THE ENGINEERING JOURNAL

Ideas, tested
against the work.

Notes on building useful AI systems, evaluating tradeoffs and thinking across the stack.

METABOLIQ ENGINEERING

Explore the technical publication.

Architecture decisions, experiments and lessons from building AI systems.

LATEST / ENGINEERING

17 NOVEMBER 2026 / 7 MIN READ

Coverage complete.
Evidence still needs review.

29 untouched classifications tested. Recovered failures, preserved original results and modest AI-rated evidence differences with criteria caveats.

Read the completeness continuation
17 NOVEMBER 2026 / 7 MIN READ

Evidence completeness.
Evaluation interrupted.

Five completed pairs, no observed gain. One HTTP 429, 29 unattempted classifications and the limits of blinded AI evidence review.

Read the evidence-completeness evaluation
17 NOVEMBER 2026 / 9 MIN READ

Sensitive context.
Original failures preserved.

A stopped evaluation and twelve-case continuation. The combined result, medical review miss, original failures and AI-review limits.

Read the sensitive-context evaluation
17 NOVEMBER 2026 / 9 MIN READ

Recovered response.
Unchanged correctness.

One HTTP 503 retry restored a valid but wrong route. All 40 cases, both review misses and the limits of AI review.

Read the reliability evaluation
17 NOVEMBER 2026 / 9 MIN READ

Negated closure.
No observed gain.

Identical routing on 35 common-valid cases, five failed calls and an unmeasured correction. The complete comparison and AI-review limits.

Read the negated-closure evaluation
16 NOVEMBER 2026 / 9 MIN READ

Vague requests.
Clearer review.

Three observed routing corrections, two failed calls and a shared unnecessary review. The findings and limits of a fresh AI-reviewed comparison.

Read the vague-request evaluation
16 NOVEMBER 2026 / 9 MIN READ

Bounded evidence.
No observed gain.

Zero contract rejections in both modes, seven failed calls and the same review miss. What exact extraction does—and does not—establish.

Read the evidence evaluation
16 NOVEMBER 2026 / 9 MIN READ

Clearer routing.
Visible failures.

Five observed routing corrections, eight failed calls and what separate AI label review can—and cannot—establish.

Read the paired evaluation
16 NOVEMBER 2026 / 7 MIN READ

Valid output.
Missed review.

All 40 outputs passed validation. Three mapped review cases were missed. Diagnostics, independent inputs and the limits of the labels.

Read the findings
16 NOVEMBER 2026 / 7 MIN READ

Gemini improved triage.
The failures still matter.

38 of 40 exact decisions, one rejected output and the routing coverage lost when rules constrain the model.

Read the comparison
16 NOVEMBER 2026 / 7 MIN READ

What 30 triage
cases revealed.

25 exact matches, five documented failures and the review misses hidden by an accuracy headline.

Read the evaluation
16 NOVEMBER 2026 / 6 MIN READ

From AI demo to production:
start with the workflow.

A practical framework for defining scope, testing quality, integrating tools and owning the system after launch.

Read the article
ENGINEERING LAB / INTERACTIVE

Inspect the triage workflow.

Try synthetic requests and see route proposals, review decisions and their reasons. Rules baseline; no live model or business actions.

RESEARCH METHOD / PROPOSED

How we would evaluate inference efficiency.

Quality, latency, throughput, memory and cost, recorded together.

START WITH A REAL PROBLEM

What should AI
make possible for you?

Bring the workflow. We’ll help define the next step.

Request a workflow assessment

WORKFLOW DESIGN NOTE

What happens after an inquiry?

A synthetic lead-to-revenue walkthrough, with approval paths, failure handling requirements and a scorecard for the first pilot.

Explore the walkthrough and evaluation plan ↗