Cost, Latency, and Throughput Engineering for Agents
Why agent performance engineering lives in the harness, with a real repo update that adds per-step timing and workload estimates to trace summaries and run summaries.
The blog
Blog
Long-form, evidence-backed writing on agentic AI — newest first.
Security, Auth, and Policy in Agent Harnesses
A practical look at what security actually means in an agent harness after adding a checked-in policy config, provider env handling, and verification surfaces to the live demo repo.
Multi-Agent Systems Without the Theater
A practical look at small multi-agent systems after adding explicit planner→executor→reviewer handoffs to the live harness-engineering demo.
Sandboxing, Isolation, and Safe Execution
A practical look at harness-level sandboxing and isolation after adding explicit action categories, policy checks, and write-path enforcement to the live harness-engineering demo.
Tracing, Observability, and Evals for Agent Systems
A practical look at tracing, operator-facing observability, and trace-aware evals in the live harness-engineering demo after adding persisted trace summaries and lightweight eval fixtures.
Human-in-the-Loop Done Properly
A practical look at human-in-the-loop design in the live harness-engineering demo: approval as explicit workflow state, not a chat courtesy, plus a new pending-action inspection surface for operators.
LLM and VLM for Radiotherapy Contouring: State of the Art, Gaps, and Opportunities
A comprehensive review of multimodal LLM and VLM approaches for target contouring in radiation oncology, covering the current state of the art, open challenges, and future opportunities.
Memory Architecture for Agents: Context, Sessions, and State
A practical look at memory architecture in the live harness-engineering demo: separating working context, durable session state, and retrieval memory instead of calling everything memory.
Vector Databases Explained: History, Internals, and Why Agentic AI Depends on Them
A deep technical guide to vector databases: what they are, how they evolved, how they work internally, and how to use them with embeddings, RAG, and agents.
Durable Execution Is the Difference Between a Demo and a System
Checkpointing, approval-safe pause/resume, and replay-friendly run history are what turn an agent demo into an operational system. A practical look at the live harness-engineering repo after adding persisted run …
