MQ

Systems Craft

Decision Lab

Small production-minded demos for the choices that shape reliable data and machine learning systems: latency budgets, pipeline failures, and serving architecture tradeoffs, plus statistical modeling workflows where syntax, diagrams, and diagnostics need to agree.

Hot-path accounting1/4
Latency Budget Simulator

Allocate a request budget across feature fetch, scoring, policy checks, and response shaping to see where tail latency quietly steals reliability.

LatencyC++p99Profiling

p95 request path

163ms total against a 180ms budget

17ms spare
Feature fetch58ms

Remote joins dominate p95.

Model score46ms

Batching is underused.

Policy checks35ms

Rules are serialized.

Response24ms

Payload shaping is stable.

Incident reasoning2/4
Pipeline Failure Drill

Walk a production data symptom backward through freshness, schema, feature, and publishing checks until the operational root cause is visible.

Data qualityMonitoringRoot causeSLOs

Symptom

Claims score dropped 18% after a nightly release.

Root cause

A categorical field shipped with a renamed level before the feature contract was updated.

Repair

Block publish on schema-contract mismatch and replay the affected feature window.

Freshnesspass
Volumepass
Schemafail
Feature paritywarn
Publish gateblocked
Architecture choice3/4
Model Serving Tradeoff

Compare batch, streaming, and low-latency serving modes by freshness, cost, auditability, and failure tolerance before picking an implementation.

ServingML systemsTradeoffsReliability

Streaming

Best when decisions need fresh features without request-time joins.

Freshness

Seconds

Cost

Medium

Failure mode

Lag

Audit trail

Medium

Model syntax4/4
lavaan SEM Workbench

Translate lavaan syntax into a path diagram, then inspect how measurement loadings, structural paths, and fit diagnostics support an SEM workflow.

SEMlavaanRFit indices

PoliticalDemocracy SEM

Build `ind60`, `dem60`, and `dem65` from indicators before reading the structural paths.

=~latent measurement
~structural path
~~residual covariance