Quickstart

​

1. Create Account

​

2. Generate an API Key

1. From the Dashboard, click Add under API Keys
2. Name your key
3. Select Test environment (production requires a paid plan)
4. Click Generate Key
5. Copy and save the key — it’s only shown once

​

3. Set Up Your S3 Bucket

1. Create an S3 bucket (names are globally unique, so include your company name — e.g., acme-corp-raw-ai-logs)
2. Create the following IAM policy:
   Copy

   {
     "Version": "2012-10-17",
     "Statement": [{
       "Effect": "Allow",
       "Action": ["s3:PutObject", "s3:GetObject", "s3:ListBucket"],
       "Resource": [
         "arn:aws:s3:::acme-corp-raw-ai-logs",
         "arn:aws:s3:::acme-corp-raw-ai-logs/*"
       ]
     }]
   }
   
3. Create an IAM user and attach the policy
4. Generate access keys for the user (select “Application running outside AWS”) and save them — the secret is only shown once

​

4. Install the SDK

mkdir notary-demo && cd notary-demo
python3 -m venv .venv
source .venv/bin/activate
pip install "agentsystems-notary[langchain]" langchain-anthropic python-dotenv

mkdir notary-demo && cd notary-demo
python3 -m venv .venv
source .venv/bin/activate
pip install "agentsystems-notary[crewai]" crewai python-dotenv

​

5. Configure Environment

# AgentSystems Notary
AGENTSYSTEMS_NOTARY_API_KEY=sk_asn_test_...

# AWS credentials for your S3 bucket
AWS_ACCESS_KEY_ID=...
AWS_SECRET_ACCESS_KEY=...
AWS_DEFAULT_REGION=us-east-1

# Your LLM provider
ANTHROPIC_API_KEY=...

​

6. Integrate the SDK

import os
from dotenv import load_dotenv
from agentsystems_notary import LangChainNotary
from langchain_anthropic import ChatAnthropic

load_dotenv()

# Initialize Notary callback
notary = LangChainNotary(
    api_key=os.getenv("AGENTSYSTEMS_NOTARY_API_KEY"),
    slug="customer-123",  # Your customer's identifier
    org_bucket_name="acme-corp-raw-ai-logs",
    debug=True
)

# Add to any LangChain model
model = ChatAnthropic(
    model="claude-sonnet-4-5-20250929",
    api_key=os.getenv("ANTHROPIC_API_KEY"),
    callbacks=[notary]
)

# All LLM calls are now logged
response = model.invoke("What is 2 + 2?")
print(response.content)

python test_langchain.py

import os
from dotenv import load_dotenv
from agentsystems_notary import CrewAINotary
from crewai import Agent, Task, Crew, LLM

load_dotenv()

# Initialize Notary (hooks register automatically)
notary = CrewAINotary(
    api_key=os.getenv("AGENTSYSTEMS_NOTARY_API_KEY"),
    slug="customer-123",  # Your customer's identifier
    org_bucket_name="acme-corp-raw-ai-logs",
    debug=True
)

# Create LLM
llm = LLM(
    model="anthropic/claude-sonnet-4-5-20250929",
    api_key=os.getenv("ANTHROPIC_API_KEY")
)

# Create agent and task
agent = Agent(
    role="Research Analyst",
    goal="Answer questions accurately",
    backstory="You are an expert analyst.",
    llm=llm
)
task = Task(
    description="What is 2 + 2?",
    expected_output="The answer to the math question",
    agent=agent
)
crew = Crew(agents=[agent], tasks=[task])

# All LLM calls are now logged
result = crew.kickoff()
print(result)

python test_crewai.py

​

7. Generate an Audit Ticket

1. Go to notary.agentsystems.ai
2. Click Tenants in the navbar (or View All from the Tenants card on the Dashboard)
3. Click Generate Verification Ticket
4. Select your tenant from the dropdown
5. Select Test data type (production requires a paid plan)
6. Leave the default date range or adjust if needed
7. Check the confirmation box and click Download Ticket

​

8. Export Your Logs

​

9. Verify

1. Go to verify.agentsystems.ai
2. Upload the audit ticket (.json file)
3. Upload the logs ZIP
4. Click Start Verification