Post Oak Labs Showcase · #27 of 33 Agentic Mandate Sandbox
🔒 All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Demo #27 · Agentic Runtime · Compose → Test → Apply
5 bundled mandate templates Per-step execution trace @ainumbers.co/sandbox-trace-v1

Test the mandate before the agent ships it.

Drop in any AP2 mandate this showcase emits — AML, BaaS, DORA gap, instant-pay fraud, stablecoin readiness — queue a candidate agent action, and watch the runtime traverse the mandate's rules. The trace shows which rule fired, why, what state followed, and the final allow / step-up / refer / refuse decision. The artifact you keep is the trace, exported as AP2 against @ainumbers.co/sandbox-trace-v1.

Zero PII · Client-side Sandbox model is illustrative — production runtimes parse the same mandate structure Last Reviewed · 2026-05-13
EU AI Act · DORA Art. 25–26 — pre-production testing obligations

EU AI Act Article 14 (human oversight) and Article 15 (accuracy, robustness, cybersecurity) apply to high-risk AI systems in financial services. DORA Articles 25–26 require resilience testing of ICT systems including threat-led penetration testing for in-scope entities. The Financial Stability Board (FSB) AI principles (Nov 2024) explicitly call out pre-deployment testing of agentic FS AI. The mandate is the contract; the sandbox is the test rig that proves the contract holds before production.

Sources: EU 2024/1689 (AI Act) Arts. 14, 15, Annex III · EU 2022/2554 (DORA) Arts. 25–26 · FSB AI in financial services (Nov 2024)
§1 · Mandate Template none loaded

Load a mandate

Pick a bundled template (each is a representative mandate this showcase emits) or paste your own AP2 JSON. The sandbox parses the schema, runs the action against it, and emits a trace.

…or paste your own AP2 mandate JSON
No mandate loaded. Pick a template above to begin.
§2 · Candidate Action — scoped to mandate

Queue a candidate action

Actions are scoped to the loaded mandate's schema. The default parameters trigger different evaluation branches; tweak and re-run to explore the policy lattice.

§3 · Execution Trace

What the runtime did

Run the sandbox to see the per-step trace.

— run sandbox to populate —
AP2 v1.0 · idle
Agentic Runtime

Building agentic payment infrastructure?

We design the deterministic AP2 / MCP policy layer that runtimes like this one depend on. If you're putting agents anywhere near money, let's pressure-test your mandate architecture.

Talk to our team →
Post Oak Labs · production deployments in the Caribbean & South Asia · works with a limited number of institutions at a time
Exported