# Builder Path - Intermediate

## Intermediate builder path

Improve response quality. Integrate workflow actions. Implement routing and error handling.

### Outcomes

By the end, you will be able to:

* Configure the LLM node for consistent, structured outputs.
* Call at least one integration action from a workflow.
* Route execution using logic nodes.
* Implement fallback paths for expected failure modes.
* Evaluate results and monitor production usage.

### Quick jumps

<table data-view="cards"><thead><tr><th>Topic</th><th>Start here</th><th data-hidden data-card-cover data-type="image">Cover image</th></tr></thead><tbody><tr><td><strong>LLM configuration</strong><br>Tool use, settings, and reliability knobs.</td><td><ul><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/YjEQjSjqwYs4YdqzgwL9">LLM Node</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/bXdQDPCbUAF0P1kePQTz">Prompting</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/zHZW3c7ySYSkcDTyB5GN">Tools</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/xnjRMZjmgnc0IBxj3VOL">Advanced Settings</a></li></ul></td><td><a href="/files/Qj81Tt6j94ru9URhv9aq">/files/Qj81Tt6j94ru9URhv9aq</a></td></tr><tr><td><strong>Integrations</strong><br>Call external services and write results back.</td><td><ul><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/vf4ogE30dPrbepGzbZM0">Apps</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/Dm31MgnDl0Mj9OxKlI7k">Action Node</a></li></ul></td><td><a href="/files/qTxLFYfvDU5qTRcawto1">/files/qTxLFYfvDU5qTRcawto1</a></td></tr><tr><td><strong>Control flow</strong><br>Branching, routing, and loops.</td><td><ul><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/MTfF9Ykq5ixKqVv1Jy9F">Logic</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/RyGHbfepRiS6MbZ5Wa6b">AI Routing</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/RdhF2CKFrSstOtWaDDjp">If/Else Node</a></li></ul></td><td><a href="/files/pPIM6hkD0xSDEe2vIsRo">/files/pPIM6hkD0xSDEe2vIsRo</a></td></tr><tr><td><strong>Error handling</strong><br>Fallback paths and troubleshooting.</td><td><ul><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/RW9CA5BzKp03ejxJX354">Fallback &#x26; Error Handling</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/iUrAo2e5tc0hKLRGMYYw">Troubleshoot a Workflow</a></li></ul></td><td><a href="/files/IdWIs1BwAUqgPphSCn9K">/files/IdWIs1BwAUqgPphSCn9K</a></td></tr></tbody></table>

### The path

{% stepper %}
{% step %}

### 1) Establish a quality baseline

Define acceptance criteria and output format. Update prompts to consistently meet those requirements.

* [Instruction vs Prompt](/getting-started/core-ai-concepts/instruction-vs-prompt.md)
* [Prompt Engineering](/getting-started/core-ai-concepts/prompt-engineering.md)
* [How to Improve LLM Performance](/workflow-builder/core-nodes/ai-agent-node/llm-hosting-and-governance/how-to-improve-llm-performance.md)
  {% endstep %}

{% step %}

### 2) Configure the LLM node

Configure prompts and tools for structured outputs. Tune model settings based on latency, cost, and quality.

* [LLM Node](/workflow-builder/core-nodes/ai-agent-node.md)
* [Prompting](/workflow-builder/core-nodes/ai-agent-node/prompting.md)
* [Tools](/workflow-builder/core-nodes/ai-agent-node/tools.md)
* [Advanced Settings](/workflow-builder/core-nodes/ai-agent-node/advanced-settings.md)
  {% endstep %}

{% step %}

### 3) Add one integration

Integrate one application action. Validate the action inputs and outputs end-to-end.

* [Apps](/workflow-builder/apps.md)
* [Action Node](/workflow-builder/outputs/action-node.md)
  {% endstep %}

{% step %}

### 4) Add routing and control flow

Add routing and branching. Add explicit error handling for expected failure modes.

* [AI Routing](/workflow-builder/utils-logic-and-others/logic/ai-routing.md)
* [If/Else Node](/workflow-builder/utils-logic-and-others/logic/if-else-node.md)
* [Fallback & Error Handling](/guides-and-tips/stackai-hacks/handling-errors-and-fallback.md)
  {% endstep %}

{% step %}

### 5) Measure and iterate

Evaluate workflow outputs. Monitor usage and errors.

* [Analytics](/agentic-adoption-and-security/observability/analytics.md)
* [Evaluator](/agentic-adoption-and-security/observability/evaluator.md)
  {% endstep %}
  {% endstepper %}


---

# Agent Instructions: 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:

```
GET https://docs.stackai.com/getting-started/learning/stack-ai-curriculum/builder-path-intermediate.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.