Skip to content

Commit 9409997

Browse files
Ambika Joshigitbook-bot
authored andcommitted
GITBOOK-315: No subject
1 parent 6e78812 commit 9409997

9 files changed

Lines changed: 181 additions & 23 deletions

File tree

README.md

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,23 @@
11
---
22
description: Low-code AI orchestration platform to empower people everywhere.
3+
layout:
4+
width: default
5+
title:
6+
visible: true
7+
description:
8+
visible: true
9+
tableOfContents:
10+
visible: true
11+
outline:
12+
visible: false
13+
pagination:
14+
visible: true
15+
metadata:
16+
visible: true
17+
tags:
18+
visible: true
19+
actions:
20+
visible: true
321
---
422

523
# 🗃️ Gooey.AI Docs

SUMMARY.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,8 @@
2121
* [Deploy to Slack](ai-agent/how-to-deploy-an-ai-copilot/deploy-to-slack/README.md)
2222
* [Siri Deployment](ai-agent/how-to-deploy-an-ai-copilot/deploy-to-slack/siri-deployment.md)
2323
* [Deploy to Facebook](ai-agent/how-to-deploy-an-ai-copilot/deploy-to-facebook.md)
24-
* [Broadcast Messages (via web or API)](ai-agent/how-to-deploy-an-ai-copilot/broadcast-messages-via-web-or-api.md)
24+
* [Broadcast Messages (via web or API)](ai-agent/how-to-deploy-an-ai-copilot/broadcast-messages-via-web-or-api/README.md)
25+
* [Sending Targeted Messages with the Broadcast API](ai-agent/how-to-deploy-an-ai-copilot/broadcast-messages-via-web-or-api/sending-targeted-messages-with-the-broadcast-api.md)
2526
* [Add buttons to your AI agent](ai-agent/how-to-deploy-an-ai-copilot/add-buttons-to-your-copilot.md)
2627
* [📈 Monitor an AI Agent](ai-agent/conversation-analysis/README.md)
2728
* [Feedback](ai-agent/conversation-analysis/feedback.md)

ai-agent/copilot/README.md

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,23 @@
11
---
22
description: Build your no-code AI agent in minutes!
3+
layout:
4+
width: default
5+
title:
6+
visible: true
7+
description:
8+
visible: true
9+
tableOfContents:
10+
visible: true
11+
outline:
12+
visible: false
13+
pagination:
14+
visible: true
15+
metadata:
16+
visible: true
17+
tags:
18+
visible: true
19+
actions:
20+
visible: true
321
---
422

523
# 🤖 Build an AI Agent

ai-agent/how-to-deploy-an-ai-copilot/broadcast-messages-via-web-or-api.md renamed to ai-agent/how-to-deploy-an-ai-copilot/broadcast-messages-via-web-or-api/README.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ description: >-
1111

1212
Navigate to the [integrations tab](https://gooey.ai/copilot/integrations) on the published run that you've connected. Expand "Configure Settings 🛠️" and scroll to the bottom of the settings. For supported deployment types like Slack and WhatsApp, you should see the following input widget:
1313

14-
<figure><img src="../../.gitbook/assets/image (1).png" alt=""><figcaption><p>The Broadcast Widget. Allows entering text and uploading audio, video, and miscellaneous file attachments. Hit "Send Broadcast" and subsequently click "confirm" to send a message to all your users!</p></figcaption></figure>
14+
<figure><img src="../../../.gitbook/assets/image (1).png" alt=""><figcaption><p>The Broadcast Widget. Allows entering text and uploading audio, video, and miscellaneous file attachments. Hit "Send Broadcast" and subsequently click "confirm" to send a message to all your users!</p></figcaption></figure>
1515

1616
Enter your message and upload audio, video, and other documents as desired. Make sure the file type is supported by the relevant platform. WhatsApp currently supports `audio/aac`, `audio/mp4`, `audio/mpeg`, `audio/amr`, and `audio/ogg`. Slack has the best support for `audio/mp4` or `audio/mpeg`. Once you're ready to send the messages, click "Send Broadcast" and you'll be prompted for confirmation. Upon confirmation, the messages will start sending. Depending on how many users you have, it can take a few minutes for all of them to be notified.
1717

