AI Frontier Research & Engineering
Tracking emerging technology, dissecting system architecture, and publishing what I actually build and evaluate.
Article archive — page 3
- AI Agents Should Do More Than Agree: How the XY Problem Derails a Fix
XYEval shows how a plausible but misplaced user suggestion can lower agent success; the practical response is to verify the goal, then explain a better path with evidence.
- What Evidence Should an AI Agent's Vulnerability Report Include? MobileCybench Replays Executable Probes
MobileCybench replays Android agent exploits in an isolated environment, then checks trusted state with executable probes to see which security properties were violated.
- Cross-Account MCP with AWS AgentCore Gateway: Keep Data in Each LOB Account
Trace how AWS’s multi-account AgentCore Gateway pattern separates user JWT authorization through Cedar from downstream M2M OAuth, and identify the sample’s production hardening gaps.
- Self-Modifying Agents Need Inspectable Release Provenance: What Ouroboros v7.4.4 Shows
A focused engineering reading of Ouroboros v7.4.4: how durable identity, memory, self-modification, and managed subagents can be connected to SHA256, SBOMs, GitHub build provenance, and smoke receipts before deployment.
- RSIAgent: Can an Agent Improve Without Updating Model Weights?
A focused engineering reading of RSIAgent's curriculum, actor, verifier, and broad-to-deep exploration loop, with a careful audit of frozen experience, benchmark reporting, and reproducibility limits.
- What Should We Measure When AI Starts Doing AI R&D? Anthropic's Three Dashboards
Anthropic proposes three measurements for AI-led R&D: automation, agent oversight, and safety compute; this article separates its internal self-report from methodology limits and cross-lab comparability.
- GitHub Agentic Workflows: Turning Runnable Agent CI into a Runtime Contract
A focused engineering reading of gh-aw v0.89.17: how log audits, MCP Gateway and firewall boundaries, grading, model-cost signals, and incident monitoring move Agentic CI beyond a demo.
- Pydantic AI v2.45: Durable Agent Reliability Is a Session and Trace Contract
A technical reading of how Pydantic AI v2.45.0 aligns DynamicToolset, MCP sessions, tool history, and usage spans with durable runs, plus the adoption boundaries for TypeSafeModel and Bedrock effort handling.
- Gemini Antigravity Agent 09-2026: An Agent Runtime Protocol Migration
A practical breakdown of Antigravity Agent 09-2026's remote/local compatibility boundary, built-in tool contract changes, adapter design, contract tests, and the migration risk before 05-2026 shuts down on October 5, 2026.
- AWS Bedrock AgentCore and Documentation Drift: Code as Authority, MCP at the Write Boundary
A source-grounded analysis of AWS and Corley’s Eutelsat case: use code as the source of truth, RAG for domain context, and human-reviewed MCP writes for governed documentation publishing.
- Amazon SageMaker HyperPod Inference Gateway: Where GPU-Aware Routing Helps
An engineering analysis of how Amazon SageMaker HyperPod Inference Gateway uses KV cache, queue depth, LoRA, and prefix-cache signals, with the EKS add-on, CRD, failure, benchmark, and vendor-claim boundaries made explicit.
- How Claude Speeds Up Biomolecular Models: FlashPairformer and Reversible Inference Kits
An engineering reading of Anthropic's Claude-assisted optimization of more than 30 biomolecular and genomics models, from FlashPairformer and Big mode to stock/exact/fast contracts, cost curves, and evidence limits.
- TypeSafe AI and Jev: Turning AI into a Calibrated Decision Primitive
An engineering reading of TypeSafe AI's System One model and Jev: typed decisions, probability-aware workflows, evaluation claims, and the limits of replacing text generation with decision primitives.
- Jev in the Agent Runtime: Confidence-Gated Routing, Fan-Out, and Community Experiments
A practical architecture guide to placing Jev between agents, tools, and human review through confidence-gated routing, speculative fan-out, composite scoring, and careful evaluation.
- AWS Bedrock AgentCore Consent Portal: Agent OAuth Is More Than a Connect Button
A close reading of Amazon Bedrock AgentCore Consent Portal’s end-user OAuth flow: separating the corporate IdP, Gateway, GitHub or Slack outbound provider, callbacks, session binding, token vault, and CloudTrail from the security guarantees AWS does not claim.
- Redpanda Agentic Data Plane v0.2.61: Push Credentials, Context, and Write Authority to the Agent Boundary
A close reading of Redpanda Agentic Data Plane v0.2.61 and v0.2.60: credential passthrough, context estimates, activity filtering, Pylon capability gates, and the earlier v0.2.58 audit semantics.
- Gemini 3.8 Flash Coding-Agent Workflow: Routing Uncertainty from Planning to Execution
Using Astra planning and Flash execution as an example, this article adds a SPEC verification gate, escalation rules, and a careful reading of DeepSWE costs.
- Unified Knowledge Graph RAG: GraphRAG and LightRAG Are Query Policies, Not Global Switches
A systems reading of AWS's Unified Knowledge Graph RAG reference stack: how GraphRAG and LightRAG share ingestion, graph, hybrid retrieval, and lineage infrastructure while selecting a query strategy per question.
For speaking invitations, internal engineering sessions, or architecture exchange, see the topics and public work I can bring into the conversation.
Speaking & contact