Join waitlistWaitlist
Proof packetResearchDocsAdoptersContactJoin waitlist
← Back to adopters
Adopter quickstart

PydanticAI proof path

Private-beta path for adopting Imladri with PydanticAI: initialize the adapter, wrap one risky capability, run the scanner or proof command from the repo, and review the same evidence in Profile.

Join waitlistView proof packetRead integration docs
Certification status

Certified

Certified

Certified against PydanticAI Python tool execution, including Tool.function_schema.call, Agent.run_sync, FunctionToolset, and action-alias mapping.

2/2 PydanticAI lanes passed; real-package verification covers pydantic-ai with 2 allowed body calls and zero blocked-path body calls.

Runtimepython
Access modePrivate beta
Approved beta starter
cli
imladri init --framework pydantic-ai --ci-provider github
Reference dependencies
dependencies
npm install @imladri/sdk
pip install pydantic-ai
Minimal wrapper
python
from pydantic_ai import Agent, FunctionToolset, Tool
from imladri.adapters import wrap_pydanticai_tools

def customer_lookup(customer_id: str) -> dict:
    return {"customer_id": customer_id}

def ticket_summarize(ticket_id: str) -> dict:
    return {"ticket_id": ticket_id}

guarded_tools = wrap_pydanticai_tools(
    agent,
    [
        Tool(customer_lookup, name="customer_lookup", description="Lookup customer"),
        FunctionToolset([
            Tool(ticket_summarize, name="ticket_summarize", description="Summarize ticket"),
        ]),
    ],
    strict_tools=["customer.lookup"],
    action_aliases={
        "customer_lookup": "customer.lookup",
        "ticket_summarize": "ticket.summarize",
    },
)

pydantic_agent = Agent(model, tools=[guarded_tools[0]], toolsets=[guarded_tools[1]])
result = pydantic_agent.run_sync("Look up the approved customer.")
Terminal proof evidence
terminal evidence
imladri sdk certify --real --target pydanticai --include-heavy
imladri scan --path . --fail-on new
imladri proof export --format json --output pydanticai-proof.json