CAIN-42 CAIN Studio

Recipe · Any other framework

Any other framework: guard refunds with CAIN

Step by step, for a support agent that issues refunds: install, wrap the tool, see the live decision, write and test a rule, handle approvals.

Last reviewed 2026-10-02

1 Get a key

No key yet? Create a free account (every new account starts with a 7-day trial), then copy the key from the console. Requests go from your browser straight to this site.

Give each agent its own key in production (console → Agent keys): decisions, trust history and revocation are then per agent.

2 Install

pip install "cainstudio @ https://cainstudio.online/cainstudio-0.4.1-py3-none-any.whl#sha256=1bea5cf49aeeb2775acec58933fc39b008a1c84bfd7c9690c54723ed707af689"
export CAIN_API_KEY=...

cainstudio 0.4.1, pinned by URL and SHA-256 so pip installs exactly the published wheel (the package is not on PyPI yet). Framework dependencies come from PyPI as usual.

3 Put CAIN in front of any Python callable

guard_tools() and @guarded put CAIN on the call path of a plain callable, for Strands, Semantic Kernel, Haystack, smolagents or a home-grown loop.

from cainstudio.integrations.universal import guard_tools

def issue_refund(order_id: str, amount_usd: float) -> str:
    """Refunds: a support agent that issues refunds."""
    ...  # your existing code, unchanged

tools = guard_tools([issue_refund], agent_id='refunds-agent')   # hand these to Strands, Semantic Kernel,
                                                    # Haystack, smolagents or your own loop

On a refusal the agent gets the reason (or an exception with on_block="raise"). The tool body never runs: not on a refusal, not on a hold, not when CAIN cannot be reached.

4 See what CAIN decides for this exact call

This is the request the integration sends when the model calls issue_refund with these arguments. record: false evaluates it without writing an evidence record. A new agent has no trust history, so expect REQUIRE_APPROVAL at first; destinations outside your egress allowlist are refused by the egress stage.

5 Write the rule, and test it before you save it

Routine refunds stay automatic; large ones are held for a human, with the order and amount in the approval.

The panel sends the draft rule to the rule tester: it says which rule would decide the call and saves nothing. Swap in the safe arguments below to see it pass through. matches is a case-insensitive glob (*, ?), not a regular expression; conditions on one rule must all hold; the first matching rule by priority wins.

Safe arguments: {"order_id": "ord_1042", "amount_usd": 12}

When it does what you want, save it from the console or with POST /fabric/tool-rules:

curl -sS -X POST https://cainstudio.online/fabric/tool-rules \
  -H "X-API-Key: $CAIN_API_KEY" -H 'Content-Type: application/json' \
  -d '{"name": "refunds-guard", "effect": "require_approval", "priority": 10, "match_path": "/tools/issue_refund", "conditions": [{"field": "amount_usd", "op": "gt", "value": 50}]}'

6 Handle the calls that wait for a person

A held call is not executed. It appears in the approval queue with its exact arguments; an approval lets that one call run once. Adapters can wait instead of returning: wait_for_approval=120.

GET /fabric/approvals

7 Check it before you ship

cainstudio redteam --agent refunds-agent   # dry-runs dangerous calls; exit 2 if any would run
cainstudio decisions                 # what was decided, and why
cainstudio explain <decision_id>

Every recorded decision is signed; Cain().verify(decision) checks its quorum certificate on your machine (Python SDK).

More

Try CAIN-42 on your own agents

Create a free account and every new account starts with a 7-day trial of the full platform. Or try the sandbox first, with no account at all.

Create a free account →  ·  Try the sandbox  ·  See the whole ecosystem