danielhuber.dev@proton.me Wednesday, April 8, 2026
Agent Engineering
Practical ideas and concepts around agent engineering

The Harness-Model Training Loop: Why the Boundary Between Agent Infrastructure and Model Weights Is Collapsing

Open models reaching agent parity, task-specific harness engineering, and trace-driven fine-tuning are merging what used to be separate concerns into a single iterative loop — with major implications for how teams build and operate agents.

April 4, 2026

What's Happening


Analysis

Sequenced Pipelines: How Structured Handoffs Improve Multi-Agent Systems

How sequenced specialist agents with defined handoff contracts and backward feedback loops produce more reliable results than flat swarms or orchestrator/worker splits.

April 2, 2026

When Evals Become Optimization Targets

Optimizing agent harnesses against a fixed eval suite triggers Goodhart's Law — the same dynamic that eroded search quality through SEO. How adversarial eval co-evolution can help.

March 28, 2026

Strategic Forgetting in Agent Memory Systems

Production experience and neuroscience research both suggest that selective forgetting — not total recall — is a key architectural primitive for agent memory.

March 28, 2026

When the Harness Becomes the Differentiator

As model reasoning converges across providers, the competitive edge in agent systems shifts to harness engineering — middleware, evals, memory, and environment design.

March 28, 2026

Coding Agent Runtimes Go Full-Stack

In a single week, sandboxes, subagents, deployment CLIs, and control planes all shipped across major platforms — tracing the shape of a full managed runtime.

March 21, 2026

The Emerging Coding Agent Runtime Stack

Sandboxes, subagents, and deploy CLIs are converging into a recognizable runtime stack for coding agents. A look at how the layers are forming.

March 19, 2026

From the Archive

The Agent Harness as Execution Environment

Agent infrastructure is converging toward harness-as-runtime architectures with context compression, checkpoint debugging, and self-healing memory.

March 14, 2026

Evaluate-as-Action: Teaching RAG Agents to Judge Their Own Retrieval

How making retrieval quality assessment an explicit agent action—rather than an implicit assumption—improves multi-hop reasoning and enables process-level reward shaping for RAG agents.

March 11, 2026

LDP: Identity-Aware Communication for Multi-Agent LLM Systems

How the LLM Delegate Protocol makes agent identity, trust, and provenance first-class primitives in multi-agent communication.

March 11, 2026