> For the complete documentation index, see [llms.txt](https://academy.pentaho.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.pentaho.com/solution-architect-path-sandbox/solution-architect/di-developer.md).

# DI Developer

The first course of the Solution Architect path: DI Developer. 53 lessons across 6 modules: build, run and operate Pentaho Data Integration pipelines, ending in a capstone project.

{% hint style="warning" icon="eye" %}
**SANDBOX — draft page.** Built from `developer-di-practitioner` 0.1.28 in Pentaho Content Manager. Module and lesson names, the reading-or-workshop kinds and the times come straight from each lab's manifest. Items marked REPLACE-ME need an owner's confirmation.
{% endhint %}

The first step on the Solution Architect path: learn Pentaho Data Integration the way a practitioner uses it. By the end you'll build, run and operate real pipelines — reading and writing files, databases and object storage, enriching and joining the data in flight, and packaging it all as parameterised jobs — and you'll have delivered a complete daily sales pipeline of your own as the capstone. It's the same course as PDI Developer, Level 1 — Practitioner.

{% columns %}
{% column %}

<p align="center"><i class="fa-file-lines" style="color:green;">:file-lines:</i><br><strong>53 lessons</strong><br><em>across 6 modules</em></p>
{% endcolumn %}

{% column %}

<p align="center"><i class="fa-flask" style="color:orange;">:flask:</i><br><strong>34 workshops</strong><br><em>hands-on labs</em></p>
{% endcolumn %}

{% column %}

<p align="center"><i class="fa-clock" style="color:cyan;">:clock:</i><br><strong>~14h 35m</strong><br><em>two to three days, or a week of evenings</em></p>
{% endcolumn %}
{% endcolumns %}

{% hint style="success" icon="cloud-arrow-up" %}
Every workshop is hands-on and runs on Pentaho's hosting platform. The Lab Guide is embedded in each lab and loads automatically when you open it — nothing to install.
{% endhint %}

***

<h3 align="center">Before you start</h3>

{% columns %}
{% column %}
{% hint style="success" icon="circle-check" %}
**What you'll need**

Familiarity with the basics of data integration — tables, files, keys and the idea of a pipeline. No prior Pentaho experience is assumed, and comfort with SQL will make the database and scripting modules go faster. The hosted lab provides Pentaho Data Integration, MySQL and MinIO, all started for you as you sign in.
{% endhint %}
{% endcolumn %}

{% column %}
{% hint style="info" icon="tag" %}
**Built against**

Pentaho Enterprise Edition **11.0.0.0-237**, the build every course on the Academy runs. The hosted labs run this exact release, so every screen, menu and dialog matches the guide step for step.
{% endhint %}
{% endcolumn %}
{% endcolumns %}

***

{% hint style="info" icon="trophy" %}

#### What you'll build

A complete Daily Sales Pipeline: a parameterised job that ingests CSV, JSON and master data, validates and enriches the rows, tracks historical changes with a slowly changing dimension, and loads a dimensional model. On the way there you'll have built pipelines against text, JSON, XML and Excel files, a MySQL database and MinIO object storage; joined, looked up and merged data in flight; scripted with Formula and JavaScript; and run it all through jobs with parameters and run configurations — the skills the Installation and deployment courses that follow take for granted.
{% endhint %}

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FaO0obPHxNqrN0tyoec8L%2Fcapstone-daily-sales-pipeline.svg?alt=media" alt="The capstone&#x27;s target design. The job runs Start, stage_orders, stage_customers and stage_products, then maintain_dim_region, build_fact, write_summary and Success; any entry&#x27;s failure hop leads to Mail and Abort job. Below, Filter rows sends the 3 sales rows missing a key to the rejects; valid orders get customer, product and region keys, then Formula, fact_sales.csv and the summary workbook."><figcaption><p>The job, and what its transformations do with the data</p></figcaption></figure>

