Self-Learning Routing: How RoutePlex Gets Smarter Over Time

When you first use RoutePlex, the router has nothing specific to your workload to go on. It selects models based on general performance signals that apply equally to everyone.

That's fine for getting started. But over time, your workload has patterns. Maybe Claude consistently produces better analysis for your use case. Maybe GPT-4o Mini is fast enough for your summarization tasks and costs a third of the price. The best router for you isn't the same as the best router for everyone.

Self-Learning Routing is how we solve this.

What Gets Tracked

After each successful request, RoutePlex records a lightweight metadata entry:

• The model used and the detected query type
• Response quality signals — length, structure, and token ratios
• Latency and cost
• A one-way hash of your message (for pattern detection)

Nothing else. Your prompts, your responses, and your data are never stored. Quality is inferred from response structure — not content. The hash is irreversible by design.

How the Learning Works

As your profile accumulates data, the router favors models that have consistently worked well for similar requests on your account. A model that reliably produces high-quality analysis for your workload gets priority on analysis requests. A model with mediocre performance gets deprioritized.

The influence is bounded and incremental — designed to tilt selection without overriding the base scoring. The system learns carefully, not aggressively.

Confidence Gating

Learning only influences routing once there's enough data to trust it:

• Cold start — When a model hasn't been used enough on your account, routing falls back to global patterns.
• Warm-up — As usage accumulates, your personalized signal gradually takes over from the global defaults.
• Established — Once a model has been used enough to build confidence, personalization carries the most weight.

Until your account reaches confidence, RoutePlex falls back to global patterns — aggregated signals from across the platform, anonymized and weighted by similarity to your query type.

Explicit Feedback

You can accelerate learning by rating individual responses. User ratings are blended with automatic quality signals and immediately update the routing preference for that query type.

From the dashboard or via the API:

curl -X POST https://api.routeplex.com/api/v1/insights/feedback \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -d '{"request_id": "req_abc123", "score": 5, "is_helpful": true}'

What You Can See

The Insights tab shows the full picture:

• Which models are performing best for each query type
• Whether prompt enhancement is improving quality for your workload
• Cost optimization opportunities (e.g. if you're using a premium model for simple queries)
• Personalized recommendations with confidence scores

Your Data, Your Control

All learning data belongs to you. Delete it at any time from the dashboard settings or via:

DELETE /api/v1/insights/data

Routing immediately reverts to global defaults. No questions asked.

The Result

After enough usage, RoutePlex's routing decisions are tailored to your specific workload. The models that work best for your use case get priority. The ones that underperform get deprioritized. Automatically, in the background, without any configuration.

This is intelligent routing that improves as you use it.

View your Insights →