Amass logo
DocumentationAPI ReferenceApp gallery
Sign inSign up

Search documentation

Search the documentation by keyword

Getting Started
  • Overview
  • Quickstart
  • Authentication
  • Roadmap
  • Pricing
For AI Agents
  • LLM Quick Reference
Amass Cores
  • BiomedCore
  • DrugCore
  • RegulatoryCore
  • TrialCore
Examples
  • Starter Agent
  • API Workflows
  • Amass SKILL.md

    Quickstart

    Make your first Amass API call in under a minute.


    1. Get an API Key

    1. Sign in at platform.amass.tech
    2. Go to API Keys
    3. Click Create API Key
    4. Copy the key immediately — it starts with amass_ and is shown only once

    See Authentication for details.


    2. Make Your First Request

    Search BiomedCore for CRISPR publications:

    Shell
    curl "https://api.amass.tech/api/v1/cores/biomedcore/records?query=CRISPR&limit=5" \
      -H "Authorization: Bearer amass_YOUR_KEY"

    Search TrialCore for cancer immunotherapy trials:

    Shell
    curl "https://api.amass.tech/api/v1/cores/trialcore/records?query=cancer+immunotherapy&limit=5" \
      -H "Authorization: Bearer amass_YOUR_KEY"

    Search RegulatoryCore for FDA & EMA drug authorizations:

    Shell
    curl "https://api.amass.tech/api/v1/cores/regulatorycore/records?query=pembrolizumab&limit=5" \
      -H "Authorization: Bearer amass_YOUR_KEY"

    3. Explore Results

    Every response returns data in a consistent shape:

    JSON
    {
      "data": [
        {
          "amassId": "AMBC_...",
          "title": "...",
          "..."
        }
      ]
    }

    Use the amassId to fetch full details:

    Shell
    curl "https://api.amass.tech/api/v1/cores/biomedcore/records/AMBC_abc123" \
      -H "Authorization: Bearer amass_YOUR_KEY"

    Common Workflows

    Search, filter, get details

    The pattern below works across all Cores. For complete worked examples with real response tables, see API Workflows.

    1. Search broadly:

    Shell
    curl "https://api.amass.tech/api/v1/cores/biomedcore/records?query=biomarker+oncology&limit=100" \
      -H "Authorization: Bearer amass_YOUR_KEY"

    2. Pick a record and get full details with optional fields:

    Shell
    curl "https://api.amass.tech/api/v1/cores/biomedcore/records/AMBC_abc123?include=fulltext&include=authorsMetadata" \
      -H "Authorization: Bearer amass_YOUR_KEY"

    Convert external IDs to Amass IDs

    Use the lookup endpoint to convert PMIDs, DOIs, or NCT IDs to Amass IDs:

    Shell
    curl -X POST "https://api.amass.tech/api/v1/cores/biomedcore/records/lookup" \
      -H "Authorization: Bearer amass_YOUR_KEY" \
      -H "Content-Type: application/json" \
      -d '{"items": [{"pmid": "38123456"}, {"doi": "10.1038/s41586-024-00001-x"}]}'

    Python Example

    PYTHON
    import requests
    
    API_KEY = "amass_YOUR_KEY"
    BASE = "https://api.amass.tech/api/v1"
    
    response = requests.get(
        f"{BASE}/cores/biomedcore/records",
        headers={"Authorization": f"Bearer {API_KEY}"},
        params={
            "query": "alzheimer tau protein",
            "minPublicationDate": "2024-01-01",
            "minJournalQualityJufo": "2",
            "limit": 50,
        },
    )
    response.raise_for_status()
    
    for record in response.json()["data"]:
        print(f"{record['pmid']} — {record['title']} ({record['citationCount']} citations)")

    With retry logic for rate limits

    PYTHON
    import time, requests
    
    def fetch(url, headers, max_retries=5):
        for attempt in range(max_retries):
            r = requests.get(url, headers=headers)
            if r.status_code == 429:
                time.sleep(int(r.headers.get("Retry-After", 2 ** (attempt + 1))))
                continue
            r.raise_for_status()
            return r.json()
        raise Exception("Max retries exceeded")

    Starter agent

    For a complete working example, see the Amass Platform Starter Agent - an interactive Python agent that queries BiomedCore and TrialCore via natural language. It performs agentic retrieval out-of-the-box and ships with a router loop, conversation history, and a fallback chain across Anthropic, OpenAI, and Google providers while other LLM providers are also supported.


    Next Steps

    • BiomedCore — Full endpoint reference and record schema
    • TrialCore — Clinical trial search and filters
    • DrugCore — Drug and molecule search and filters
    • RegulatoryCore — Cross-agency FDA & EMA drug authorizations
    • API Workflows — Competitive intelligence, due diligence, and more — with real response data
    • Overview — Error handling and rate limits
    • LLM Quick Reference — Compact reference for AI agents