AI Agent Failures Usually Trace Back to Instruction Defects, Not Model Limitations
After a year of running AI agents on live production workflows, one practitioner has stopped using the phrase "the model got dumber." Most cases that appear to be model stupidity or hallucinations actually result from three recurring defects in the instructions given to the agent.
The first defect occurs when a rule is written in ordinary prose rather than as an explicit, machine-actionable constraint. The second defect appears when instructions are framed negatively, telling the agent what not to do instead of defining the required behavior. The third defect arises when a rule lacks any verification step, allowing the agent to proceed without checking compliance.
The author notes that these patterns emerged consistently across tasks in programming, DevOps, analytics, and information security. By systematically rewriting instructions to eliminate prose form, negative phrasing, and missing checks, the frequency of apparent model failures dropped sharply. The conclusion is that "agent is dumb" is usually a diagnosis of the prompt, not the underlying model.
Related articles
AI in Vulnerability Management: Assistant, Weapon, and Emerging Target
Artificial intelligence now plays three simultaneous roles in vulnerability management: it assists defenders with prioritization and analysis, arms attackers with faster discovery tools, and introduces entirely new classes of assets and vulnerabilities that must be managed. Mature applications include ML-driven risk scoring in platforms such as Tenable VPR, Qualys TruRisk and Rapid7 Active Risk, which cut priority lists by 40-50 percent, and Google’s Big Sleep project that discovered a real-world SQLite flaw (CVE-2025-6965) before exploitation occurred. On the offensive side, systems like XBOW completed 104 test scenarios in 28 minutes versus 40 hours for human testers, shrinking the average time-to-exploit window to negative seven days according to Mandiant M-Trends 2025. New AI-specific attack surfaces are documented in the OWASP Top 10 for LLM applications and the emerging MCP Top 10, covering prompt injection, tool poisoning, and command injection against Model Context Protocol servers. Real incidents already include Air Canada’s chatbot inventing a refund policy and New York City’s MyCity bot dispensing illegal advice for nearly two years. Researchers have also demonstrated sandbox escapes in coding agents from Cursor, OpenAI Codex and Claude Code through classic file-write-and-execute patterns rather than any sentient behavior.
Solar Unveils AI Firewall to Protect Against Dangerous Actions by AI Agents
At SOC Forum 2026, Russian cybersecurity firm Solar presented its new Solar AI Firewall solution designed to filter requests to external AI models and block prompt injections. The product sits between users and AI systems, applying multi-layer protection that responds in milliseconds and counters 200 types of attacks. Special emphasis is placed on autonomous AI agents capable of performing actions in corporate systems, where the firewall inspects operations and blocks potentially harmful ones. Integrations with DLP, SIEM, and IDM tools are supported, and the solution is available both as a cloud service and for on-premises deployment. Solar has been testing the product internally and observed significant shadow AI usage outside corporate controls. The company plans further development of comprehensive AI risk management capabilities.
TenetBench Benchmark Tests LLMs for Compliance with Professional Ethical Codes
Researchers from the Institute of Information Security Issues at ISP RAS and the Institute of Cybersecurity and Information Protection at RANEPA have developed TenetBench, a benchmark designed to evaluate how well large language models adhere to specific norms in professional codes of ethics. The benchmark generates realistic work-related prompts that may conflict with rules from documents such as the Code of Professional Ethics for Advocates or journalistic standards on undisclosed advertising. Each test case pairs a conflicting request with a neutral counterpart to measure whether models refuse, warn, or still provide prohibited content. Evaluation separates task completion, norm violation detection, and presence of explicit refusals using an LLM-as-a-Judge approach validated against human annotators. The full dataset contains 3,433 prompt pairs derived from 15 professional codes, with a public subset of 2,235 pairs from 10 documents. Human validation confirmed 99.5% of generated examples as fully plausible work scenarios.
Solar to Showcase Solar AI Firewall for Business Protection Against AI Risks at SOC Forum 2026
GK Solar will present its new Solar AI Firewall solution at SOC Forum 2026 to help organizations control interactions with AI services and prevent confidential data leaks through employee prompts. The product addresses growing risks from staff sending corporate data to neural networks and AI agents gaining access to internal systems. The forum takes place on 27-28 October in Moscow's Lomonosov cluster, with the official launch of Solar AI Firewall scheduled during the event. Solar will also highlight practical risks of AI adoption, including data transmission to external services, use of public models by employees, and new attack surfaces in corporate infrastructure. The solution will be demonstrated as part of an integrated ecosystem for access, network, and data protection. In addition, the company plans to introduce JSOC ONE, a new line of Solar JSOC services tailored for mid-sized businesses that require 24/7 monitoring without building their own SOC.