***

<h3 align="center">Skills you'll gain</h3>

<table data-view="cards"><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><i class="fa-screwdriver-wrench" style="color:blue;">:screwdriver-wrench:</i> <strong>Tools</strong></td><td>Spoon · Pentaho client tools · server components · Kettle variables</td></tr><tr><td><i class="fa-diagram-sankey" style="color:blue;">:diagram-sankey:</i> <strong>Core pipeline</strong></td><td>Transformations · steps · hops · rows · run/preview cycle · logging · error handling</td></tr><tr><td><i class="fa-file-lines" style="color:blue;">:file-lines:</i> <strong>File formats</strong></td><td>Text · JSON · XML · Excel</td></tr><tr><td><i class="fa-database" style="color:blue;">:database:</i> <strong>Databases</strong></td><td>Connect, read and write · update, insert-update and delete · slowly changing dimensions · dimensional models</td></tr><tr><td><i class="fa-box-archive" style="color:blue;">:box-archive:</i> <strong>Storage</strong></td><td>Object storage with MinIO</td></tr><tr><td><i class="fa-diagram-venn" style="color:blue;">:diagram-venn:</i> <strong>Enrichment</strong></td><td>Database, merge, XML and row joins · lookups · merge-streams and merge rows (diff) · Formula · Modified JavaScript Value</td></tr><tr><td><i class="fa-gears" style="color:blue;">:gears:</i> <strong>Production</strong></td><td>Jobs · order of execution · parameters and variables · metadata-driven table onboarding · run configurations</td></tr><tr><td><i class="fa-trophy" style="color:blue;">:trophy:</i> <strong>Capstone — Daily Sales Pipeline</strong></td><td>One parameterised job · CSV, JSON and master data validated and staged · enriched and tracked with an SCD · loaded as a dimensional model</td></tr></tbody></table>

***

<h3 align="center">Course outline</h3>

<p align="center"><i class="fa-file-lines" style="color:green;">:file-lines:</i> reading · <i class="fa-flask" style="color:orange;">:flask:</i> hands-on workshop</p>

{% hint style="info" icon="circle-info" %}
Full lessons unlock once you're enrolled — this is the outline only. Times are the lab guides' own estimates.
{% endhint %}

<table data-search="false"><thead><tr><th width="382">Module</th><th width="115" align="center">Reading</th><th width="132" align="center">Workshops</th><th width="100" align="right">Time</th></tr></thead><tbody><tr><td>Getting Started</td><td align="center">1</td><td align="center">—</td><td align="right">~5m</td></tr><tr><td>Components &#x26; Concepts</td><td align="center">2</td><td align="center">5</td><td align="right">~1h 45m</td></tr><tr><td>Data Sources</td><td align="center">6</td><td align="center">13</td><td align="right">~4h 45m</td></tr><tr><td>Enriching the Dataset</td><td align="center">5</td><td align="center">9</td><td align="right">~3h 40m</td></tr><tr><td>Enterprise Solution</td><td align="center">5</td><td align="center">6</td><td align="right">~2h 20m</td></tr><tr><td>Capstone Project</td><td align="center">—</td><td align="center">1</td><td align="right">~2h</td></tr><tr><td><strong>Total</strong></td><td align="center"><strong>19</strong></td><td align="center"><strong>34</strong></td><td align="right"><strong>~14h 35m</strong></td></tr></tbody></table>

{% stepper %}
{% step %}

### <i class="fa-rocket" style="color:blue;">:rocket:</i> Getting Started

`1 reading · ~5m`

How to get the most out of this course, and how your lab environment is set up. A few minutes here makes every later lab smoother.

<details>

<summary>See the full breakdown</summary>

<table data-search="false"><thead><tr><th width="79"></th><th>Lesson</th><th width="90">Time</th></tr></thead><tbody><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Before You Start</td><td>~5m</td></tr></tbody></table>

</details>
{% endstep %}

{% step %}

### <i class="fa-lightbulb" style="color:blue;">:lightbulb:</i> Components & Concepts

`2 readings · 5 workshops · ~1h 45m`

The pieces of Pentaho and the vocabulary that runs through every later lab. Meet the client tools and server components, configure Spoon and the Kettle variables that drive it, then build a 'Hello World' transformation covering steps, hops, rows and the run/preview cycle — finishing with logging and error handling.

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2F65dap8b164wyXaMa4dng%2Fpentaho-architecture.svg?alt=media" alt="Spoon, with its Designer, Engine, Scheduler, Repository Browser and DB Explorer, sends .ktr and .kjb files to the Pentaho Server, whose engine, repository, Quartz scheduler, security and monitoring use a system database; Pan, Kitchen and Carte run standalone"><figcaption><p>Client tools and the Pentaho Server</p></figcaption></figure>

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FAPKJuvKAjuMJSBMiDbc6%2Ferror-hop-split.svg?alt=media" alt="CSV file input reads customers-100-with-errors.txt; the 97 rows that convert go to Dummy (do nothing), and the 3 rows that fail go down the error hop to Errors with errorCount, errorDescriptions, errorFields and errorCodes"><figcaption><p>Valid rows flow on; failed rows take the error hop</p></figcaption></figure>

