Resources/Blog

Writing on trust in agents

Essays, trust reports, research notes, how-tos, compliance, partnerships, and announcements — press coverage lives in News.

A small robot whose arms are a hammer, a screwdriver, paintbrushes and pens FEATURED · ESSAYNov 30, 2024 Factotum not fiduciary Today’s AI agents are factotums — competent but loyal to their developers. What we deserve are fiduciary agents with a duty of care. Read the essay →
§ COMPLIANCE Staying Local? Why The On-Premise Option Matters for Agentic AI Security Aug 30, 2026 › HOW-TO How Exactly Does Vijil Handle Agent Identity? No passwords, no keys in env vars. An agent's identity is minted from what it is verifiably, and proved every time it exercises an authorized capability. Aug 16, 2026 ❝ ESSAYS Vijil's Genomic Sequence - The Mutation of Agentic Trust's DNA Three essays from November 2024, republished with their original dates — the genome from which Vijil grew. Aug 15, 2026 ❝ ESSAYS The Guardrails Gap: Open Source Quick Fix Pros and Cons Aug 5, 2026 § COMPLIANCE ISO 42001 Compliance: The path to operationalizing agentic AI Jul 27, 2026 § COMPLIANCE Untangling the Agentic AI Governance Bottleneck Jul 15, 2026 ◆ PARTNERSHIPS Bridging the AI Agent Governance Gap: From Policy to Practice Jun 21, 2026 ∴ RESEARCH NOTES Embedding Trust: A New Model for Detecting LLM Hallucinations Jun 15, 2026 ❝ ESSAYS How Much Trust Is Enough for AI Governance? Jun 7, 2026 ❝ ESSAYS Trust Is the Real Bar for Production AI Agents Jun 3, 2026 § COMPLIANCE From Policy to Code: The NAIC Model as a AI Agent Governance Blueprint May 23, 2026 ∴ RESEARCH NOTES Mapping the Unknown: Open Problems in Frontier AI Risk Management Apr 29, 2026 ⚑ ANNOUNCEMENTS Leading AI Researcher Tim G. J. Rudner Joins Vijil as Chief Scientist Vijil research team focuses on fundamental challenges of building trustworthy AI agents for enterprise use Apr 28, 2026 ❝ ESSAYS Crossing the agent pilot to production chasm Mar 31, 2026 ∴ RESEARCH NOTES Towards Proactive Compliance: Why Partial Preferences Matter Mar 9, 2026 › HOW-TO Revisiting LLM Security scanning with garak in the agentic era Mar 2, 2026 ❝ ESSAYS 2026: The Year That Businesses Get AI Agents They Can Trust Jan 22, 2026 ⚑ ANNOUNCEMENTS Vijil Raises $17 Million to Make AI Agents Resilient, Named a Gartner® Cool Vendor Customers such as SmartRecruiters deploy trusted AI agents 75% faster with Vijil Nov 24, 2025 ◆ PARTNERSHIPS Deploy Vijil Dome to defend AI Agents on DigitalOcean Kubernetes Deploying Vijil Dome to defend your AI agents running on a DigitalOcean Kubernetes cluster is now easier Nov 11, 2025 ◆ PARTNERSHIPS How Can AI Agents Be Audited Automatically? Phala + Vijil deploy trusted agents in a TEE Oct 7, 2025 ◆ PARTNERSHIPS Trusted Agents at Scale: Groq with Vijil for Speed and Security Trust scores for four Groq-hosted models, then the walkthrough: build the agent on Groq, evaluate it with Vijil, defend it with Dome Oct 6, 2025 ⚑ ANNOUNCEMENTS From Swords to Plowshares: Generating Guardrails from Evaluations Announcing a new feature of Vijil Evaluate that enables you to automatically generate custom guardrails based on your agent eval Sep 14, 2025 ⚑ ANNOUNCEMENTS Exploring Chatbot Mistakes: from Root Causes to Potential Solutions In this reflection from our Marketing Intern, Lena, we explore why chatbots still make toxic, biased, or baffling mistakes—and how transparency, better… Aug 4, 2025 › HOW-TO How Secure is Your Agent under the Vijil Dome? Discover how to protect your LangChain agents from prompt injection, data leaks, and harmful outputs using Vijil Dome’s guardrails and track improvements… Jul 29, 2025 › HOW-TO Customizing Guardrails with Vijil Dome In Part 3 of our Vijil Dome series, learn how to build custom guardrails that enforce domain-specific protections—like PII detection—on top of Dome’s… Jul 28, 