Connect AI agents to Attention

Scalekit connector

The Attention connector lets your AI agent act in each user's Attention account. Each user connects their own Attention API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 29 tools.

Tools: 29
What they doRead · write · destructive: 17 · 10 · 217 read10 write2 destructive
Users sign in with: API key

What you can do

Read conversations: list recorded calls and meetings, and fetch participants and full transcripts
Ask questions about calls: get AI-generated answers across a deal’s conversations, with supporting transcript excerpts
Manage conversations: import recordings, update titles and labels, change privacy, archive, and create video snippets
Review with scorecards: list scorecard templates, submit coaching reviews, and pull aggregate scorecard results
Track meetings and emails: list a user’s calendar events and search tracked emails by subject, account, or deal
Manage users and teams: create, update, and remove users, and organize them into nested teams

Setup

npm install @scalekit-sdk/node dotenv

pip install scalekit-sdk-python python-dotenv

Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Attention connection
In AgentKit > Connections, create an Attention connection. The name you give it is the connection_name your code passes. See Configure connections.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'attention'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Attention:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'attention_connection_report_get',
27
  toolInput: {},
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "attention"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Attention:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={},
27
    tool_name="attention_connection_report_get",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user opens the link once and enters their Attention credentials there. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

attention_ask_attentionAsk a natural-language question over one or more conversations within a deal and get back an AI-generated answer.Read-only
Ask Attention
Ask a natural-language question over one or more conversations within a deal and get back an AI-generated answer. Optionally include timestamped transcript excerpts that support the answer, or synthesize a single cross-conversation summary.
Inputs
conversations_idsarrayrequired
List of conversation IDs to analyze. Pass an empty array to consider all conversations under the given deal.
deal_idstringrequired
Identifier of the CRM deal that provides context for this question.
promptstringrequired
Natural-language question or instruction to run against the selected conversations.
include_timestampsboolean
If true, includes timestamped transcript excerpts that support the answer.
summarizeboolean
If true, synthesizes all per-conversation outputs into a single combined response.
attention_calendar_events_listList a specific user's calendar events/meetings with date-range filtering and pagination.Read-only
List Calendar Events
List a specific user's calendar events/meetings with date-range filtering and pagination.
Inputs
pageintegerrequired
Page number for pagination.
sizeintegerrequired
Number of items per page.
user_uuidstringrequired
UUID of the user whose calendar events to list.
date_fromstring
Filter events starting from this date-time (inclusive, ISO 8601).
date_tostring
Filter events until this date-time (inclusive, ISO 8601).
attention_connection_report_getGet an org-wide report of which users have connected their calendar and email to Attention, including a summary count and a per-user connection status breakdown.Read-only
Get Connection Report
Get an org-wide report of which users have connected their calendar and email to Attention, including a summary count and a per-user connection status breakdown.
Inputs
This tool takes no inputs.
attention_conversation_by_external_id_getLook up an Attention conversation by its external application ID, the ID from the source system that originally imported it (for example a Zoom meeting or CRM activity ID).Read-only
Get Conversation by External ID
Look up an Attention conversation by its external application ID, the ID from the source system that originally imported it (for example a Zoom meeting or CRM activity ID). Returns the Attention conversation UUID when a match exists, and a 404 when no conversation has that external ID. Use this to reconcile a Zoom or CRM ID to an Attention conversation, then pass the returned UUID to attention_conversation_get for the full record. Use attention_conversations_list to browse by filters instead. Requires the external ID that was supplied when the conversation was imported.
Inputs
external_idstringrequired
The external application ID used when the conversation was imported into Attention, such as a Zoom meeting ID or CRM activity ID. Example: 84730218832
attention_conversation_getRetrieve a single Attention conversation by ID, including metadata, participants, and (optionally) the detailed transcript.Read-only
Get Conversation
Retrieve a single Attention conversation by ID, including metadata, participants, and (optionally) the detailed transcript.
Inputs
conversation_idstringrequired
Unique identifier of the conversation.
detailed_transcriptboolean
If true, includes detailed transcript data for the conversation.
include_internal_participantsboolean
If true, includes internal participants in the response.
attention_conversation_media_download_url_getGenerate a presigned download URL for a conversation's underlying recording/media file.Read-only
Get Conversation Media Download URL
Generate a presigned download URL for a conversation's underlying recording/media file.
Inputs
conversation_idstringrequired
Unique identifier of the conversation whose media should be downloaded.
attention_conversation_upload_url_getGet a signed URL (plus an identifier key) for uploading a local conversation media file, for use before calling attention_conversation_import.Read-only
Get Conversation Upload URL
Get a signed URL (plus an identifier key) for uploading a local conversation media file, for use before calling attention_conversation_import.
Inputs
This tool takes no inputs.
attention_conversations_listList conversations (calls, meetings) recorded in Attention, with optional date-range and filter parameters.Read-only