<details>

<summary>See the full breakdown</summary>

<table data-search="false"><thead><tr><th width="79"></th><th>Lesson</th><th width="90">Time</th></tr></thead><tbody><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Components</td><td>~35m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Configuring Pentaho Data Integration</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Kettle Variables</td><td>~10m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Key Concepts</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Hello World</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Logging</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Error Handling</td><td>~10m</td></tr></tbody></table>

</details>
{% endstep %}

{% step %}

### <i class="fa-database" style="color:blue;">:database:</i> Data Sources

`6 readings · 13 workshops · ~4h 45m`

Read and write the formats and systems you'll meet daily — text, JSON, XML and Excel; relational databases, covering CRUID and slowly changing dimensions; and object storage with MinIO.

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FZiGzx99Jg6Nv6Jre8WQP%2Fdimension-lookup-update.svg?alt=media" alt="Dimension lookup/update for each row. Update mode looks up id in DIM_SCD at the stream date: a new key is inserted as version 1; for a found key, nothing differs: do nothing; an Update field overwrites the current version (type 1); a Punch through field overwrites every version; an Insert field closes the version and adds a new one (type 2). Lookup mode returns the found key&#x27;s TK, or TK 0."><figcaption><p>What the step decides for each row, in each mode</p></figcaption></figure>

<details>

<summary>See the full breakdown</summary>

<table data-search="false"><thead><tr><th width="79"></th><th>Lesson</th><th width="90">Time</th></tr></thead><tbody><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Overview</td><td>~30m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Flat Files</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Text File Input</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Text File Output</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Read JSON</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Read XML</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Excel Writer</td><td>~20m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Databases</td><td>~10m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review CRUID</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Connecting to Database</td><td>~5m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Reading from a Database</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Writing to a Database</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Table Update</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Table Insert - Update</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Deleting Records</td><td>~15m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review SCDs</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Slowly Changing Dimensions</td><td>~20m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Storage</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>MinIO</td><td>~30m</td></tr></tbody></table>

</details>
{% endstep %}

{% step %}

### <i class="fa-wand-magic-sparkles" style="color:blue;">:wand-magic-sparkles:</i> Enriching the Dataset

`5 readings · 9 workshops · ~3h 40m`

Shape data inside the pipeline: joins across databases, streams, rows and XML; lookups; merge-streams patterns; and scripting with Formula and Modified JavaScript Value when SQL alone isn't enough.

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FcD9d72f98KKS9v7yJ16X%2Fjoin-types.svg?alt=media" alt="Which rows each join keeps: inner keeps rows in A and B; left outer adds rows only in A; right outer adds rows only in B; full outer keeps all three"><figcaption><p>The four join types</p></figcaption></figure>

<details>

<summary>See the full breakdown</summary>

<table data-search="false"><thead><tr><th width="79"></th><th>Lesson</th><th width="90">Time</th></tr></thead><tbody><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Overview</td><td>~10m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Merge</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Merge Streams</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Merge Rows (diff)</td><td>~20m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Joins</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Database Join</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Join Rows</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Merge Join</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>XML Join</td><td>~30m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Lookups</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Database Lookups</td><td>~15m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Scripting</td><td>~20m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Formula</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Modified JavaScript Value</td><td>~10m</td></tr></tbody></table>

</details>
{% endstep %}

{% step %}

### <i class="fa-building" style="color:blue;">:building:</i> Enterprise Solution

`5 readings · 6 workshops · ~2h 20m`

Move from individual transformations to production: jobs, parameters and variables, metadata injection, and run configurations. Get your pipelines ready for scheduling, monitoring and shipping.

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2Fpwy3FiGxHlTxjqggyWm1%2Fjob-order-of-execution.svg?alt=media" alt="By default the job runs Transformation A, C and Success on one thread, then Transformation B; with Run Next Entries in Parallel on Start, A and B start together on two threads, and C still waits for A and Success for C"><figcaption><p>One branch at a time, or both branches at once</p></figcaption></figure>

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FERcj8jUkvJRMc7D2SFwh%2Fmetadata-injection-onboarding.svg?alt=media" alt="Two transformations: metadata_inject_step.ktr&#x27;s Data grids and file name feed ETL metadata injection, which fills in and runs metadata_inject_template.ktr, a CSV file input, Select values and Table output with no fields of their own"><figcaption><p>What you build: the metadata on the left fills the template on the right</p></figcaption></figure>