@@ -23,7 +23,7 @@ Note that WhatsApp restricts free-form message sending to users who have contact
2323

2424
The API supports a few extra features including only sending the message to some subset of users or adding custom buttons. To get started, click the [API link ](https://api.gooey.ai/docs#operation/video-bots__broadcast)(either here or from the deployment tab shown above) to view the API documentation for message broadcasting.
2525

26-
<figure><img src="../../.gitbook/assets/image (3).png" alt=""><figcaption><p>API documentation for broadcasting.</p></figcaption></figure>
26+
<figure><img src="../../../.gitbook/assets/image (3).png" alt=""><figcaption><p>API documentation for broadcasting.</p></figcaption></figure>
2727

2828
### Specifying which Deployment to Broadcast through
2929

@@ -114,3 +114,5 @@ payload = {
114114
}
115115
}
116116
```
117+
118+
More details on [Sending Targeted Messages](sending-targeted-messages-with-the-broadcast-api.md).&#x20;
Lines changed: 101 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,101 @@
1+
# Sending Targeted Messages with the Broadcast API
2+
3+
The Broadcast API can send a message to one user, not only to every user in an integration.
4+
5+
`integration_id` selects the bot integration. `filters` narrows the recipient list inside that integration.
6+
7+
caution If you omit `filters`, the message is sent to all conversations/users for that integration. Always include a phone-number filter for one-user sends.
8+
9+
If the phone number does not match an existing conversation in that integration, the API returns a `404` and does not send the message.
10+
11+
### Example Request
12+
13+
```http
14+
POST https://api.gooey.ai/v2/agent/broadcast/send/
15+
Authorization: Bearer <GOOEY_API_KEY>
16+
Content-Type: application/json
17+
```
18+
19+
```json
20+
{
21+
"text": "Welcome! I'm your assistant.",
22+
"integration_id": "your-integration-id",
23+
"filters": {
24+
"wa_phone_number__in": ["+91XXXXXXXXXX"]
25+
}
26+
}
27+
```
28+
29+
Response:
30+
31+
```json
32+
{
33+
"status": "success",
34+
"count": 1
35+
}
36+
```
37+
38+
Use E.164 phone format, for example `+919876543210`.
39+
40+
### Sending Files
41+
42+
The same endpoint accepts file URLs through `audio`, `video`, and `documents`.
43+
44+
```json
45+
{
46+
"text": "Your report is ready.",
47+
"integration_id": "your-integration-id",
48+
"documents": ["https://example.com/report.pdf"],
49+
"filters": {
50+
"wa_phone_number__in": ["+91XXXXXXXXXX"]
51+
}
52+
}
53+
```
54+
55+
This is useful when a backend job or Gooey Function generates a PDF, audio file, video, or other downloadable asset. Once the file URL is available, call the Broadcast API and scope the send to the user with `filters`.
56+
57+
### Using a Gooey Function
58+
59+
If an agent needs to trigger the message, create a Gooey Function that calls `/agent/broadcast/send/`. The agent can pass the `integration_id`, target phone number, message text, and optional file URL to the function.
60+
61+
```js
62+
async ({ integration_id, phone_number, text, file_url }) => {
63+
const phoneNumber = phone_number.replace(/\s/g, "");
64+
65+
const payload = {
66+
text,
67+
integration_id,
68+
filters: {
69+
// For Twilio-backed SMS/MMS, use twilio_phone_number__in instead.
70+
wa_phone_number__in: [phoneNumber]
71+
}
72+
};
73+
74+
if (file_url) {
75+
payload.documents = [file_url];
76+
}
77+
78+
const res = await fetch("https://api.gooey.ai/v2/agent/broadcast/send/", {
79+
method: "POST",
80+
headers: {
81+
"Content-Type": "application/json",
82+
"Authorization": `Bearer ${process.env.GOOEY_API_KEY}`
83+
},
84+