List Conversations
List conversations (calls, meetings) recorded in Attention, with optional date-range and filter parameters. Returns a paginated list of conversation summaries.
Inputs
detailed_transcriptboolean
If true, includes detailed transcript data for each conversation.
from_date_timestring
Start of the date-time range for filtering conversations (ISO 8601).
hide_internalboolean
If true, excludes conversations with no external participants.
owner_emailstring
Filter conversations by the owning user's email address.
pageinteger
Page number for pagination.
sizeinteger
Number of results per page.
team_idstring
Filter conversations by team UUID.
titlestring
Filter conversations by title.
to_date_timestring
End of the date-time range for filtering conversations (ISO 8601).
attention_emails_listList/search tracked emails with filters by subject, CRM account, deal, and date range — the email counterpart to the existing attention_conversations_list tool.Read-only
List Emails
List/search tracked emails with filters by subject, CRM account, deal, and date range — the email counterpart to the existing attention_conversations_list tool.
Inputs
crm_account_idarray
Filter emails by CRM account ID(s).
deal_uuidarray
Filter emails by deal UUID(s).
from_date_timestring
Start of the date-time range for filtering emails (ISO 8601).
pageinteger
Page number for pagination (starts from 1).
sizeinteger
Number of results per page (max 50).
subjectstring
Filter emails by subject using case-insensitive partial matching.
to_date_timestring
End of the date-time range for filtering emails (ISO 8601).
attention_roles_listList available user roles in the Attention organization and their UUIDs — needed as a lookup before calling attention_user_create or attention_user_update, which require a roleUUID.Read-only
List Roles
List available user roles in the Attention organization and their UUIDs — needed as a lookup before calling attention_user_create or attention_user_update, which require a roleUUID.
Inputs
This tool takes no inputs.
attention_scorecards_listList scorecard templates configured in the Attention workspace, used for call review and coaching.Read-only
List Scorecards
List scorecard templates configured in the Attention workspace, used for call review and coaching.
Inputs
pageinteger
Page number for pagination (1-indexed).
sizeinteger
Number of results per page.
attention_scorecards_summary_getGet aggregate scorecard results for a scorecard across a date range, filtered by teams, users, and scorecard items.Read-only
Get Scorecards Summary
Get aggregate scorecard results for a scorecard across a date range, filtered by teams, users, and scorecard items. Complements attention_scorecards_list and attention_scorecard_result_create with rollup analytics such as score totals, min/max, and per-item averages.
Inputs
from_date_timestringrequired
Start date-time of the range to summarize (ISO 8601).
scorecard_items_uuidsarrayrequired
Scorecard item IDs to include in the summary. Pass an empty array to include all items.
scorecard_uuidstringrequired
Identifier of the scorecard template to summarize.
team_uuidsarrayrequired
Team IDs to include in the summary. Pass an empty array to include all teams.
to_date_timestringrequired
End date-time of the range to summarize (ISO 8601).
user_uuidsarrayrequired
User IDs to include in the summary. Pass an empty array to include all users.
attention_team_getRetrieve a single Attention team by ID.Read-only
Get Team
Retrieve a single Attention team by ID.
Inputs
team_idstringrequired
Unique identifier of the team.
attention_team_members_listList the members belonging to a specific Attention team.Read-only
List Team Members
List the members belonging to a specific Attention team.
Inputs
team_idstringrequired
Unique identifier of the team.
attention_teams_listList all teams configured in the Attention workspace.Read-only
List Teams
List all teams configured in the Attention workspace.
Inputs
This tool takes no inputs.
attention_usage_report_getGet API/feature usage statistics (coaching sessions, calls viewed, comments left, snippets created, AI queries, etc.) for specified users or teams over a date range.Read-only
Get Usage Report
Get API/feature usage statistics (coaching sessions, calls viewed, comments left, snippets created, AI queries, etc.) for specified users or teams over a date range.
Inputs
end_datestringrequired
End date for the usage report period (inclusive).
start_datestringrequired
Start date for the usage report period (inclusive).
team_uuidsarray
List of team UUIDs to include in the report. Omit to include all teams.
user_uuidsarray
List of user UUIDs to include in the report. Omit to include all users.
attention_users_listList users in the Attention organization, with optional filters by ID, email, or team.Read-only
List Users
List users in the Attention organization, with optional filters by ID, email, or team.
Inputs
filter_emailstring
Filter results to this user's email address.
filter_idstring
Filter results to this user ID.
include_deletedboolean
If true, includes deleted users in the response.
team_uuidstring
Filter results to users in this team.
attention_conversation_importImport an externally recorded conversation into Attention by supplying a media URL and the owning user.Write
Import Conversation
Import an externally recorded conversation into Attention by supplying a media URL and the owning user. Attention will transcribe and analyze the recording asynchronously.
Inputs
media_urlstringrequired
URL of the call recording media file to import.
user_idstringrequired
Unique identifier of the user who owns this conversation.
application_external_idstring
External identifier for this recording in the source application.
application_namestring
Name of the source application providing the recording.
conversation_started_atstring
Start date-time of the conversation (ISO 8601).
conversation_titlestring
Title for the imported conversation.
opportunity_idstring
Identifier of the CRM opportunity linked to this conversation.
skip_crm_fields_calculationboolean
If true, skips CRM field calculation for the imported conversation.
skip_opportunities_exportboolean
If true, skips exporting data to CRM opportunities.
skip_scorecard_calculationboolean
If true, skips scorecard calculation for the imported conversation.
