Foundry Evaluation¶
Status¶
Planned
No Foundry integration exists. No experiment has been run. This page describes
the experiment that evals/systems/foundry.py is shaped for, and what needs
to happen before it can execute.
The question¶
Foundry has a Memory Engine that retrieves candidate memories for an agent. Venkai is a context-selection layer that scores, filters, deduplicates and budget-constrains candidates from any retrieval engine.
The question: does Venkai's selection improve the quality/cost tradeoff of Foundry's retrieval?
That question is answerable only by measurement. No claim about Venkai improving Foundry's output has been measured.
The experiment¶
Two arms, one variable:
flowchart LR
A["Foundry Memory Engine"] --> B["candidate memories"]
B --> C["baseline greedy packer"] --> E["LLM"]
B --> D["Venkai selection"] --> F["LLM"]
Arm A (baseline): Foundry retrieves candidates, the harness's shared greedy packer packs them under a token budget. This is what an agent using Foundry today would get if it simply packed the top-k results.
Arm B (Venkai): Foundry retrieves the same candidates, Venkai applies its scoring pipeline (relevance 40% + recency 20% + importance 25% + frequency 15%), filters by a relevance floor, deduplicates, and packs under the same budget.
Variables held constant¶
- Dataset and memory corpus
- Query set
- LLM model and prompt template
- Temperature
- Context token budget
Variable (the only one)¶
Selection layer: baseline greedy packer vs. Venkai selection pipeline.
If the embedding model cannot be held constant (because Foundry uses its own), that is a second uncontrolled variable and the comparison is downgraded from "selection layer" to "end-to-end stack". This must be declared in the report.
Metrics¶
| Metric | What it measures | Direction |
|---|---|---|
| Context recall | fraction of relevant memories in the selected context | higher is better |
| Context precision | fraction of selected memories that are relevant | higher is better |
| Redundancy ratio | duplicate information in the selected context | lower is better |
| Irrelevance ratio | irrelevant information in the selected context | lower is better |
| Selected tokens | total tokens shipped to the LLM | lower is better (at same quality) |
| Latency | end-to-end time, query to selected context | lower is better |
| Task success | whether the LLM can answer from the context | higher is better |
What needs to happen before this can run¶
- Written permission to benchmark under the terms of access.
- Documented retrieval interface — how a corpus is loaded, how a query is issued, what comes back, what the ranking parameters are.
- Embedding model alignment — a way to hold the embedding model constant, or an explicit declaration that it is a second uncontrolled variable.
- Cost and rate-limit figures so the benchmark run does not silently truncate.
These four prerequisites are listed in evals/systems/foundry.py. Until all
four exist, the adapter raises SystemUnavailable and the rest of the harness
runs without it.
What data is needed¶
- Access to Foundry's retrieval API — direct API access or a batch export of candidate memories for a test corpus.
- A test corpus — memories and queries with known correct answers. The
reference dataset (
reference_v1, 41 synthetic cases) is the fastest path; a real workload is the more informative one. - Permission to benchmark — written, not verbal.
Minimum evaluation time¶
2–3 days: day 1 for integration alignment, day 2 for dry run and control verification, day 3 for full benchmark and report. Assumes the interface is stable and documented.
What the result will and will not tell us¶
A Venkai win on context recall with comparable or fewer tokens would mean the selection pipeline adds value on top of Foundry's retrieval. A loss, or a win bought with significantly more tokens, would mean it does not.
Either way, the result is specific to this dataset, this budget, and these queries. Generalising from a single run is not supported by the data.
Related¶
- Evaluation — the full harness, its metrics, its limitations
- Context selection — what Venkai's selection does
- Ranking — the scoring blend being measured