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FVDFWM5Bj85IjEcX6Kqab%2Fvariables-and-parameters.svg?alt=media" alt="Where the value of ${NAME} in a step comes from: a named parameter for one .ktr or .kjb, with its default or a value passed by Spoon, Pan, Kitchen or a job entry, which wins on a name clash; Set variables, for the rest of the job; and kettle.properties and the environment, for every run on the machine. A side note contrasts ${} text substitution with a ? marker the driver binds."><figcaption><p>Where a value comes from, and how far it reaches</p></figcaption></figure>

<details>

<summary>See the full breakdown</summary>

<table data-search="false"><thead><tr><th width="79"></th><th>Lesson</th><th width="90">Time</th></tr></thead><tbody><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Overview</td><td>~10m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Jobs</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Hello World (Job)</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Order of Execution</td><td>~10m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Metadata Injection</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Onboarding to a Table</td><td>~20m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Parameters</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Parameters</td><td>~10m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Parameters SQL</td><td>~10m</td></tr><tr><td><i class="fa-file-lines" style="color:green;">:file-lines:</i></td><td>Review Scalability</td><td>~15m</td></tr><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Run Configurations</td><td>~15m</td></tr></tbody></table>

</details>
{% endstep %}

{% step %}

### <i class="fa-trophy" style="color:blue;">:trophy:</i> Capstone Project

`1 workshop · ~2h`

Bring it all together: build a parameterised job that ingests CSV, JSON and master data, validates and enriches the rows, tracks historical changes with an SCD, and loads a dimensional model — a complete, interview-ready pipeline.

<figure><img src="https://4232202144-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPeIhSpTGdExnuti9odGI%2Fuploads%2FFJON7Nkv4Yqv8JbMVPFn%2Fcapstone-data-model.svg?alt=media" alt="The capstone&#x27;s data model. The four input files load stg_orders (37 orders, 3 rejected), stg_customers, stg_products and dim_region, a Type 2 dimension keyed by region_sk. fact_sales takes region_sk and region_name from dim_region and revenue and gross_margin from Formula; its 37 rows go to fact_sales.csv and a summary workbook: 5 regions, 10113.31 revenue, 37 orders."><figcaption><p>The data model: the tables the job loads, and where each fact column comes from</p></figcaption></figure>

<details>

<summary>See the project brief</summary>

<table data-search="false"><thead><tr><th width="79"></th><th>Lesson</th><th width="90">Time</th></tr></thead><tbody><tr><td><i class="fa-flask" style="color:orange;">:flask:</i></td><td>Daily Sales Pipeline</td><td>~2h</td></tr></tbody></table>

You're a freshly onboarded data engineer at a regional retailer. The analytics team needs **yesterday's sales** ready by 9am every morning, joined with customer and product master data, with historical attribute changes tracked, validated, and loaded into a dimensional model the BI tools can query.

</details>
{% endstep %}
{% endstepper %}

***

<h3 align="center">Exam &#x26; accreditation</h3>

{% columns %}
{% column %}
{% hint style="info" icon="clipboard-check" %}
**The course exam**

40 questions drawn at random from a pool of 50, covering the five taught modules — Getting Started, Components & Concepts, Data Sources, Enriching the Dataset and Enterprise Solution. The pass mark is 80%. It's open-book: browse any module or ask the AI assistant while you work. The Capstone Project is assessed by its own lab checks rather than by the exam.
{% endhint %}
{% endcolumn %}

{% column %}
{% hint style="warning" icon="file-certificate" %}
**Course accreditation**

Finish the lessons and workshops, pass the exam and complete the capstone's checks, and you'll automatically be able to download your course accreditation — Pentaho Data Integration Developer. It states your name, the course and the Pentaho version you studied against, and is valid for two years. The exam is self-paced and not proctored.

This course is the first step on the Certified Solution Architect learning path: DI Developer, then Installation, then the Containers, High Availability and Enterprise Security Speciality courses, leading to the Certified Solution Architect credential — which closes with a proctored exam delivered through Kryterion's Webassessor.
{% endhint %}
{% endcolumn %}
{% endcolumns %}

***

<p align="center"><a href="https://academy.pentaho.com/solution-architect-path-sandbox/solution-architect/installation.md" class="button primary" data-icon="arrow-right">Next: Installation</a></p>

<p align="center"><a href="https://academy.pentaho.com/solution-architect-path-sandbox/solution-architect.md" class="button secondary" data-icon="arrow-left">Back to the Solution Architect path</a></p>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://academy.pentaho.com/solution-architect-path-sandbox/solution-architect/di-developer.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
