Skip to main content

Tracker — AI Monitoring Job

A Tracker is an AI-powered monitoring job inside a Space. You tell it what to watch, and it produces signals — scored assessments you can act on.


What You Configure

  • Name & Description — What this tracker is about
  • Instruction — What to analyze (the topic and context)
  • Score Meaning — The target to measure — what this tracker's score represents
  • Skills — Composable capabilities (e.g., Web Research, Stock Analysis)
  • Run Mode — Manual (on-demand) or Scheduled (automatic)
Example Instruction
Analyze market sentiment for Tesla (TSLA) stock.

Look at recent news, analyst reports, and social media.

Explain your reasoning.
Example Score Meaning
Market Sentiment

Custom Data Sources

Trackers can use two types of custom data:

Source TypeDescription
Tracker Vault (Private)Each tracker has a built-in vault — upload your own files (PDFs, CSVs, etc.) that the tracker uses as context.
Linked Trackers (Public)Link to other users' published trackers to use their signals as context.

Run Modes

ModeHow It Works
ManualTrigger via Console or API
ScheduledRun tracker automatically at your configured interval as frequent as 1 mintue

Publishing

You can publish your tracker to the Marketplace for others to see and usee. You earn 70% commission per run when they use it by linking it to their own trackers.


Tracker Run Cost

Each run costs: skill base cost × reasoning multiplier + add-ons

See skills → · See full pricing →

Create your first tracker →


Agent

An Agent is the AI that powers your tracker. You compose your agent's behavior by selecting skills — composable building blocks that give your agent specialized capabilities.

How It Works

  1. Select skills (optional) — Choose skills when creating a tracker, or leave empty for tracker vault data only
  2. Write an instruction — Tell the agent what to analyze
  3. Run — The agent uses the selected skills to research, compute, and produce a signal

Each skill brings specialized prompt instructions and domain-specific capabilities. Skills are additive — combine multiple skills for comprehensive analysis. With no skills selected, the agent operates as a general analyst using only your tracker vault data and linked trackers.

For the full list of available skills, search and filtering, see the Skills Catalog →.

How Skills Work

When you create or edit a tracker, you can select skills to give your agent external data access. Each skill:

  1. Brings specialized capabilities — tailoring the agent's reasoning and data access for the domain
  2. Enables domain-specific actions — such as searching the web, retrieving market data, or running computations
  3. Adds to cost — skills are priced individually and combine additively

Skills are additive — the more you add, the broader the agent's capabilities. Use web_research alone for general monitoring, or combine it with stock_research and social_media_research for comprehensive financial intelligence.

Skill ID Convention

Skill ID is always the snake_case version of the name — use this in the API:

"skills": ["social_media_research", "stock_research"]

Reasoning Modes

Control how deeply the agent thinks:

ModeMultiplierBest For
Basic×1Quick analysis, routine monitoring
Advanced×8Complex analysis, nuanced reasoning
Super×30Deep research, critical decisions

Using Skills

Via Console

When creating or editing a tracker, select skills from the dropdown. You can combine multiple skills.

Via API

Pass skill IDs in the agent_config.skills array:

Example: Multiple skills
curl -X POST https://api.quantinal.ai/v1/api/spaces/{space_id}/trackers \
-H "Authorization: Bearer qapi_..." \
-H "Content-Type: application/json" \
-d '{
"name": "Full Market Analysis",
"description": "Comprehensive stock analysis with sentiment",
"run_mode": "manual",
"agent_config": {
"instruction": "Analyze Tesla (TSLA) with financial data and social sentiment",
"skills": ["stock_research", "social_media_research", "web_research"],
"reasoning_mode": "advanced"
}
}'

Skill Pricing

When using multiple skills, costs are additive. Base cost is then multiplied by reasoning mode and add-ons.


Tracker Vault

The Tracker Vault is your tracker's private data store. Upload files or push structured JSON data via the API — the tracker's agent uses this data as context during analysis.

Description Matters

Your tracker's description gives the AI critical context about what data is stored. Be specific: instead of "reports", write "Quarterly earnings reports and analyst notes for FAANG companies". The more descriptive, the better the AI can reason about your data.

Supported Formats

TypeFormats
DocumentsPDF, CSV, TXT, Markdown
ImagesJPG, PNG (with description for search indexing)
Structured DataJSON objects or arrays (via API)

Uploading Data

File Upload

Upload documents and images via the Console (on the tracker page) or API:

curl -X POST https://api.quantinal.ai/v1/api/trackers/{tracker_id}/vault/sources \
-H "Authorization: Bearer qapi_..." \
-F "file=@report.pdf"

JSON Upload

Push structured data via API — single objects or batches of up to 1,000 rows:

curl -X POST https://api.quantinal.ai/v1/api/trackers/{tracker_id}/vault/sources \
-H "Authorization: Bearer qapi_..." \
-H "Content-Type: application/json" \
-d '{
"source_name": "earnings-data",
"data": [
{"ticker": "AAPL", "eps": 1.53, "date": "2025-Q4"},
{"ticker": "MSFT", "eps": 3.23, "date": "2025-Q4"}
]
}'
Using the API

Use your tracker_id in the URL to manage vault data.

Vault Pricing

Data uploads are generally free (rate limited). Storage counts against your Space capacity. See full pricing →

Data Lifecycle

  • TTL (Time To Live) — Set vault_ttl_days on the tracker to auto-expire data after N days (1-365)
  • Manual deletion — Delete individual sources via the API or console
  • GDPR compliance — Full data export and deletion available

Upload data to your tracker → · API Reference →