News


## Retrival Augmented Generation (RAG)
* [RAG](https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/) is how you can give LLMs access to your corporate data so they can answer questions with your proprietary internal knowledge. 
* Ask Steve can be pointed to an API that uses your RAG system instead of directly to an LLM so it can answer employee questions, wherever they are, in the flow of work. 
* This example uses the open source vector database [qdrant](https://qdrant.tech/) for storing information and the visual workflow builder [n8n](https://n8n.io) for creating the code that connects OpenAI's gpt4o-mini to the vector database.
* An Ask Steve Skill was created that calls the n8n API, which tells the OpenAI LLM to search the qdrant vector database and use the results in its answer.
<br />
<iframe width="400" height="281" src="https://www.youtube.com/embed/taNoHYBT3uk?si=c4aEojkTDNFoiC6O" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

Connect Ask Steve to your Retrieval Augmented Generation (RAG) system


## Google Docs
* You can now chat with your Google Docs using Ask Steve - either an entire document or a text selection. 
* If you make changes to your Doc, you will need to refresh the page in order for Ask Steve to pick up the changes. 
<iframe width="400" height="281" src="https://www.youtube.com/embed/-tpV5Dl-MTU?si=kNwJWljRtqAiKvPU" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>


## Google Slides
* You can now chat with your Google Slides using Ask Steve - either an entire deck or a text selection.  
* If you make changes to your Slides, you will need to refresh the page in order for Ask Steve to pick up the changes. 
<iframe width="400" height="281" src="https://www.youtube.com/embed/43118FC6UOs?si=SM9a07ed_4NgjxWP" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

Use Google Docs and Slides


## PDFs
* You can now chat with your PDFs using Ask Steve - either an entire document or a text selection. 
<iframe width="400" height="281" src="https://www.youtube.com/embed/oYkGbrtlDUY?si=rm9QVrBk9kbEDhx4" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>


Interact with PDFs


## Local Files
* You can now use Ask Steve's [File Chat](https://quickstart.asksteve.to/viewer/) to interact with pdf, docx, pptx, jpg, png and gif files.  
* All processing is done on your computer. Nothing is uploaded to the cloud. 
* Use the file selector to pick a file, or drag and drop one onto the dropzone. 
* Or paste an image or text anywhere on the page. 
<iframe width="400" height="281" src="https://www.youtube.com/embed/_6E6V41WZhA?si=kEfF1hJccS_TcFGz" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>


Use Local Files


## Google Apps Script Editor
* Install the [Google Apps Script Skill Pack](https://quickstart.asksteve.to/) to add Ask Steve buttons to the Google Apps Script editor
* Explain the current file or selection
* Optimize the current file or selection
* Get help writing new code
* Use the Chat to get help debugging code
<iframe width="400" height="281" src="https://www.youtube.com/embed/7uwXnHR_2vU?si=dP3jhU6Z5AUEB_kB" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>


Get AI Help with Google Apps Script


## YouTube
* Chat with any YouTube video using Ask Steve
* Ask Steve uses the video title, description, length, # views, and transcript to try to answer.
<iframe width="400" height="281" src="https://www.youtube.com/embed/_JEzgl5SNbE?si=nZK4oHMlpuWkASx4" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>


Chat With Any YouTube Video


## Keyboard Shortcuts
* Your top 2 pinned Skills are automatically given the keyboard shortcuts Command-Shift-1 and Command-Shift-2 (Control instead of Command on Windows & ChromeOS) - this gives you super fast access to them
* Pinned Skills are sorted alphabetically
<iframe width="400" height="281" src="https://www.youtube.com/embed/bJHYI-AhMz4?si=BfLxilU7xehGb1vc" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>


Use Keyboard Shortcuts for Fast Access to Skills

Tutorials


### Overview
This video walks you through how you can setup a Scenario in Make.com and a Skill in Ask Steve that enables you to select leads on any web page and have them parsed and written into the correct columns in a Google Sheet. 

In the past you'd have to copy the name, role and company of every lead you found into your Sheet by hand. Now you can highlight one or more leads in any format on any web page and Ask Steve to save it to your Sheet. It will call the Make.com scenario which will send the leads to OpenAI to turn whatever you sent it into structured data (name, role, company, etc.) and then write the leads into Google Sheets, saving you a ton of time. It will even add a LinkedIn search link so that you can get to the lead's profile quickly, and record the URL where you found the lead. 

Using this setup as a baseline, you can easily customize it for other use cases, and connect it to other software systems (Salesforce, Airtable, etc.)   

You can use the concepts demonstrated here to connect Ask Steve to any API. Learn more about how to call Webhooks and APIs [here](/docs/webhooks).

