# 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="../../../workflow-builder/core-nodes/ai-agent-node">LLM Node</a></li><li><a href="../../../workflow-builder/core-nodes/ai-agent-node/prompting">Prompting</a></li><li><a href="../../../workflow-builder/core-nodes/ai-agent-node/tools">Tools</a></li><li><a href="../../../workflow-builder/core-nodes/ai-agent-node/advanced-settings">Advanced Settings</a></li></ul></td><td><a href="https://3697023207-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FFSlso1Kjob5CLDrh0dVn%2Fuploads%2FXQCuXvxgIoxdkxbpzpkT%2FScreenshot%202026-02-23%20at%206.38.36%E2%80%AFPM.png?alt=media&#x26;token=df1d8e03-4ace-40d1-847a-1a21b2370136">Screenshot 2026-02-23 at 6.38.36 PM.png</a></td></tr><tr><td><strong>Integrations</strong><br>Call external services and write results back.</td><td><ul><li><a href="../../../workflow-builder/apps">Apps</a></li><li><a href="../../../workflow-builder/outputs/action-node">Action Node</a></li></ul></td><td><a href="https://3697023207-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FFSlso1Kjob5CLDrh0dVn%2Fuploads%2FHUtoXULy3WwBKO4kbxDA%2FScreenshot%202026-02-23%20at%206.41.08%E2%80%AFPM.png?alt=media&#x26;token=3143f744-9d63-4bee-8770-b2d7c76d5133">Screenshot 2026-02-23 at 6.41.08 PM.png</a></td></tr><tr><td><strong>Control flow</strong><br>Branching, routing, and loops.</td><td><ul><li><a href="broken-reference">Logic</a></li><li><a href="../../../workflow-builder/utils-logic-and-others/logic/ai-routing">AI Routing</a></li><li><a href="../../../workflow-builder/utils-logic-and-others/logic/if-else-node">If/Else Node</a></li></ul></td><td><a href="https://3697023207-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FFSlso1Kjob5CLDrh0dVn%2Fuploads%2FhmXCDiCBzKRMgWR874AV%2FScreenshot%202026-02-23%20at%206.29.23%E2%80%AFPM.png?alt=media&#x26;token=b8513bda-1a84-4af4-b66f-43ccf3428ad8">Screenshot 2026-02-23 at 6.29.23 PM.png</a></td></tr><tr><td><strong>Error handling</strong><br>Fallback paths and troubleshooting.</td><td><ul><li><a href="../../../guides-and-tips/stackai-hacks/handling-errors-and-fallback">Fallback &#x26; Error Handling</a></li><li><a href="../../../guides-and-tips/stackai-hacks/troubleshooting-a-workflow">Troubleshoot a Workflow</a></li></ul></td><td><a href="https://3697023207-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FFSlso1Kjob5CLDrh0dVn%2Fuploads%2FkbGs5sS3Xx7GAQyZGFKC%2FScreenshot%202026-02-23%20at%206.27.04%E2%80%AFPM.png?alt=media&#x26;token=5ccb8626-fb0e-4967-baee-df8ca8572585">Screenshot 2026-02-23 at 6.27.04 PM.png</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](https://docs.stackai.com/getting-started/core-ai-concepts/instruction-vs-prompt)
* [Prompt Engineering](https://docs.stackai.com/getting-started/core-ai-concepts/prompt-engineering)
* [How to Improve LLM Performance](https://docs.stackai.com/workflow-builder/core-nodes/ai-agent-node/llm-hosting-and-governance/how-to-improve-llm-performance)
  {% 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](https://docs.stackai.com/workflow-builder/core-nodes/ai-agent-node)
* [Prompting](https://docs.stackai.com/workflow-builder/core-nodes/ai-agent-node/prompting)
* [Tools](https://docs.stackai.com/workflow-builder/core-nodes/ai-agent-node/tools)
* [Advanced Settings](https://docs.stackai.com/workflow-builder/core-nodes/ai-agent-node/advanced-settings)
  {% endstep %}

{% step %}

### 3) Add one integration

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

* [Apps](https://docs.stackai.com/workflow-builder/apps)
* [Action Node](https://docs.stackai.com/workflow-builder/outputs/action-node)
  {% endstep %}

{% step %}

### 4) Add routing and control flow

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

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

{% step %}

### 5) Measure and iterate

Evaluate workflow outputs. Monitor usage and errors.

* [Analytics](https://docs.stackai.com/agentic-adoption-and-security/observability/analytics)
* [Evaluator](https://docs.stackai.com/agentic-adoption-and-security/observability/evaluator)
  {% endstep %}
  {% endstepper %}