Skip to main content

Filed under

AI Agents

5 entries

  1. AI Agents 7 min read

    You Can’t Prove the Agent. Prove the Gate.

    Formal verification for AI-agent security. You can’t prove a probabilistic model does the right thing — but the deterministic gate in front of it is small enough to prove outright. Dafny proofs, a Rego twin, and differential testing, following the method AWS used for Cedar.

  2. Compliance 7 min read

    The Firewall Stays Put. The Agent Improvises.

    Rewriting security controls for probabilistic agents. Static control catalogs assume systems that do what they’re told; AI agents don’t — so here’s how to express agent guardrails (tool allowlists, secret-egress denial, audit) as machine-checkable OSCAL component definitions.

  3. AI Agents 12 min read

    Building Nexus-Agents: What I Learned Creating a Multi-Model AI Orchestration System

    The engineering story behind nexus-agents, a research-backed multi-model orchestration system that coordinates Claude, Gemini, and Codex through consensus voting, adaptive routing, and graph workflows.

  4. AI Agents 8 min read

    Consensus Voting With AI Models: When Three Opinions Beat One

    How multi-model consensus voting catches blind spots that single models miss. The research behind adversarial roles, Bayesian aggregation, and structured deliberation across Claude, Gemini, and Codex.

  5. Research 8 min read

    From RouteLLM to Contextual Bandits: How Research Papers Shaped My Model Router

    How I went from naive round-robin model selection to a five-stage routing pipeline backed by RouteLLM, TOPSIS, and LinUCB research. The failures that led to each improvement.