attention_conversation_privacy_updateToggle an Attention conversation between private and public visibility.Write
Update Conversation Privacy
Toggle an Attention conversation between private and public visibility.
- Idempotent
Inputs
conversation_idstringrequired
Unique identifier of the conversation.
privacystringrequired
New privacy setting for the conversation.one of publicprivate
attention_conversation_updateUpdate the title and/or labels of an existing Attention conversation.Write
Update Conversation
Update the title and/or labels of an existing Attention conversation.
- Idempotent
Inputs
conversation_idstringrequired
Unique identifier of the conversation.
labelsarray
Array of label strings to set on the conversation.
titlestring
New title for the conversation.
attention_deck_createGenerate an AI slide deck/presentation from a conversation, deal, or other content source and share the resulting link with a list of recipient emails.Write
Create Deck
Generate an AI slide deck/presentation from a conversation, deal, or other content source and share the resulting link with a list of recipient emails.
Inputs
context_idstringrequired
Identifier of the content source the deck should be generated from (e.g. a deal or conversation ID).
users_to_sharearrayrequired
Email addresses to share the generated deck with.
additional_instructionsstring
Supplementary free-text guidance for deck generation.
deck_typestring
Presentation category, e.g. sales_presentation.
slidesinteger
Target number of slides for the generated deck.
structurearray
Custom layout and content specification per slide.
attention_scorecard_result_createSubmit a scorecard result (coaching/QA review) for a conversation or chat in Attention, with a summary and a list of scored items.Write
Create Scorecard Result
Submit a scorecard result (coaching/QA review) for a conversation or chat in Attention, with a summary and a list of scored items.
Inputs
itemsarrayrequired
Array of scored scorecard items.
scorecard_uuidstringrequired
Unique identifier of the scorecard template.
summarystringrequired
Overall summary of the scorecard result.
chat_uuidstring
Unique identifier of the chat this result is attached to.
conversation_uuidstring
Unique identifier of the conversation this result is attached to.
attention_snippet_createCreate a shareable video snippet/clip from a specific time range of an Attention conversation.Write
Create Snippet
Create a shareable video snippet/clip from a specific time range of an Attention conversation.
Inputs
conversation_idstringrequired
Unique identifier of the conversation to clip from.
internalbooleanrequired
If true, the snippet is only visible internally.
notify_viewsbooleanrequired
If true, notifies the snippet owner when it's viewed.
user_uuidstringrequired
Unique identifier of the user creating this snippet.
video_end_timenumberrequired
End time of the clip within the conversation video, in seconds.
video_start_timenumberrequired
Start time of the clip within the conversation video, in seconds.
in_libraryboolean
If true, adds the snippet to the shared snippet library.
library_item_infoobject
Library folder/location details, required when in_library is true.
notesstring
Additional notes about the snippet.
titlestring
Title for the snippet.
attention_team_createCreate a new team in the Attention organization, optionally nested under a parent team.Write
Create Team
Create a new team in the Attention organization, optionally nested under a parent team.
Inputs
namestringrequired
Name of the new team.
parent_team_uuidstring
UUID of the parent team, if this team is part of a hierarchy.
attention_team_updateRename an Attention team or move it under a different parent team.Write
Update Team
Rename an Attention team or move it under a different parent team.
- Idempotent
Inputs
team_idstringrequired
UUID of the team to update.
namestring
New name for the team.
parent_team_uuidstring
UUID of the new parent team.
attention_user_createCreate a new user in the Attention organization with an email, role, seat type, and one or more team assignments.Write
Create User
Create a new user in the Attention organization with an email, role, seat type, and one or more team assignments. Look up role UUIDs with attention_roles_list and team UUIDs with attention_teams_list first.
Inputs
emailstringrequired
Email address of the new user.
first_namestringrequired
First name of the new user.
last_namestringrequired
Last name of the new user.
role_uuidstringrequired
UUID of the role to assign to the new user.
team_uuidsarrayrequired
Team UUIDs the new user should belong to (at least one required).
passwordstring
Password for the new user's account.
primary_team_uuidstring
Which of the provided team_uuids should be marked as the user's primary team.
seat_typestring
Seat type for the new user: listener or recording.one of listenerrecording
attention_user_updateUpdate an existing Attention user's name, password, role, seat type, or team assignments.Write
Update User
Update an existing Attention user's name, password, role, seat type, or team assignments. Only the fields provided are changed.
- Idempotent
Inputs
user_idstringrequired
UUID of the user to update.
deals_enabledboolean
Enable or disable the deals feature for this user.
first_namestring
New first name for the user.
last_namestring
New last name for the user.
passwordstring
New password for the user's account.
role_uuidstring
UUID of the new role to assign to the user.
seat_typestring
Seat type for the user: listener or recording.one of listenerrecording
team_uuids_to_addarray
Team UUIDs to add this user to.
team_uuids_to_removearray
Team UUIDs to remove this user from.
attention_conversation_archiveArchive an Attention conversation so it's excluded from active listings, while preserving its underlying data and history.Destructive
Archive Conversation
Archive an Attention conversation so it's excluded from active listings, while preserving its underlying data and history.
- Idempotent
Inputs
conversation_idstringrequired
Unique identifier of the conversation to archive.
attention_user_deletePermanently remove a user from the Attention organization, revoking their access.Destructive
Delete User
Permanently remove a user from the Attention organization, revoking their access.
- Idempotent
Inputs
user_idstringrequired
UUID of the user to delete.

