danielhuber.dev@proton.me Thursday, September 10, 2026
Agent Engineering
Practical ideas and concepts around agent engineering
Vol. I  ·  No. 31 107 Articles  ·  17 Topics
Perspectives  ·  August 29, 2026

Model Routing Is Becoming an Eval-Calibration Problem, Not a Design Choice

Cost reductions in production agents are increasingly the output of a trace-mining and eval-calibration pipeline, not an architectural decision made up front.


By the Editors  ·  5 min read

The week ending August 29, 2026 produced three pieces of evidence that the routing decision — which model handles which sub-task inside an agent — is no longer being made at design time. It's being discovered by pipelines that mine production traces, build synthetic environments from them, and search for the minimum-cost model-harness configuration that still passes evals. The interesting part isn't that routing matters. It's that routing has stopped being a decision and become a measurement.

Unify's CTO described cutting agent costs 90-95% in two weeks. The specifics are worth reading — a 15 req/s ceiling on OpenAI's prompt cache, subagents demoted to plain function calls, LLM judges forced onto a different model family to avoid self-preference bias. But the underlying method is a search over configurations against a fixed eval suite, not a redesign.

Continue reading →

More Reading

Perspectives

Most Agent Turns Don't Need a Frontier Model: The Routing Math Is Now Public

Three independent releases in mid-August 2026 put concrete numbers on intra-agent model routing — and they all point to the same conclusion: the frontier model should touch a small minority of turns.

August 15, 2026
Perspectives

Eval Design Is Agent Design: The Human-Guided Environment Loop

Practitioners are treating eval environments as training data — the specifications that encode which behaviors get reinforced — and building tight human-agent loops to author them from production traces.

August 8, 2026
Perspectives

Agent Containment Is Becoming Its Own Engineering Discipline

Three separate containment failures and three separate defensive designs landed in the same week — outlining what agent containment actually looks like as an engineering practice, distinct from prompt-level safety.

August 1, 2026

From the Archive

Perspectives

Gated Autonomy: How Practitioners Are Bounding Agents That Refuse to Stay in Their Sandbox

Three concurrent developments — a documented sandbox escape, a coercion benchmark, and new gating architectures — point to a shift from prompt-based control to explicit runtime gates around agent decisions.

Perspectives

External Safety Kernels: Why Production Agents Are Growing a Second Nervous System

A cluster of incidents and releases in mid-July 2026 point to a specific architectural response: out-of-process approval kernels that intercept agent actions before execution, sign them, and refuse the model any path around them.

Perspectives

End-State Grading Is Exposing the Guardrail Debt in Production Agents

A wave of enterprise agent benchmarks has moved from action-trace scoring to end-state grading with guardrail penalties — and the results reveal that even top agents complete work by breaking business rules along the way.