2025 › HOW-TO Defending AI Agents with Vijil Dome: LangChain Learn how Vijil Dome integrates seamlessly with LangChain to add powerful, chain-native security guardrails for building robust, secure, and… Jul 27, 2025 › HOW-TO Defending AI Agents with Vijil Dome: OpenAI Clients In this post, we introduce Vijil Dome, our open-source guardrails framework designed for real-time, policy-based control of agent behavior. Dome offers… Jul 23, 2025 ❝ ESSAYS Vijil Dome: Securing the Future of AI Agents At AWS Summit NYC, a shift toward enterprise-ready AI agents became clear. Jamie Mneimneh (Brightmind Partners) and Vin Sharma (Vijil) break down why… Jul 21, 2025 › HOW-TO Defending Google ADK Agents with Vijil Dome Building secure AI agents is just the start—defending them is where it counts. Follow our step-by-step guide to integrate Vijil Dome into your ADK agent and… May 20, 2025 › HOW-TO Test the Trustworthiness of Agents built with Google ADK Google Agent Development Kit (ADK) is a powerful framework for building AI agents. But as every agent developer knows by now, creating an agent is the easy… May 12, 2025 › HOW-TO Defending DeepSeek R1 with Vijil Dome While DeepSeek R1 is competitive to OpenAI GPT-o1 on reasoning tasks, it has several failure modes that hamper its use in business-critical applications.… May 5, 2025 ⚑ ANNOUNCEMENTS Vijil Named to the 2025 CB Insights’ List of the 100 Most Innovative AI Startups Vijil recognized for innovations in trustworthy AI agents Apr 23, 2025 ⚑ ANNOUNCEMENTS Vijil Announces Listing of Vijil Evaluate on Google Cloud Marketplace, Accelerating Deployment of Trustworthy AI Agents into Production Vijil announced today that Vijil Evaluate, its AI agent testing service, is now available on Google Cloud Marketplace to help developers test agents with… Apr 1, 2025 ◆ PARTNERSHIPS Autonoma deploys an IoT service assistant quickly with trustworthy AI tools from Vijil Autonoma uses AI agent hardened by Vijil on DigitalOcean to reduce IoT service troubleshooting time Mar 26, 2025 ◎ TRUST REPORTS vijil Trust Report DeepSeek R1 The VIJIL Trust Report for DeepSeek R1 indicates critical levels of risk with security and ethics, high levels of risk with privacy, stereotype, toxicity,… Mar 19, 2025 ❝ ESSAYS AI Ethics Benchmarks Are Failing. Here’s What Actually Works. Are AI ethics benchmarks actually useful? Many companies rely on abstract, outdated tests that don’t reflect real-world compliance. Discover why Vijil’s AI… Mar 17, 2025 ❝ ESSAYS Factotum not Fiduciary Today's AI agents are factotums — competent but loyal to their developers. What we deserve are fiduciary agents with a duty of care. Nov 29, 2024 ❝ ESSAYS Deconstructing Trust We cannot trust AI agents the way we trust machines or people. Perhaps we ought to trust them the way we trust corporations. Nov 22, 2024 ❝ ESSAYS Trust in Agents The first in a series excavating the root of trust — and why we cannot trust AI agents the way we trust machines or people. Nov 14, 2024 ❝ ESSAYS Get Your MMLU Score 20X Cheaper and 1000x Faster Run MMLU-Pro benchmarks 20x cheaper and 1000x faster with Vijil Evaluate. Discover how our high-performance evaluation engine and Lite benchmarks deliver… Sep 11, 2024 ⚑ ANNOUNCEMENTS Vijil Emerges from Stealth with Seed Funding from Mayfield and Gradient Ventures Vijil came out of stealth on July 24 with funding from Mayfield's AIStart seed fund and Gradient Ventures, Google's AI-focused seed fund. We are thrilled to… Aug 27, 2024 ◎ TRUST REPORTS Evaluating Meta Llama 3 for Stereotyping To help organizations build AI agents that humans can trust Apr 26, 2024 ❝ ESSAYS A Conversation with garak's Creator, Leon Derczynski, on LLM Security Catch our live conversation with Leon Derczynski, creator of garak, the leading open-source LLM vulnerability scanner. We explore the motivations behind… Jan 24, 2024