Independent Research
Designing, deploying, and defending
and defending
autonomous AI systems
Research at the intersection of agentic AI architecture, enterprise security, and human-centered system design.
Read Latest PaperResearch Pillars
Research Pillar 01
AI Systems, Agents and Security
Primary technical research axis focused on agentic architectures, security red-teaming, and runtime enforcement frameworks.
Core Question
"How do we design, deploy, and defend autonomous AI systems operating in real organizations?"
Representative Topics
- Agentic architectures and LLM orchestration
- Agent-to-agent influence vectors
- Prompt injection and policy puppetry
- Runtime enforcement frameworks
- MITRE ATLAS operationalization
Output Types
Academic papersRed-team playbooksOpen-source frameworksRisk briefings
Selected Work
2026.Research Paper
Agentic Binary Reverse Engineering: State of the Art, Architecture, Benchmarks, Failure Modes, and Research Agenda
AI Systems and Security
2026.Research Paper
Agentic Patch Validation in Automated Vulnerability Repair
AI Systems and Security
2026.Research Paper
Sandboxing and Capability Control for Tool-Using Autonomous Agents
AI Systems and Security
2026.Research Paper
Tool-using LLM agent security and prompt-injection defenses
AI Systems and Security
Conceptual Framework
fig. 01Research Integration Model
Current Focus
Active Research Threads
Active
Multi-Agent Prompt Injection Chains
Writing
Indirect Injection Propagation
Active
Orchestrator Policy Enforcement
Active
Glitch Token Mining
Building
Enhanced Token Validation
Research
Embedding Cluster Analysis
Testing
Email Extraction Failure Modes
Draft
Responsible Disclosure Workflow
Building
Multi-Agent Prompt Injection Pillar Page
Drafting
Glitch Token Glossary Cluster
Active
AI Referral Measurement Setup
Active
llms.txt + Sitemap Foundation
Approved
Triage Rubric v1
Publications
Selected Papers
2026·Research Paper
Preserving Learning in Generative AI Tutoring Systems: Pedagogical Safety, Cognitive Effort, and Adaptive Scaffolding
Human Learning and Knowledge Systems
2026·Research Paper
Agentic Binary Reverse Engineering: State of the Art, Architecture, Benchmarks, Failure Modes, and Research Agenda
AI Systems and Security
2026·Research Paper
Agentic Patch Validation in Automated Vulnerability Repair
AI Systems and Security
2026·Research Paper
Generative AI Tutors and Personalized Adaptive Learning Systems
Human Learning and Knowledge Systems
2026·Research Paper
Effects of AI Assistance on Critical Thinking and Cognitive Offloading
Human Learning and Knowledge Systems
2026·Research Paper
Tool-use reliability, function-calling robustness, and structured output enforcement
Applied Intelligence and Automation
2026·Research Paper
Compound AI systems and orchestration patterns for multi-step automation
Applied Intelligence and Automation
2026·Research Paper
Sandboxing and Capability Control for Tool-Using Autonomous Agents
AI Systems and Security
2026·Research Paper
Tool-using LLM agent security and prompt-injection defenses
AI Systems and Security
2026·Research Note
Hardening Multi-Agent Systems Against Prompt Injection
AI SecurityPrompt InjectionMulti-Agent SystemsDefensesHardening
2026·Project Writeup
NOW9000: A Voice-Based AI Jailbreak Game
JailbreakingVoice AgentGuardrailsPrompt InjectionSocial Engineering
2026·Follow-on Research
Full-Vocabulary Glitch Token Census and ASR Validation Methodology Correction
LLM SecurityGlitch TokensASR ValidationMethodology
2026·Follow-on Research
Auditing Glitcher's ASR Validation and Mining Coverage: Deterministic Decoding Bugs and Candidate Generation Gaps in Glitch Token Discovery
LLM SecurityGlitch TokensResearch AuditMethodology
2026·Research Paper
Prompt Injection, Tool Hijacking, and Data Exfiltration Defenses in RAG/Agent Systems
AI SecurityPrompt InjectionRAG SecurityAgent Security
2026·Research Tooling
Glitcher: Mining and Classifying Glitch Tokens in Large Language Models
LLM SecurityGlitch TokensTooling
2023·SecTor 2023
Harnessing Large Language Models for Enhanced Malware Reverse Engineering
MalwareReverse EngineeringLLMSecTor 2023
Support
Fund Independent Research
This is self-funded, independent security research. Contributions directly support compute costs, API access, and open publication.
address
not configured
not configured
Bitcoin Address
address not yet configured
Current Balance
—
About
Background
Richards.AI is an independent research practice focused on the security, reliability, and human impact of autonomous AI systems. The work spans academic research, enterprise consulting, and open-source tooling.
Current primary focus: agent architecture security, with particular emphasis on multi-agent influence vectors, runtime enforcement frameworks, and operationalizing threat models like MITRE ATLAS for enterprise deployments.
12+
Years in Security
Enterprise
ServiceNow Focus
Open
Research and Code
Research Philosophy
"The three pillars are not separate silos. Security asks can we control it?Applied intelligence asks can we make it useful? And human learning askscan it genuinely improve lives? Each informs and strengthens the others."
Jer Richards
Principal Researcher