<iframe width="400" height="281" src="https://www.youtube.com/embed/goe9yBwx4rA?si=UV48SJZxGWH9LPas" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

### Accounts You'll Need: 
1. An Ask Steve [Premium Plan](https://www.asksteve.to/pricing) account so you can connect to the Make.com API
2. A [Make.com](https://www.make.com/) account
3. An OpenAI [Developer Platform account](https://platform.openai.com/) 

### Files You'll Need:
1. Make a copy of [this Google Sheet](https://docs.google.com/spreadsheets/d/1FH5pQhLKloAsBbo8oFvw-ZEUs9F_MFgPibghdzKrdaU/edit?gid=0#gid=0)
2. Download the Make blueprint and the Ask Steve Skill from [here](https://quickstart.asksteve.to/tutorials/make-lead-to-sheets.zip)
\
\
Then follow along with the video! If you need help, ask in our [Google Group](https://groups.google.com/g/ask-steve)

Connect Ask Steve to Make.com for Lead Tracking


### Call Any API from Ask Steve

Right now Ask Steve calls an LLM in the background with your prompt and returns the result. But really it's just calling an API which happens to be an LLM. With a few small new features in the 1.0.9 version of Ask Steve, We've made it easy to call **ANY API**.

So now rather than triggering a single LLM call from the current page or selection, you can do... anything! Pre-process the input, augment it with external information, log it, etc. Then process the input with code, external services, one or more LLMs, or some combination. And finally post-process the result before returning it to the user in the Ask Steve UI. 

To demo this, I created a simple workflow using [n8n.io](https://n8n.io/) - a really powerful low/no-code workflow automation builder - and connected it to an Ask Steve Skill. This workflow takes the selected text, parses it, puts it into a Google Sheet and returns a confirmation. 

<iframe width="400" height="281" src="https://www.youtube.com/embed/4879AXfUaLo?si=eTz7y9iQsytMExDL" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
\
You can do this with your own code running on a server somewhere, or with any visual workflow builder like [n8n](https://n8n.io/), [Gumloop](https://www.gumloop.com/), [Activepieces](https://www.activepieces.com/), [Make](https://www.make.com/), [Zapier](https://zapier.com/) etc. that supports Webhooks. 

[Let us know](mailto:admin@asksteve.to) if you connect Ask Steve to your own API!

> Want to unlock the power of ChatGPT and Gemini in any web page? 
> **[Install Ask Steve Now](https://quickstart.asksteve.to/browsers/)**


Connect Ask Steve to Any API

*This was originally written while I was at Google, so the examples are geared toward software that most Googlers would know - rajat*

People often talk about wanting to make products delightful. What does this mean in practice? 

<div style={{backgroundColor: 'violet', padding: '1rem'}}>
**Delight is when a task is made unexpectedly easy**
</div>

The key thing to note here is that Delight is based on **the user’s expectations**.
* If they are expecting a task to be difficult and it is, then their expectations have been met. 
* If it is easier than they were anticipating, then they are **delighted**. 
* If it is harder, then they are **frustrated**.

### Illustrative examples of Delight:
* When Google Docs automatically corrects my spelling errors for me. 
* When Google Docs automatically completes my sentences for me. 
* When I use [Smart Chips](https://support.google.com/docs/answer/10710316?hl=en) in Google Docs to automatically create meeting notes, or an email, or show the actual name of a Google Doc when I paste a URL. 
* When I can respond to a Google Doc/Sheets/Slides comment from within Gmail
* When Smart Reply gives me the perfect response to a text that I can send with 1 click.
* When I’m trying to parallel park my car and the rear-view camera shows me the rear-view, lines that indicate my path and warnings when I get too close to the curb or another car. 
* When Google Photos [automatically creates albums of each of my kids](https://blog.google/products/photos/keep-your-favorite-photos-date-live-albums/), because it recognizes their faces. 
* When Google Photos [Magic Eraser](https://www.androidheadlines.com/how-to-use-magic-eraser-google-photos) enables me to easily remove unwanted people & objects from the background of my pictures.

### Illustrative counter-examples - Frustration:
* Every time I have to file an expense report in Concur, I am filled with dread. I know that I will likely feel stupid & confused at some point in the process. 
* Every time I have to log vacation, I mentally steel myself to use the slow and clunky Workday UI. 
* Every time I have to parallel park in a car without a backup camera, it stresses me out and takes multiple attempts. 

<img src='/assets/images/posts/delight_scale.png' alt="The Delight Scale"  style={{ marginLeft: 'auto', marginRight: 'auto', borderRadius: '10px'}} />

### Delight goes best with *flow*
There is a joy that comes from using a really good tool. Tools that are made well disappear, enabling you to enter [flow](https://en.wikipedia.org/wiki/Flow_(psychology)) and accomplish your goals without thinking about the tool and the ways it is getting in your way. You can feel when tools aren’t made well (Concur, Workday) - every unexpected behavior or rough edge slows you down and makes you think. 