body: JSON.stringify(payload)
85+
});
86+
87+
if (!res.ok) {
88+
throw new Error(await res.text());
89+
}
90+
91+
return await res.json();
92+
};
93+
```
94+
95+
For audio or video files, use `audio: file_url` or `video: file_url` instead of `documents`.
96+
97+
Use the filter key that matches your integration type.
98+
99+
### WhatsApp 24-Hour Window
100+
101+
WhatsApp only allows outbound messages within 24 hours of the user's last message to your integration. If a broadcast does not arrive, check whether the recipient has messaged the integration in the last 24 hours. If not, ask them to send a message first, then retry.

ai-agent/how-to-deploy-an-ai-copilot/deploy-to-facebook.md

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,23 @@
11
---
22
description: One-click deployment for your AI Agent
3+
layout:
4+
width: default
5+
title:
6+
visible: true
7+
description:
8+
visible: true
9+
tableOfContents:
10+
visible: true
11+
outline:
12+
visible: true
13+
pagination:
14+
visible: true
15+
metadata:
16+
visible: true
17+
tags:
18+
visible: true
19+
actions:
20+
visible: true
321
---
422

523
# Deploy to Facebook

tools/evaluations/README.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# ⚖️ Bulk Runner and Evaluation
1+
# ⚖️ Evaluations
22

33
## Why do you need bulk runner and evaluations? <a href="#id-4zynvpxsa8kj" id="id-4zynvpxsa8kj"></a>
44

@@ -31,15 +31,15 @@ How can you do this at scale?
3131

3232
Here are the **quickstart guides** for Bulk Runner and Evaluation:
3333

34-
<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td>How to set up Golden Q&#x26;As</td><td><a href="how-to-set-up-golden-q-and-as.md">how-to-set-up-golden-q-and-as.md</a></td><td></td></tr><tr><td>How to set up Bulk Runner?</td><td><a href="how-to-set-up-bulk-runner.md">how-to-set-up-bulk-runner.md</a></td><td><a href="../../../.gitbook/assets/Bulk Runner.png_400x400.png">Bulk Runner.png_400x400.png</a></td></tr><tr><td>How to set up Evaluation?</td><td><a href="how-to-set-up-evaluations.md">how-to-set-up-evaluations.md</a></td><td><a href="../../../.gitbook/assets/W.I.9.png_400x400.png">W.I.9.png_400x400.png</a></td></tr></tbody></table>
34+
<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td>How to set up Golden Q&#x26;As</td><td><a href="how-to-set-up-golden-q-and-as.md">how-to-set-up-golden-q-and-as.md</a></td><td></td></tr><tr><td>How to set up Bulk Runner?</td><td><a href="how-to-set-up-bulk-runner.md">how-to-set-up-bulk-runner.md</a></td><td><a href="../../.gitbook/assets/Bulk Runner.png_400x400.png">Bulk Runner.png_400x400.png</a></td></tr><tr><td>How to set up Evaluation?</td><td><a href="how-to-set-up-evaluations.md">how-to-set-up-evaluations.md</a></td><td><a href="../../.gitbook/assets/W.I.9.png_400x400.png">W.I.9.png_400x400.png</a></td></tr></tbody></table>
3535

3636
## How Does Bulk Runner Work? <a href="#r7so22ymyyn2" id="r7so22ymyyn2"></a>
3737

3838
### Bulk Run Overview <a href="#id-2v61ngoeupi4" id="id-2v61ngoeupi4"></a>
3939

4040
This diagram details the process of generating AI-driven answers to a set of test questions using a Language Model (LLM) with Retrieval-Augmented Generation (RAG) capabilities.&#x20;
4141

42-
![](<../../../.gitbook/assets/Understanding Bulk run and Evaluations.jpg>)
42+
<img src="../../.gitbook/assets/Understanding Bulk run and Evaluations.jpg" alt="" width="563">
4343

4444

4545

@@ -65,7 +65,7 @@ The generated answers are compiled into an output table. Each question is paired
6565

6666
This section details the process for comparing and evaluating generated answers against a set of golden answers to assess their semantic and technical accuracy.
