AI Frontier Research & Engineering
Tracking emerging technology, dissecting system architecture, and publishing what I actually build and evaluate.
Article archive — page 4
- AWS Step Functions × Bedrock AgentCore: Validate Agent Proposals Before Critical State Changes
A practical control boundary for multi-agent workflows: separate AgentCore proposals from deterministic validation, human approval, idempotent execution, and durable audit history in Step Functions.
- GitSpawn: When Repository Git Config Runs Before a Coding Agent's Trust Boundary
A technical analysis of how repository-local core.fsmonitor can trigger background commands before coding-agent workspace trust and approvals, with the archive delivery condition, patch matrix, safe lab boundary, and enterprise controls.
- Forge v0.18.1: Open-Source Multi-User MCP Auth and Agent Governance
A runtime-contract analysis of how Forge v0.18.1 connects multi-user MCP identity, OAuth consent, tenancy, policy, egress, and per-invocation audit—and where independent evidence is still missing.
- AG2 v1.0.3: MCP 2.0 Migration with Deterministic Agent Governance
A technical review of AG2 v1.0.3's MCP 2.0 breaking migration, TealTiger's deterministic governance path, and a testable rollout boundary for agent runtimes.
- Model Hardware Standard: an MCP-shaped interface for physical devices
An evidence-led look at Anthropic's Model Hardware Standard research preview: standardized drivers, discovery, and device control for agents, while identity, authorization, approvals, and physical safety remain platform responsibilities.
- Automated Alignment Researchers: Why Agentic Post-Training Needs Integrity Gates
Anthropic's automated alignment researcher experiment shows how agents can search and iterate on post-training methods while benchmarks, capability floors, data isolation, and integrity review remain outside the agent's authority.
- WeKnora Architecture: From Document Ingestion to a Governed Agent Knowledge Platform
A systems reading of Tencent WeKnora: its three-process core, ingestion and retrieval flows, and how Agents, MCP, sandboxed Skills, memory, and governance share one control plane.
- What LLM Inference Costs: DeepSeek-R1 Benchmarks and GPU Rental Prices
Read public DeepSeek-R1 MLPerf logs for 8 B200 and B300 GPUs, then apply sourced GPU rental quotes while separating measured latency, arithmetic cost scenarios, and API prices.
- How to Read AI Agent Papers: From CoT and WebGPT to ReAct
One diagram shows how CoT and WebGPT merge into ReAct, then connects Gorilla and IPI to the rest of the agent-systems reading path.
- How to Read RAG Papers: From Dense Retrieval (DPR) to Lewis RAG
One diagram shows how DPR and Lewis RAG connect to the retrieval papers already on this site.
- Agentic AI Platform Contract: The Control Plane You Must Wire Before Production
A copyable Agentic platform contract: what the platform provides, what projects must wire (E·P·J·T), seven non-bypass rules, and where the IT 100-question evidence stops.
- AIPOCH Open Science: Turning Scientific Agents into a Governable Workbench
Break down AIPOCH Open Science v0.19.0: skills, notebook dependencies, OAuth, and artifact provenance. The version number lives in the body; the search entry point is the product name and scientific agents.
- AI Software Development Environments: Choosing Between Vibe Coding and Verified Agent Workflows
InfoWorld surveys GitHub Copilot, Google Antigravity, JetBrains Air, Kiro, Zed, and Zenflow; this article turns that tour into a selection framework based on autonomy, context, isolation, and verification.
- GitHub Copilot MCP Governance: From Allowlist Semantics to Agent Adoption Telemetry
GitHub has added enterprise MCP allow and deny lists alongside third-party agent activity in usage metrics; this article explains the policy semantics, telemetry boundary, and a practical rollout loop.
- Claude Managed Agents Become a Governed Runtime: Budgets, Delegation, Locality, and Inference Hooks
Anthropic's Managed Agents now expose session budgets, advisors, inference geography, repository skills, and inference hooks as runtime controls; this article maps their value and remaining boundaries.
- TREC RAG 2026: Why RAG Evaluation Is Adding Agents
Use TREC RAG 2026 to explain how RAG evaluation moved from document QA to agent-in-the-loop. This article covers direction and task design, not enterprise harness implementation.
- How to Build an Enterprise RAG Evaluation Harness (TREC RAG 2026)
Using TREC RAG 2026 and RAGDoll as references, design a replayable enterprise RAG evaluation harness: data model, citations, agent traces, judge calibration, and launch gates.
- Cloudflare's Open Agentic Internet Blueprint: Readable, Discoverable, Callable, and Payable Web
An architectural deep dive into Cloudflare's proposed Agentic Internet framework, spanning Web Bot Auth, Markdown for Agents, WebMCP browser tool exposure, and x402 micro-payments.
For speaking invitations, internal engineering sessions, or architecture exchange, see the topics and public work I can bring into the conversation.
Speaking & contact