> For the complete documentation index, see [llms.txt](https://docs.codewords.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.codewords.ai/~/revisions/2IgKSsIuX4bzBsMZVaMc/guides/tips-and-tricks.md).

# Tips and Tricks

### **Be Specific About Your Goal**

To get the best results from Cody, start with a clear, specific description of what you want to accomplish.

\
What **Doesn't Work**:

{% hint style="warning" %}

1. "I need something for social media"
2. "Make a workflow that helps with marketing"
3. "I want to automate my business"
   {% endhint %}

What Works **Great**:

{% hint style="success" %}

1. handwritten"Create a workflow that will scrape website X and summarise the content and email me the response"
2. "Build me a workflow that scrapes Google review data for restaurants and saves it into a CSV file "
3. "Build me something can extract text data from an image of a handwritten letter"
4. "Create a workflow that transcribes a YouTube video, distills it into notes, and stores it in my Google Doc"
   {% endhint %}

The difference is clear: Cody needs to understand the specific business problem you're solving.

### **Focus on Outcomes, Not Tools** 

Instead of asking for specific technologies, describe what you want to achieve 

**Don't Focus on the How:**

* "I need a web scraper"
* "Build me an AI thing"
* "I want to use the OpenAI API"

**Focus on the What:**

* "I want to extract product prices from competitor websites every week."
* "I want to analyze customer reviews and tell me the main themes."
* "I want to automatically respond to simple customer emails."

When you focus on what you want to achieve rather than how you think it should be built, Cody can choose the best tools and approach for your needs.

* **Provide Context and Details:** Give Cody enough information to make smart decisions about your workflow 
* **Instead of Vague Requests:** "Build me a lead generation workflow" 
* **Provide Rich Context:** 

{% hint style="info" %}
"Build me a lead generation workflow that:

* Finds marketing agency owners on LinkedIn
* In the US, with 10-50 employees
* Gets their contact info and company details
* Outputs to a Google Sheet for my sales team
* Processes about 50 leads per week."
  {% endhint %}

### **Describe Your Current Process** 

Walk Cody through exactly what you do now, step by step 

**Example:** "Right now I manually:

1. Check our Twitter analytics for mentions and engagement
2. Look at LinkedIn post performance
3. Put it all in a PowerPoint for my weekly team meeting
4. This takes me 2 hours every Monday morning

I want a workflow that does this automatically and emails me the report."

### **Be Specific About Data** 

Show Cody exactly what data you're working with, including examples

**Example:** "I have a Google Spreadsheet with:

* Column A: Customer names
* Column B: Their LinkedIn URLs
* Column C: Company names
* About 200 rows are updated weekly

I want to add job titles and company size in columns D and E."

**Clear Integration Requirements:** Specify exactly where results should go and what notifications you need. **Example:** "When the workflow finds new leads, I want it to:

* Add them to my HubSpot CRM in the 'Marketing Qualified' pipeline
* Send a Slack message to our #sales channel with the count
* Email me a summary if it finds more than 10 high-priority leads."

### **The Perfect Request Template**

Use this structure to get the best results:

**What I Want to Accomplish:** \[Clear business goal]

**My Current Process:** \[Step by step what you do manually now]

**My Data/Inputs:** \[What information you're starting with, with examples]

**Desired Outputs:** \[Exactly what you want to get back]

**Integration Needs:** \[Where results should go, notifications needed]

**Success Criteria:** \[How you'll know it's working well]

{% hint style="info" %}
**What I Want to Accomplish:** Monitor competitor pricing and get alerts when prices change.

**My Current Process:** Every Friday, manually check 5 competitor websites for prices on 20 products, and record them in a spreadsheet

**My Data/Inputs:** Google Sheet with product names, competitor URLs, and current prices

**Desired Outputs:** Updated prices, email alerts for 10%+ drops, weekly summary

**Integration Needs:** Update Google Sheet, email me and the sales manager, Slack notification

**Success Criteria:** Catches changes within 24 hours, 95% accurate, no false alerts
{% endhint %}

### Start Simple 

Once your first workflow is working, add features progressively. Provide business context so Cody understands your industry and challenges.

{% hint style="info" %}
**Example:** "I run a digital marketing agency managing social media for 25 local restaurants. My biggest challenge is creating enough content while tracking what performs best."
{% endhint %}

## Version History

You can revert a workflow to a previous version by providing Cody with the Implementation ID of the desired version. Simply ask Cody to change the workflow to that specific Implementation ID.


---

# 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://docs.codewords.ai/~/revisions/2IgKSsIuX4bzBsMZVaMc/guides/tips-and-tricks.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.