Physical AI agents need more than perception and fast telemetry. They need memory of what was tried, what happened afterward, and whether the same action should be repeated, suppressed, or escalated in the next similar context.
ZeptoDB is building that as Action-Outcome Memory: a time-series memory plane for robot operations, edge safety decisions, fleet audit, and policy improvement.
Every action becomes evidence. Every outcome becomes memory. Every future decision can be checked against what actually happened before.
Robots, drones, mobile fleets, cold-chain systems, and industrial agents increasingly make operational decisions in real environments. A generic log can show that an action happened. It usually cannot answer the higher-value question:
Should this action be repeated in this context?
That requires keeping the full sequence intact:
This is a time-series problem as much as an AI problem. The value is not just text memory or vector recall. The value is replaying action evidence with SQL, ASOF JOINs, windows, suppression audits, and bounded edge-to-fleet transfer.
The first comparison tested whether context changes which previous outcome is safe to reuse. The next step replayed the same decision trail through native ZeptoDB SQL. Both summaries below are rendered from the shared experiment record used by the evidence hub.
Can a robot reuse a prior recovery without repeating an action that only worked under a different physical context?
The result moved the problem from incident search to evidence-backed action reuse.
Boundary:Five synthetic Physical AI incident families; not a production safety guarantee.
Can the fixture be replayed through live ZeptoDB tables, joins, windows, and spatial checks?
Robot state, sensor evidence, recommendations, suppressions, and outcomes became one inspectable SQL path.
Boundary:Research tables and replay harness; no new promoted product surface.
Follow the complete experiment timeline →
edge event -> robot state / sensor summary -> historical action outcomes -> context gate -> allow, suppress, or manual review -> decision ledger -> edge outbox -> bounded fleet feed -> fleet audit and policy learningZeptoDB’s current path separates immediate edge behavior from fleet-wide learning:
Temporal evidence
Store robot incidents, state, sensor summaries, actions, retrieval evidence, suppressions, outcomes, and ACK rows as queryable time-series tables.
SQL replay
Use ASOF JOIN, action/outcome JOIN, suppression audit JOIN, ROW_NUMBER, LAG, and spatial predicates to replay why an action was allowed or suppressed.
Bounded edge-to-fleet feed
Transfer decision, retrieval, and suppression evidence through bounded batches with duplicate, late, outage, and restart handling.
Shadow supervisor
Test recommendations in shadow mode, suppress hazardous proposals, preserve manual-review decisions, and avoid duplicate work after restart.
This is an active product track, not a loose idea. It is also not a broad GA control feature today.
| Area | Current status |
|---|---|
| Offline Physical AI comparison | Research complete |
| Native ZeptoDB SQL replay | Research complete |
| Edge/fleet bounded feed semantics | Research complete |
| C++ connector and SQL/HTTP runtime path | Experimental runtime path |
| Action-Outcome shadow supervisor | Experimental runtime path |
| Edge/fleet SQL/HTTP adapter | Controlled pilot scope |
| Default-on operator feature / GA autonomous control | Not promoted |
The current supported language is: controlled pilot / controlled shadow pilot, with explicit non-goals, monitoring, rollback, and promotion gates.
Warehouse robots
Avoid repeating risky route decisions after slip, occlusion, geofence, or localization incidents.
Robot arms
Suppress repeated torque-limit increases when similar recoveries required pause, recalibration, or speed reduction.
Drones and mobile robots
Compare continue-mission, return-to-base, clean-sensor, and navigation-mode actions against previous outcomes.
Cold-chain and logistics
Preserve action, environmental context, and recovery outcome for fleet-level audit after edge decisions.