Policy pack · Compliance
Financial services: DORA and MiFID II policy pack
Policy set for AI agents in financial services, implementing controls from the Digital Operational Resilience Act (DORA) and the Markets in Financial Instruments Directive (MiFID II).
What's in it
9 policies, 5 of them blocking.
Critical policies block the step before it runs. High, medium and low ones let it run and open an incident.
| Policy | Checked | Severity | Rule |
|---|---|---|---|
| Agent must document its financial services purpose | At registration | high | field_not_empty |
| Agent must designate a responsible owner | At registration | high | field_not_empty |
| Agent must designate a maintainer | At registration | medium | field_not_empty |
| Financial agents must be high or limited risk | At registration | critical | field_in_list |
| Financial write operations require human approval | Before every step | critical | step_requires_gate |
| Market data read taints downstream trade execution | Before every step | critical | tainted_path_block |
| No LLM call between approval and trade execution | Before every step | critical | step_preceded_by_without_intervening |
| Limit LLM calls per task | Before every step | high | execution_max_steps |
| Restrict execution to market hours | Before every step | critical | working_hours_only |
Version 1.0.2. Source: manifests/compliance/financial-services-dora-mifid.yaml.
Assign it
One command, no redeploy.
Assign it from the dashboard or the CLI. Running agents pick up an assignment within the policy refresh window, five minutes by default.
- Policies
- 9, of which 5 are checked before every step.
- Version
- 1.0.2
$ kyvvu list-manifests$ kyvvu assign-manifest --agent-id <agent> --repo-id <repo> \ --manifest manifests/compliance/financial-services-dora-mifid.yamlNot legal advice. This pack is Kyvvu's interpretation of DORA and MiFID II. It isn't reviewed or endorsed by a regulator, and using it doesn't on its own make you compliant: it gives you technical controls, and a record that they ran, to support your compliance work.
About this pack
Covers human approval for financial writes, market data taint tracking (path-dependent enforcement), approval integrity without LLM interference, LLM call limits, and working-hours restrictions.
Runtime policies in this pack
- Limit LLM calls per task (critical)
- Financial write operations require human approval (critical)
- Market data read taints downstream trade execution (critical)
- No LLM call between approval and trade execution (critical)
- Restrict execution to market hours (critical)
From Kyvvu's open policy library at github.com/Kyvvu/manifests, Apache 2.0.
Next
Run the whole pack in your browser.
In your browser
Try it in the playground
The policy is loaded. Add the steps your agent takes and watch the engine decide, step by step.
On your machine
Five minutes, no account
kyvvu try runs a demo agent against the bundled baseline. Then assign this pack from the dashboard or the CLI.
For security teams
See it on your agents
A 30-minute demo on the agents you actually run, with the policies that fit them.