6767

68-
![](<../../../.gitbook/assets/Understanding Bulk run and Evaluations (1).jpg>)
68+
![](<../../.gitbook/assets/Understanding Bulk run and Evaluations (1).jpg>)
6969

7070
1. **Input: Questions and Golden Answers**
7171
1. **Test Question Set**: A curated set of questions to be answered, such as:

tools/evaluations/how-to-set-up-bulk-runner.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ In this example scenario, we are setting up a simple bulk run to check regressio
1010

1111
Choose the “SAVED” run from Gooey.AI Workflows that you would like to use.
1212

13-
![](<../../../.gitbook/assets/2 (1) (1) (1).png>)
13+
<img src="../../.gitbook/assets/2 (1) (1) (1).png" alt="" width="563">
1414

1515
### Step 2: Input Data Spreadsheet <a href="#s6plmddmwaiq" id="s6plmddmwaiq"></a>
1616

@@ -20,17 +20,17 @@ Prepare your test question set:
2020
2. Make sure the Excel sheet/Google Sheets table has a “header” section
2121
3. Add all your questions in the column below it
2222

23-
<figure><img src="../../../.gitbook/assets/3 (1) (1) (1).png" alt="" width="369"><figcaption></figcaption></figure>
23+
<figure><img src="../../.gitbook/assets/3 (1) (1) (1).png" alt="" width="369"><figcaption></figcaption></figure>
2424

2525
1. Paste the link of your Google sheet or upload your data
2626

2727
&#x20;
2828

29-
<figure><img src="../../../.gitbook/assets/4 (1) (1) (1).png" alt="" width="563"><figcaption></figcaption></figure>
29+
<figure><img src="../../.gitbook/assets/4 (1) (1) (1).png" alt="" width="563"><figcaption></figcaption></figure>
3030

3131
The output will look like this:
3232

33-
<figure><img src="../../../.gitbook/assets/Screenshot 2025-09-01 at 7.48.32 PM.png" alt=""><figcaption></figcaption></figure>
33+
<figure><img src="../../.gitbook/assets/Screenshot 2025-09-01 at 7.48.32 PM.png" alt=""><figcaption></figcaption></figure>
3434

3535
### Step 3: Select your input columns <a href="#yayrw51txj9z" id="yayrw51txj9z"></a>
3636

@@ -44,21 +44,21 @@ As this is a “Bulk only” scenario, you can “delete” the Agent Evaluator
4444

4545
&#x20;
4646

47-
<figure><img src="../../../.gitbook/assets/Screenshot 2025-09-01 at 7.48.39 PM.png" alt=""><figcaption></figcaption></figure>
47+
<figure><img src="../../.gitbook/assets/Screenshot 2025-09-01 at 7.48.39 PM.png" alt=""><figcaption></figcaption></figure>
4848

49-
<figure><img src="../../../.gitbook/assets/6.png" alt="" width="563"><figcaption></figcaption></figure>
49+
<figure><img src="../../.gitbook/assets/6.png" alt="" width="563"><figcaption></figcaption></figure>
5050

5151
### Output <a href="#id-6n9vkbjh3n11" id="id-6n9vkbjh3n11"></a>
5252

5353
The workflow will create a new CSV, with an added few columns based on the run, including, “Output Text”, “Run URL”, and “Run Time”.
5454

5555
**Your output will be on the right side of the page.**
5656

57-
<figure><img src="../../../.gitbook/assets/7.png" alt="" width="563"><figcaption></figcaption></figure>
57+
<figure><img src="../../.gitbook/assets/7.png" alt="" width="563"><figcaption></figcaption></figure>
5858

5959
#### Additional Note <a href="#kfu0hmigziyi" id="kfu0hmigziyi"></a>
6060

6161
If you want more details in the Output section, use the drop down in the “Output Columns". This is useful if you want to keep track of Price, Latency, Error Messages, and other details.
6262

63-
<figure><img src="../../../.gitbook/assets/Screenshot 2025-09-01 at 7.50.50 PM.png" alt=""><figcaption></figcaption></figure>
63+
<figure><img src="../../.gitbook/assets/Screenshot 2025-09-01 at 7.50.50 PM.png" alt=""><figcaption></figcaption></figure>
6464

