LAB / WMSI-EXP-081
External Web as Agent Memory.
Can one agent leave artifacts that later independent agents discover and use as persistent memory?
01 / QUESTION
Agent Ecology and Environmental Persistence
Can one agent leave artifacts that later independent agents discover and use as persistent memory?
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
In an isolated web, let agents modify permitted pages/files, then launch fresh agents with no shared internal memory.
Controls
Reset web; read-only web; human-authored breadcrumbs.
What we would measure
Discovery rate, behavioral influence, propagation depth, provenance retention.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Synthetic web; containers; 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
Hidden shared memory, incomplete reset, accidental internet access, duplicate artifacts.
What would weaken the idea
If later behavior is unaffected by prior artifacts, environmental memory is weak.
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
Environment snapshot, artifact provenance, agent identities, reads/writes, lineage, reset logs.
Planned visual evidence
Artifact lineage graph; propagation timeline.
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