Verification & Guardrails

Plain-English Playwright end-to-end tests where Jev resolves each step's target element and judges whether verify claims hold.

Hackathon arena where 200 people attack a support agent and a Jev allow/block/escalate gate on every tool call is hardened each round.

Jev-first CLI coding agent that routes a request to a deterministic workflow which asks Jev fixed-choice questions about bounded evidence.

Proof-of-concept Claude Code plugin where Jev checks every pending tool call against the session plan, then allows, asks or blocks.

LangGraph student-support agent with PII masking and hybrid RAG, where Jev verifies drafts before auto-reply or human review.

Reference Telltale analyzer extension that asks Jev typed questions from configurable guard packs about coding-agent actions.

CI gate that asks Jev to classify database migration DDL as SAFE or DANGER and blocks destructive changes before they reach Supabase.

Code reviewer where code runs checks and slices the diff, Jev answers narrow typed questions per hunk, and code composes the verdict.

UiPath bring-your-own-guardrail connector that runs AI Trust Layer llm_as_judge checks as Jev noul questions.

Linear-backed work ledger for coding agents where a Jev-compatible model verifies done reports, blockers and plan changes against the task.

Typed judgment harness for coding agents with gates from PRD to release; runs on JSON-forced LLMs today and Jev by swapping the backend.

Experimental protocol that checks the evidence behind a worker agent's PASS or BLOCKED report, with Jev answering narrow evidence questions.

Paper code where Jev screens agent tool output for relevance and prompt injection before the agent reads it.

HKUST policy-tree guard with a 2B open classifier that routes each agent request or action to a leaf and classifies safety.

Portuguese study using Jev as a real-time guardrail and as a pre-evaluator for LLM-as-judge on customer-service agents.

TLA+-verified consensus kernel around Jev that may escalate but never returns a confident wrong verdict, tested on 1,680 pharmacy cases.

Pre-action gate and browser agent where rules decide first, then Jev or a local Jev-compatible model, emitting allow, confirm or block.

Kernel coordinating several Claude Code agents on one repo: Jev rates collision risk before each write to pass, wait or escalate.

OpenPoke fork sending yes/no decisions to Jev instead of Claude Sonnet, with an A/B on cost and latency and an injection-gate attack study.

Preliminary SHADE-Arena study of Jev as a monitor and per-action gate for covert agent sabotage, compared with Gemini 2.5.

Stdlib-Python guardrail and model router for LLM gateways on Jev, with an independent accuracy, calibration and latency evaluation.

Repository describing a Roblox Studio instance reviewer using typed Jev criteria with citations; README is mostly marketing.

Stop hook for Claude Code and Codex that refuses 'done' until a check passes after the last edit; Jev advises but never causes a block.

Precision-first RAG service where Jev routes queries, triages each retrieved chunk and verifies every claim before an answer is released.

Governance proxy between Jev or local Laya and agents that turns probabilities into allow, ask, deny, keep, truncate or drop actions.

TypeScript guardrail library plus DeepSeek Harness plugin screening prompts, tool calls, results, responses and claims with Jev.

CLI that sends text to Jev for 13 PII-category yes/no checks and a sensitivity score, then locates spans with regex and segmentation.

PRAXEON runtime supervisor for autonomous agents: actions are checked by policy, a LAYA or TypeSafe semantic judge, signed and sandboxed.

LangChain and LangGraph middleware that screens tool outputs for prompt injection and gates risky tool calls with Jev.

Vercel AI SDK layer that uses Jev to auto-approve, ask a human or block each tool call, and to prune irrelevant tools before a turn.