Task probability distribution
Veritiana Prompt Classifier
What do you actually use AI for?
Paste any prompt and see what type of work it represents, how complex it is and how confident the model is — directly in your browser.
Private
Runs locally in your browser
Instant
No external classification API
No sign-up
Try it immediately
Live browser test
Nothing is uploaded for classification.
Loading model
View detailed analysis
Processing profile
—
—
Versioned API-equivalent comparison
Estimated prompt input plus configurable output allowance
Comparison assumptions are versioned and illustrative. They are not provider billing, a recommendation of a specific model, or proof of the cheapest valid route.
Your prompt
0 characters · 0 estimated input tokens
Processed locally
Or load a prepared example
Trained from scratch
A dedicated neural network, not an extension of another LLM.
Result
Task, complexity and confidence
Task type
—
—
—
Complexity
—
—
—
Local inference
Your prompt stays on this device.
Powering AI Meter
The Chrome extension that adds work context to everyday AI usage.
What this proves
A visible result, with its uncertainty left intact.
The test exposes task probabilities, complexity confidence and cost assumptions separately. Classification is measured locally; routing remains a future decision layer.
1,544 local features
Word and bigram hashes, character trigrams and eight structural signals.
Two predictions
Nine task probabilities and three independent complexity probabilities.
No hidden certainty
Low-confidence results remain visibly uncertain instead of becoming definitive labels.
Browser-native
The ONNX model and feature extraction run on the client through WebAssembly.
Open model release
Inspect the model, training process and evaluation.
The complete ONNX release includes the model card, reproducible training scripts, configuration, dataset manifest, evaluation results, license and browser integration examples.
Open versus commercial
The classifier identifies. The commercial layer decides.
This page intentionally stops before production routing. It demonstrates recognition and comparison, while preserving the monetization boundary around execution policy and optimization.
Open layer
Recognition
- Task and complexity probabilities
- Confidence and uncertainty
- Local browser inference
- Token and cost comparison preview
- Open ONNX release
Commercial layer
Execution decisions
- Provider and model selection
- Context and tool policies
- Budgets, fallback and safeguards
- Organization-specific rules
- Measured quality and routing improvement
Future routing architecture
Classification is the first signal, not the final decision.
A future Veritiana routing layer can combine task, complexity and confidence with model capability, provider pricing, context requirements, policy and observed execution quality.
01User prompt
02Local classifier
03Routing policy
04Model + tools
05Execution
06AI Meter evidence
Limits
What this test deliberately does not claim.
No real-world accuracy claim
Internal weak-label evaluation is not an independent production benchmark.
No automatic best-model claim
The processing profile is illustrative and does not select or execute a provider route.
No billing replacement
Cost values are versioned API-equivalent assumptions, not provider invoices.