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.
Getting Started
This guide walks you through the complete Gradient workflow: creating an assessment, inviting a candidate, and reviewing their score.
Prerequisites
- A Gradient account with admin access
- At least one candidate to invite
Step 1: Create an assessment
You can create an assessment from the dashboard UI or via the API.
Dashboard
API
Use a template
- Go to Assessments in the sidebar
- Click New Assessment
- Fill in the task brief, role, and time limits
- Attach data sources (or start with a template)
- Click Create
curl -X POST https://app.trygradient.ai/api/assessments/create \
-H "Authorization: Bearer gai_your_key" \
-H "Content-Type: application/json" \
-d '{
"name": "Senior PM Assessment",
"role": "Senior Product Manager",
"taskPrompt": "Create a product strategy presentation for entering the European market. Use the available data sources to support your recommendations.",
"deliverableType": "pptx",
"taskTimeMinutes": 50
}'
Seed pre-built templates with sample data sources:curl -X POST https://app.trygradient.ai/api/assessments/seed \
-H "Authorization: Bearer gai_your_key"
Step 2: Add data sources
Attach documents that candidates can search during the assessment. Mark some as signal (relevant) and leave others as noise (distractors).
# Upload a CSV file as connector data
curl -X POST "https://app.trygradient.ai/api/assessments/ASSESSMENT_ID/connector-data/upload" \
-H "Authorization: Bearer gai_your_key" \
-F "file=@revenue-report.csv" \
-F "connectorType=enterprise_search" \
-F "isSignal=true"
Step 3: Invite a candidate
- Open the assessment
- Click Invite Candidate
- Enter their name and email
- They’ll receive an email with a unique assessment link
curl -X POST "https://app.trygradient.ai/api/assessments/ASSESSMENT_ID/invite" \
-H "Authorization: Bearer gai_your_key" \
-H "Content-Type: application/json" \
-d '{
"email": "jane@example.com",
"name": "Jane Smith"
}'
Step 4: Wait for submission
The candidate receives an email with a link to the assessment workspace. They’ll work through the setup and task phases, then submit their deliverable.
You can check the session status:
curl "https://app.trygradient.ai/api/sessions?assessmentId=ASSESSMENT_ID&status=submitted" \
-H "Authorization: Bearer gai_your_key"
Step 5: Trigger scoring
Once a candidate submits, trigger the scoring engine:
curl -X POST https://app.trygradient.ai/api/scoring \
-H "Authorization: Bearer gai_your_key" \
-H "Content-Type: application/json" \
-d '{"sessionId": "SESSION_ID"}'
Step 6: Review results
Retrieve the score breakdown:
curl "https://app.trygradient.ai/api/scoring/SESSION_ID" \
-H "Authorization: Bearer gai_your_key"
The response includes:
- Category scores with point breakdowns
- Percentile rankings against other candidates
- Summary text describing overall performance
- Follow-up questions for the interview
You can also review the full session in the dashboard, including session replay, the AI conversation transcript, and the candidate’s workspace configuration.