, give you hints about relevant sections in the docs related to your questions and even help you creating your first workflows.
+
+<Card title="Download Documentation for LLMs" icon="brain-circuit" href="https://docs.tilebox.com/llms-full.txt" horizontal>
+Download the complete Tilebox Documentation as a plain text file to provide it to your AI assistant or large language model.
+</Card>
+
+The full content of the Tilebox Documentation is available in plain markdown format at [https://docs.tilebox.com/llms-full.txt](https://docs.tilebox.com/llms-full.txt). Upload this document to an AI Assistant or a large language models to provide Tilebox specific context.
+
+<Tip>
+The [Documentation Context](https://docs.tilebox.com/llms-full.txt) is always updated when the documentation changes. In case you download it, refresh it from time to time to also always stay up to date.
+</Tip>
+
+## Example prompt
+
+After you have uploaded the [Documentation Context](https://docs.tilebox.com/llms-full.txt) to your AI assistant or large language model, you can now prompt it with questions and get tailored and up-to-date responses.
+
+Below prompt is an example of how your AI assistant can help you get started with Tilebox.
+
+```txt Example prompt
+Generate a script that
+
+- Creates a cluster
+- Configures console logging
+- Contains a Fibonacci calculator workflow that is using a local filesystem cache.
+  Make sure you get task dependencies right.
+  Make sure to only print the final result as the last step of the workflow.
+  Write logs to let us know what is happening.
+- Submits a job for the number 7
+- Starts a processing runner
+
+Do not invent APIs. All available Tilebox APIs are documented.
+```
+
+## Claude
+
+[Claude 3.5 Sonnet](https://docs.anthropic.com/en/docs/about-claude/models) is a great choice for an AI assistant to get started with Tilebox. To provide it with Tilebox specific context, create a [new project](https://support.anthropic.com/en/articles/9517075-what-are-projects), and then upload the [llms-full.txt](https://docs.tilebox.com/llms-full.txt) as project knowledge.
+You can then prompt it with questions or use it to generate scripts. Check out the [example prompt](#example-prompt) to get started.
+
+## ChatGPT
+
+Experiments with [GPT-4o](https://chatgpt.com/?model=gpt-4o) have lead to mixed results so far. It worked well for answering questions, but it struggled to generate workflow scripts, often imagining APIs or using them in subtly wrong ways. You may want to consider using [Claude 3.5 Sonnet](#claude) instead.

api-reference/workflows/creating-task-runner.mdx

@@ -4,7 +4,7 @@ description: How to create a task runner
 icon: list-check
 ---
 
-From a [client instance](/workflows/creating) you can create a [TaskRunner](/workflows/concepts/task-runners), capable of executing tasks.
+From a client instance you can create a [TaskRunner](/workflows/concepts/task-runners), capable of executing tasks.
 
 <RequestExample>
 

api-reference/workflows/submitting-job.mdx

@@ -4,7 +4,7 @@ description: How to submit a job
 icon: diagram-project
 ---
 
-To execute a workflow, you first need to submit a [job](/workflow/jobs) to the Tilebox API.
+To execute a workflow, you first need to submit a [job](/workflows/concepts/jobs) to the Tilebox API.
 This can be done by calling the `submit` method of a `JobClient` instance.
 
 <RequestExample>

api-reference/workflows/task-inputs.mdx

@@ -4,7 +4,7 @@ description: How to define task inputs
 icon: laptop-code
 ---
 
-A task can optionally define [input parameters](/workflow/tasks#input-parameters).
+A task can optionally define [input parameters](/workflows/concepts/tasks#input-parameters).
 These parameters are defined as class attributes, the same way as you would define a dataclass.
 
 <RequestExample>

datasets/introduction.mdx

@@ -53,7 +53,7 @@ Here are some terms used throughout this section.
 
 Prerequisites
 
-- You've [installed](/sdks/python/installation) the `tilebox-datasets` package
+- You've [installed](/sdks/python/install) the `tilebox-datasets` package
 - You've [created](/authentication) a Tilebox API key
 
 With the prerequisites out of the way, you can now create a client instance to start interacting with your Tilebox Datasets.

mint.json

@@ -54,6 +54,7 @@
         "introduction",
         "quickstart",
         "console",
+        "ai-assistance",
         "authentication"
       ]
     },

vale/styles/write-good/TooWordy.yml

@@ -188,7 +188,6 @@ tokens:
   - requirement
   - reside
   - residence
-  - retain
   - satisfy
   - shall
   - should you wish

workflows/concepts/clusters.mdx

@@ -34,7 +34,7 @@ Before registering a task runner, or submitting a job, you need to create a clus
 clusters as needed. The following sections illustrates how to do this.
 
 To manage clusters, you first need to instantiate a cluster client. You can do this by calling the `clusters` method on the
-[workflows' client](/workflows/creating).
+workflows' client.
 
 <CodeGroup title="Instantiating a Clusters Client">
     ```python Python (Sync)
@@ -132,7 +132,7 @@ To delete a cluster, you can use the `delete` method and pass in a cluster's slu
 
 ## Jobs spanning different clusters
 
-[When submitting a job](/workflows/job) you need to specify the cluster that the job should be submitted to.
+[When submitting a job](/workflows/concepts/jobs) you need to specify the cluster that the job should be submitted to.
 This allows you to target a specific group of task runners for a particular job. All sub-tasks within the job are
 submitted to the same cluster by default. This can also be manually overridden to submit sub-tasks to other
 clusters if needed. Check out the example below to see how this can be done.

workflows/concepts/jobs.mdx

@@ -20,7 +20,7 @@ Once a job is submitted, its root task is scheduled for execution, and any [elig
 may pick it up and execute it.
 
 For submitting a job, a job client needs to be instantiated first. This can be done by calling the `jobs` method on the
-[workflows' client](/workflows/creating).
+workflows' client.
 
 <CodeGroup>
 ```python Python (Sync)
@@ -115,7 +115,7 @@ and [dependencies](/workflows/concepts/tasks#dependencies), it's possible to vis
 Assuming you have submitted a job, you can use the `display` method on the job client to display the execution of the job as a graph diagram.
 
 <Note>
-    The `display` method is designed to be used in an [interactive environment](/sdks/python/jupyter), such as a Jupyter notebook.
+    The `display` method is designed to be used in an [interactive environment](/sdks/python/sample-notebooks#interactive-environments), such as a Jupyter notebook.
     In non-interactive environments, use `job_client.visualize` instead which returns the rendered diagram as a string
     in the SVG format.
 </Note>