### Delight eventually becomes *expected*
The first time you use a backup camera in a car, it feels like magic. By the hundredth time, it becomes an expectation. You miss it if it’s not there, but you are no longer delighted by it. So all delightful features become expectations over time, and the challenge is to see if you can continue to find ways to delight your users. 

Clearly framing your problem space helps with this. If you think of Docs as a word processor, you have limited the opportunities for delight. If you think of it as a collaborative tool for creating, refining and communicating ideas through words, then you have a lot more. 

### Delight doesn’t get people to use products *more*
The backup camera doesn’t make me want to parallel park more often, and Smart Chips don’t make me want to write more docs. But when I do have to parallel park or write a doc, they make me more effective and efficient at accomplishing my goals. 

### Delight isn’t *fun*
Asana has [Celebration Creatures](https://forum.asana.com/t/asana-s-celebration-creatures-got-a-glow-up/476849) that show on task completion. This is fun, but is not delight. You can add fun if you’re at least NEUTRAL on the continuum, which Asana is. If you try to add fun to a frustrating tool, good luck to you. 

### In Summary
<div style={{backgroundColor: 'violet', padding: '1rem'}}>
**Delight = Expectation of Difficulty - Actual Difficulty**
</div>


&nbsp;
> **Our goal with Ask Steve is simple: Be Delightful**\
> \
> We do this by making a bunch of tasks that would ordinarily take a lot of manual work unexpectedly easy. \
> \
> [Try it today!](https://quickstart.asksteve.to/browsers/)


What Does it Mean for a Product to be Delightful?

## We have just added the ability to connect to any LLM/model from Ask Steve!
* Instructions for connecting to a cloud model are [here](/docs/models)
* Instructions for connecting to a local model are [here](/docs/local-models)
* If you want to try a super fast model (free in beta), try out [Groq Cloud](/blog/news/groq-cloud)


Connect to Any LLM

## Groq is a company that makes chips customized to run LLMs, and they run *very* fast.
They have a cloud offering that is currently in free beta. Connect to it and see just how fast Steve can be!
1. Create a [Groq Cloud](https://console.groq.com/login) account
2. Create an API key
3. Go to the [Models](https://quickstart.asksteve.to/browsers/models.html) page in Ask Steve Settings, press `ADD NEW MODEL` and select `OpenAI GPT-3.5` from the menu. Groq Cloud's API is modeled on OpenAI's, so we'll use it as a starting point. Go ahead and paste in your Groq Cloud API Key.
4. Change the *Name* to `Groq Cloud`, the *URL* to `https://api.groq.com/openai/v1/chat/completions` and in the *Body* change *model* to `llama3-70b-8192`. You can see all the available models [here](https://console.groq.com/docs/models) and their rate limits [here](https://console.groq.com/settings/limits)
5. Press `TEST` to ensure it works, then `SAVE NEW MODEL` to save it. 
6. Steve is now SUPER FAST 🚀🚀🚀




Super Fast Responses with Groq Cloud


## How did Steve Get His Name?

In December of 2023, <a href="https://www.google.com/search?q=ethan+mollick" target="_blank">Professor Ethan Mollick</a> from Wharton posted the following on LinkedIn: 

<div style={{backgroundColor: 'lightgoldenrodyellow', padding: '1rem'}}>
<a href="https://www.linkedin.com/posts/emollick_the-thing-about-llms-that-make-them-unintuitive-activity-7125848204339732480-OeZL/" target="_blank"><img src='/assets/images/posts/steve-name.png' alt="How Steve Got His Name"  style={{ marginLeft: 'auto', marginRight: 'auto', borderRadius: '10px'}} /></a>
</div>

For some reason I found this really funny, but I also really liked the mental model of a first year grad student or intern as a way to think about an AI assistant that lived in your browser. Thus "Ask Steve" was born.

[DALL-E 3](https://openai.com/dall-e-3) drew Steve's picture (self-portrait?).

Professor Mollick has <a href="https://www.linkedin.com/in/emollick/recent-activity/all/" target="_blank">a lot of great posts on LinkedIn</a>, and you should follow him if you're interested in LLMs. He also has a good book out called <a href="https://www.penguinrandomhouse.com/books/741805/co-intelligence-by-ethan-mollick/" target="_blank">**Co-Intelligence: Living and Working with AI**</a>.

 \- rajat

Blog

Tutorials, Guides and Updates from the Ask Steve team