Workflows

Proxy API call

Node.js
Python

const result = await actions.request({
  connectionName: 'attention',
  identifier: 'user_123',
  path: '/v1/users/me',
  method: 'GET',
});
console.log(result);

result = actions.request(
    connection_name='attention',
    identifier='user_123',
    path="/v1/users/me",
    method="GET",
)
print(result)

Execute a tool

Node.js
Python

const result = await actions.executeTool({
  connector: 'attention',
  identifier: 'user_123',
  toolName: 'attention_users_list',
  toolInput: {},
});
console.log(result);

result = actions.execute_tool(
    connection_name='attention',
    identifier='user_123',
    tool_name='attention_users_list',
    tool_input={},
)
print(result)

What you can do

Setup

Install the SDK

Set your credentials

Create the Attention connection

Authorize a user and make your first call

Tools

Call it

Returns

Ask Attention

Inputs

List Calendar Events

Inputs

Get Connection Report

Inputs

Get Conversation by External ID

Inputs

Get Conversation

Inputs

Get Conversation Media Download URL

Inputs

Get Conversation Upload URL

Inputs

List Conversations

Inputs

List Emails

Inputs

List Roles

Inputs

List Scorecards

Inputs

Get Scorecards Summary

Inputs

Get Team

Inputs

List Team Members

Inputs

List Teams

Inputs

Get Usage Report

Inputs

List Users

Inputs

Import Conversation

Inputs

Update Conversation Privacy

Inputs

Update Conversation

Inputs

Create Deck

Inputs

Create Scorecard Result

Inputs

Create Snippet

Inputs

Create Team

Inputs

Update Team

Inputs

Create User

Inputs

Update User

Inputs

Archive Conversation

Inputs

Delete User

Inputs

Workflows

Related: other AI connectors