The core problem

A long-running AI system accumulates an operational archive. When the system needs to answer a question about past events, one approach is to replay the full archive as model context. This is reliable but the cost grows linearly with archive depth.

At 1,000,000 records, a full replay at 50 tokens per record requires 50 million tokens of context per query. At 2,000,000 records, 100 million. Context windows do not scale this way. At production telemetry rates, full replay is not a viable architecture.

Token cost comparison

Bounded retrieval

Fixed

Query cost is determined by the token budget, not archive depth. The retrieval set size is bounded and configurable. Over 2M records, the cost per probe is the same as at 1,000 records.

Cost does not grow with archive size.

Full context replay

O(N)

Query cost grows linearly with the number of archived records. At 1M records with 50 tokens/record, each probe requires 50M context tokens. Most LLM providers cap context windows well below this.

Not viable at production telemetry scale.

Telemetry terminal benchmark

OpenSky ADS-B live data · 2026-06-21

Run on real-time ADS-B aviation telemetry. 2,365 events ingested, 239 aircraft tracked. Probe: factual recall of specific aircraft state at a past timestamp.

106
Bounded retrieval tokens
Measured
49,894
Estimated full replay tokens
Estimated · event count × avg token/event
471x
Reduction
106 vs 49,894 · estimated baseline
100%
Probe recall
Measured

Label note: The 106-token bounded figure is measured. The 49,894-token full-replay figure is estimated from event count and average token size. The 471x ratio reflects this estimated comparison baseline.

nuPlan AV benchmark

1M and 2M record runs

At 2,000,000 archived telemetry records, a full-replay approach at an average of 100 tokens per record would require 200 million context tokens per probe. No commercial LLM context window supports this. Bounded retrieval on the same archive used approximately 400 tokens per probe (measured, Ref 002 configuration).

~400
Bounded tokens per probe
Measured · Ref 002 · 500Q config
>200M
Full replay tokens at 2M records
Estimated · not viable
100%
Recall at 400 tokens/probe
Measured · 500 probes
0
Integrity failures
Measured

Why this matters

The efficiency claim is not the primary claim. The primary claim is 100% verified recall within benchmark scope, at bounded evidence-packet cost. The efficiency data demonstrates that the bound is practical: 400 tokens per probe is a cost that fits within any LLM context window, enabling real-time querying of arbitrarily large archives.

A system that achieves 100% verified recall but requires 200M tokens per probe is not deployable. A system that achieves 100% verified recall at 400 tokens per probe is.