> ## Documentation Index
> Fetch the complete documentation index at: https://trygradient.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Assessment data sources candidates can search

> Connectors are the mail, tickets, docs, and search tools a candidate's AI can query mid-assessment. See the categories and how scoring reads them.

# Connectors

**Connectors** are data sources that candidates can browse and search during an assessment. They simulate the kind of enterprise tools and knowledge bases that professionals use daily: email, project trackers, meeting notes, internal wikis, and enterprise search. Connectors are the in-assessment data sources, and are separate from [ATS integrations](/docs/integrations), which connect Gradient to your hiring stack.

## Connector categories

When adding connectors to an assessment, admins choose from categories. Each category has named variants so the connector appears branded to the candidate (e.g., "Gmail" instead of generic "Mail").

| Category | Variants | Description |
| - | - | - |
| **Enterprise Search** | Enterprise Search, Glean, Coveo | Company knowledge base with keyword search |
| **Meeting Transcripts** | Meeting Transcripts, Granola, Otter | Search meeting notes and call transcripts |
| **Mail** | Email, Gmail, Outlook | Search email messages and threads |
| **Tickets** | Linear, Asana, Jira | Search issues and project tasks |
| **Company Documents** | Notion, Confluence, Google Drive | Search company documents and wikis |

All built-in categories use the same keyword-ranking search backend (TF-IDF style). The variant name only affects what the candidate sees and the tool name the AI uses. **Meeting Transcripts** additionally supports participant and meeting-type filters.

## How candidates use connectors

During the **Explore** phase, candidates get oriented and browse the available data sources. During the **Task** phase, they search those data sources through the AI assistant using natural language queries. See [Candidates & Sessions](/docs/concepts/candidates-and-sessions) for the phase model.

The search returns relevant documents that the candidate can then reference in their deliverable.

## Signal and noise

Each data source is tagged as either **signal** (relevant to the task) or **noise** (a distractor). This distinction is invisible to the candidate, who sees all data sources equally and must determine which ones are useful.

The scoring engine tracks:

* Which data sources the candidate connected
* Which documents they searched for and reviewed
* Whether they used signal documents in their deliverable
* Whether they included noise data uncritically

## Candidate permissions

Connectors have no permission of their own. Admins control what else candidates can do (skills, memory, the agents.md configuration) via the **Candidate Permissions** card in the assessment's Data step — see [Assessments](/docs/concepts/assessments#candidate-permissions) for the full set.

Document visibility is not a permission either. Candidates always see a connector's data files in the workspace **Files** cabinet. The connector dialog lists no documents: it connects the connector, which is what gives the AI access to search it.

<Tip>Connector data can be managed programmatically via the [Connector Data API](/docs/api-reference/connector-data). Upload CSV, JSON, TXT, or Markdown files.</Tip>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.