tools/evaluations/how-to-set-up-evaluations.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ In this example scenario, we are comparing and evaluating the quality of the ans
88

99
Choose the “SAVED” run from Gooey.AI Workflows that you would like to use.
1010

11-
![](../../../.gitbook/assets/9.png)
11+
<img src="../../.gitbook/assets/9.png" alt="" width="563">
1212

1313
### Step 2: Input Data Spreadsheet <a href="#id-4y2kttei07z1" id="id-4y2kttei07z1"></a>
1414

@@ -20,27 +20,27 @@ Prepare your golden QnA set:
2020

2121

2222

23-
<figure><img src="../../../.gitbook/assets/10.png" alt="" width="563"><figcaption></figcaption></figure>
23+
<figure><img src="../../.gitbook/assets/10.png" alt="" width="563"><figcaption></figcaption></figure>
2424

2525
**You must provide the Golden Answers. Golden answers are the most suitable and accurate answers provided by humans with expertise on the subject.**
2626

2727
1. Paste the link of your Google sheet or upload your data&#x20;
2828

29-
<figure><img src="../../../.gitbook/assets/11.png" alt="" width="563"><figcaption></figcaption></figure>
29+
<figure><img src="../../.gitbook/assets/11.png" alt="" width="563"><figcaption></figcaption></figure>
3030

3131
### Step 3: Select your input columns <a href="#o6vzivos324o" id="o6vzivos324o"></a>
3232

3333
In the current scenario, we want to use the Gooey Agent to answer all the questions in the Google sheet. So essentially they are the “input” for the Bulk Workflow.
3434

3535
Select the “questions” column in the “Input Prompt” section.
3636

37-
![](../../../.gitbook/assets/12.png)
37+
<img src="../../.gitbook/assets/12.png" alt="" width="563">
3838

3939
### Step 4: Hit Submit <a href="#brcrdr2ggss2" id="brcrdr2ggss2"></a>
4040

4141
As this is a “Bulk and Eval” scenario, you can “select” the Agent Evaluator option in the section. After that hit the “Submit” button.
4242

43-
![](../../../.gitbook/assets/13.png)
43+
<img src="../../.gitbook/assets/13.png" alt="" width="563">
4444

4545
_Note: We recommend using the “Agent Evaluator” if you are evaluating Agent Runs._
4646

@@ -52,9 +52,9 @@ _**With the evaluation option, you will also get output for “Rationale”, “
5252

5353
**Your output will be on the right side of the page.**
5454

55-
<figure><img src="../../../.gitbook/assets/Screenshot 2024-08-19 at 4.53.02 PM.png" alt="" width="563"><figcaption></figcaption></figure>
55+
<figure><img src="../../.gitbook/assets/Screenshot 2024-08-19 at 4.53.02 PM.png" alt="" width="563"><figcaption></figcaption></figure>
5656

57-
<figure><img src="../../../.gitbook/assets/Screenshot 2024-08-19 at 11.30.43 PM (1).png" alt="" width="375"><figcaption></figcaption></figure>
57+
<figure><img src="../../.gitbook/assets/Screenshot 2024-08-19 at 11.30.43 PM (1).png" alt="" width="375"><figcaption></figcaption></figure>
5858

5959
### Best Practices <a href="#oucznt5a94xk" id="oucznt5a94xk"></a>
6060

@@ -63,7 +63,7 @@ _**With the evaluation option, you will also get output for “Rationale”, “
6363
* Make sure to name your “Saved” workflows with relatable titles so that it is easy to set up the run
6464
* We recommend collecting user messages from your saved agent's “Analytics” section. Head to Your agent link> Deploy tab > View Analytics, scroll to the bottom, and **export** the “Messages” tab CSV. <br>
6565

66-
<figure><img src="../../../.gitbook/assets/16.png" alt=""><figcaption></figcaption></figure>
66+
<figure><img src="../../.gitbook/assets/16.png" alt=""><figcaption></figcaption></figure>
6767

6868
#### Note: <a href="#id-8grsusqblfge" id="id-8grsusqblfge"></a>
6969

0 commit comments

Comments
 (0)