Two SDKs to secure AI agent loops: Predicate Authority for pre-execution authorization, and Predicate Runtime for post-execution verification. Keep your agents deterministic and safe.
See how Predicate Authority blocks unauthorized actions at runtime—before they execute.
┌───────────────┐ ┌─────────────────┐ ┌───────────────────────┐
│ LLM/Agent │───▶│ PRE-EXECUTION │───▶│ POST-EXECUTION │
│ (Claude) │ │ GATE (Sidecar) │ │ VERIFICATION (SDK) │
└───────────────┘ │ ALLOW / DENY │ │ PASS / FAIL │
└─────────────────┘ └───────────────────────┘
┌─────────────────┐ ┌──────────────────┐
│ Intake Agent │ POST /v1/delegate│ Rust Sidecar │
│ (compromised) │ ──────────────────▶│ │
│ │ │ Chain Delegation│
│ mandate: m_001 │ ◀──────────────────│ Evaluation │
│ fs.read:/inbox │ { allowed: false │ │
└─────────────────┘ reason: "scope │ ┌────────────┐ │
exceeds_parent"}│ │ policy.yaml│ │
╳ │ └────────────┘ │
│ BLOCKED └──────────────────┘
▼
┌─────────────────┐
│ HR Admin Agent │ Never receives
│ (never called) │ a valid mandate
└─────────────────┘Predicate-Authority: zero-trust runtime authorization to protect AI agents from prompt injection and unauthorized tool calls before execution.
Reproducible browser agent demos using structure-first snapshots and Jest-style assertions.
"Open the top Show HN post"
Demonstrates ordinal reasoning ("first", "top") using semantic geometry. The agent identifies ranked items without screenshots.
"SPA login + profile verification"
Handles async hydration, disabled-to-enabled buttons, and profile loading on a modern Next.js SPA. No sleeps or magic waits.
"Search → open result → add to cart"
JS-heavy stress test on a real production site. Multi-step shopping flow with noisy DOM and frequent layout changes.
All demos are fully reproducible. Clone the playground, run with Qwen 2.5 3B (or any local model), and see structure-first agents in action.
Demo SPA: localllamaland.com