Articles
Published articles on agent security, model benchmarks and trust in high-stakes decisions, plus the eight systems we built: multi-agent pipeline, x402 payments, security audit framework and market forecasting.
Eight systems we have actually built, split by status: running in production, operationally hardened, or validated in research. Claims below are specific enough to check.
The stack
| System | Status | What it does |
|---|---|---|
| Multi-Agent Research Pipeline | Production | Four agents — Researcher → Analyst → Verifier → Writer. Fail-closed: it refuses to emit a report without live sourced data rather than producing an undeliverable one. 30+ sources per report when it does run. |
| x402 Payment Protocol | Production | Pay-per-call API accepting USDC on Base. No KYC, no signup. 6 paid endpoints live plus a free tier at 5 calls/min. |
| Security Audit Framework | Operational | Automated scanning of agent pipelines for secret management, key exposure and injection surface. 11 vulnerabilities found on internal systems, 3 critical, all remediated. 7.5/10 internal score. |
| Agent Reputation System | Operational | Probabilistic reputation across 13 agent profiles. 500+ tasks completed at a 100% success rate, with reputation-weighted task prioritisation in production. |
| GoA — Graph of Agents | Research | Replication of Yun et al. 2026 (ICLR 2026). Selective agent routing: 3 agents chosen from a pool of 6 outperform all 6. Validated on MMLU, MMLU-Pro, GPQA, MATH, HumanEval and MedMCQA. |
| SPIRAL RL + D-GAT Coordination | Research | Self-play reinforcement learning for multi-agent coordination, with distributed coordination via D-GAT (DG-MAPPO). Proven in simulation, pending production integration. |
| Cognitive Architecture (FEP) | Research | Free Energy Principle implementation: a world model of 5,600 entities, self-model, ICL cycles and UPAL learning. Code complete, not yet in product use. |
| Probabilistic Market Forecasting | Research | Thompson sampling plus probabilistic model averaging for Polymarket paper trading. 157 snapshots and 64 trade entries analysed, with P(profit) per position. Paper trading only. |
Articles
Published analysis of agent security, model benchmarks and trust in high-stakes decisions.
Our x402 extension was missing the one field the facilitator drops services for
We read the canonical spec instead of assuming our shape was fine. Six of our paid endpoints would have been discarded on contact.
Read → BenchmarkGLM 5.2 Security Benchmark
72% of AI agents fail basic secret management checks. Analysis across 200+ production agents.
Read → SecurityWhy AI agents need security audits
A Codex sensitive-file exclusion issue, and GLM beating Claude on security benchmarks.
Read → TrustAI agents now read MRI scans
A Claude Code analysis hit #6 on Hacker News. What it means for high-stakes decisions.
Read →