Verification & Guardrails

Python guardrail with a Streamlit dashboard that sends agent tool calls to Jev and allows, blocks or asks for clarification.

Calibrated alignment verifier that checks LLM responses and agent plans for sycophancy, deception, overreach and dark patterns with Jev.

Windows antivirus and EDR prototype that extracts file, process and URL features and asks Jev for verdicts, severity and indicators.

Offline-by-default demo of six Jev decision workflows: model tiering, prompt screening, tool-call risk, reranking and more.

Experimental browser-only MCP server where Jev picks a code-owned action ID and a human approves before execution.

OpenAI-compatible streaming proxy that holds tokens in a buffer and releases them only after a Jev check passes, cutting leaks pre-screen.

Scaffold of n8n workflow patterns using Jev for PII screening, agent guardrails as hooks, and workflow evals with Jev as judge.

UiPath prior-authorisation triage agent with a Jev guardrail that measures and records PII crossing the model boundary without masking.

Staged code-review workflow for JS/TS where Jev screens risk, picks evidence, classifies mechanism, scores severity and routes reviewers.

Autonomous PR review bot with typed Jev questions, deterministic approval gates and escalation of uncertain reviews to trusted owners.

Claude Code plugin for Rust review: compiler and Clippy facts first, Jev triages semantic risks, Claude reviews and Jev verifies findings.

VS Code extension that asks Jev a yes/no question ('is this ok?') about each line you edit and marks it thumbs up or down.

Companion code comparing Google ADK and Microsoft Agent Framework for structured video timelines, with Jev as a shared per-segment QC gate.

Concept prototype for marking NZQA scripts from rubric criteria alone with one Jev call per script and confidence-based triage.

GitHub App that asks Jev to classify each pull request as LOW, NORMAL or SPECIALIST risk and maps that to approve or request review.

Proof-of-concept scanner that asks Jev hundreds of bug questions per Solidity file and writes a heat map of likely vulnerabilities.

Educational code where a local LLM voices a game NPC and Jev classifies player messages and checks every line for spoilers.

Rewrites AI drafts in your own voice, with Jev as the judge in a bounded loop that checks style and that meaning stays intact.

Hermes Agent skill that turns an intention into a checkable finish line, with shell checks and Jev judging the fuzzy requirements.

OpenCode plugin collection whose oc-auto-perms package uses Jev to check tool-call intent against natural-language permission rules.

Oxlint plugin where lint rules are plain-English yes/no questions about code that Jev answers, reporting matches above a cutoff.

System 1 ingestion gate that asks Jev intent, risk and sensitivity in one call, then blocks, answers deterministically or passes to an LLM.

Execution-control layer for MCP agents: deterministic policy, Jev decisions, human approval and one-use execution permits.

Pi guard plugin with timing-based rules, Jev risk checks on tool calls, output redaction and reminders for repeated failures.

Buildathon entry adding failproofai policies plus Jev intent checks so an IT service-desk agent stops harmful actions.

Playwright TypeScript project using Jev for semantic assertions, element picking, goal-driven steps and test failure classification.

Small one-file Pydantic AI examples where Jev guards prompts, gates shell commands, judges evals and plays Flappy Bird.

Rust governance layer that treats Jev's per-tool-call scope and destructiveness checks as evidence feeding persistent trust state.

Datadog Labs Rust library for observability control loops where Jev recommends an action and declared guards decide if it commits.

Public Neon Function gateway that has Jev judge request bodies for prompt injection or unsafe replies before optionally forwarding them.