LAB / WMSI-EXP-054
Human + AI Research Cell.
Which human/agent division of labor best balances speed, rigor, and judgment?
01 / QUESTION
Research Workflow and Meta-Experiments
Which human/agent division of labor best balances speed, rigor, and judgment?
This is a protocol scaffold, not a completed experiment or a frozen execution plan. No measured effect or research conclusion is claimed here.
Hypothesis to test
The manipulation described below produces a reproducible, condition-specific change in the measured system behavior or internal state that is not explained by the ordinary controls.
Ordinary competing explanation
The observed pattern is explained by ordinary sampling variation, prompt/representation artifacts, surface lexical cues, evaluator bias, or the known product/runtime mechanics captured by the controls.
02 / PLANNED DESIGN
How we intend to test it
Compare human-led, AI-led, parallel, and adversarial-review cells on matched investigations.
Controls
Same source corpus and time budget.
What we would measure
Accuracy, completeness, novelty, calibration, labor/time, provenance quality.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Work/agent stack; provenance logger.
Before a full run
Feasibility=NOW; priority=P0. Before confirmatory execution, run a small pilot to estimate variance/cost, freeze the scoring rules, and assign a run-count target.
Model revisions, final prompts, sample sizes, cost limits, and scoring rules must be settled through the pilot and protocol-freeze process.
03 / INTERPRETATION
What could fool us
Source drift, unequal time budgets, evaluator knowing condition.
What would weaken the idea
If one structure does not generalize across task types, claims should remain task-specific.
Observation, inference, speculation, unknowns, and apparatus errors will be labeled separately. One striking transcript cannot establish a general effect.
04 / RECORD
Evidence we plan to preserve
Source corpus snapshot, task ledger, provenance, human interventions, model/tool logs, final reports.
Planned visual evidence
Workflow DAG; quality/cost frontier.
No research runs or raw datasets are published for this experiment. The September 26, 2026 registry and protocol compendium (version 1.0) are the sources for this planning record.
Back to all 90 experiments