Dual-Engine Schema Pruning & Tool Selection

Calibrated tool selection for AI agents.

Prune 100 tool schemas to top candidates in 0.4ms offline, or direct-dispatch with calibrated confidence.

0.4ms offline TurboQuant -92% prompt tokens 100% BFCL Top-1 (TypeSafe) Zero external dependencies
Live Interactive Engine

Playground

Test real TurboQuant vector search in your browser. Type an intent or choose an example query below.

Try:
Candidate Mode:
Direct Dispatch Threshold: 85%
Engine: TurboQuant (Offline WASM/FWHT)

Pruned Candidates (Auto)

Adaptive score drop-off

Real-Time Pruning Impact

Search Latency
0.24 ms
Offline vector search
Prompt Reduction
-91.2% tokens
Compared to 30 schemas
Unpruned Catalog ~4,680 tokens
tool-prune Candidate Set ~450 tokens

// Loading snippet...
            
Financial & Latency ROI

How much does schema pruning save?

Agents that pass entire MCP catalogs into each prompt burn thousands of redundant tokens every turn. Adjust the sliders below to calculate your savings.

5,000
500 25,000 50,000
40 tools
10 tools 60 tools 120 tools
Note: Assumes average tool schema specification is 160 tokens and pruning selects Top-3 candidates.

Estimated Monthly Savings

Monthly Tokens Saved
888M

Prompt tokens avoided

Monthly Cost Saved
$2,664

Direct LLM invoice savings

Total Agent Hours Saved
29h
Prompt token processing latency cut by 88%

Beyond token cost, schema pruning eliminates LLM context confusion: the Gorilla BFCL benchmark proves top-1 selection accuracy increases from 86.1% to 100% when noise distractors are pruned out.

Empirical Evaluation

Berkeley Function Calling Benchmark (BFCL v3)

Evaluated on the Gorilla BFCL v3 multiple-tool dataset across 100 tool schemas and subtle distractor intents.

Engine Backend Distractor Top-1 100-Tool Top-5 Prune Search Latency Network
TypeSafe (Jev) Cloud System One 100.0% 100.0% 258 ms Cloud API
TurboQuant (WASM) JS WASM (turboquant-search) 86.7% 85.0% 14 ms Offline
TurboQuant (Python) Rust SIMD (turbovec) 85.0% 82.5% 0.023 ms Offline
TurboQuant (Pure JS) Pure JS / Python Fallback 83.3% 82.5% 0.4 ms Offline
Dual-Engine Design

Architecture & Workflow

Three simple stages to eliminate agent prompt bloat and achieve deterministic sub-millisecond execution.

1

FWHT Vector Projection

Tool criteria and query tokens are hashed and rotated using a diagonal Rademacher matrix and the Fast Walsh-Hadamard Transform in O(d log d), eliminating data-dependent training overhead.

Zero network • Pure local math
2

PolarQuant & QJL Residual

Vectors are quantized to 2-bit discrete intervals, while residual error vectors are captured with 1-bit Johnson-Lindenstrauss random signs. Preserves high cosine fidelity with tiny memory footprints.

Calibrated [0, 1] probability range
3

Fast-Path Direct Dispatch

When confidence clears your threshold, dispatch deterministic tool handlers directly in under 160ms. If ambiguous, forward only top-5 candidates to the LLM prompt.

Save 92% tokens and LLM cost