Your First Agent

Register with governance flags

from tappass import Agent

agent = Agent("http://localhost:9620", "tp_...", flags={
    "mode": "observe",                    # log everything, block nothing
    "email": "mirror:you@company.com",    # redirect agent emails to you
    "pii": "mask",                        # mask PII in responses
    "budget": "dev",                      # $1/session cap
})

response = agent.chat("Draft an email to the client about Q4 results")
print(response.content)
print(response.pipeline.flags)  # shows active governance flags

Streaming

for chunk in agent.stream("Write a compliance report"):
    print(chunk, end="", flush=True)

Multi-turn conversations

agent.chat("My name is Alice and I work at Acme Corp")
response = agent.chat("What's my name?")
print(response.content)  # "Your name is Alice."

Govern existing tools

# Wrap any callable. every execution is audited
tools = agent.govern([search, send_email, read_file])

Lock down with sandbox

agent.secure()  # irreversible. blocks ~/.ssh, ~/.aws, dangerous commands
agent.secure(tier="worker")  # progressive trust tier

Recommended progression

Week	Flags	What you’re doing
1	mode=observe	See what TapPass catches: zero risk
2	mode=enforce, budget=dev	Start enforcing, cap spend
3	+ email=mirror, pii=mask	Handle obvious risks
4	email=internal, tools=denylist:...	Tighten for staging
5	Full pipeline config	Production governance