Wiki
Core10 min read

Routing and decision layers

A fast, typed decision model can gate and route work before any expensive reasoning happens — the System One / System Two split as infrastructure.

Not every request needs a reasoning model. Most are easy, high-volume, and decidable by a glance: which team owns this ticket, is this message a refund request, should this go to a human. A decision layer — a fast, typed classifier — can absorb those before the expensive agent ever wakes up, and escalate only the genuinely uncertain remainder.

Start here

Routing is the cheapest agentic win there is. A gate that answers the easy 80% in milliseconds leaves the reasoning model for the hard 20% — lower cost, lower latency, and a smaller, cleaner context for the part that actually needs thought.

Route cheaply, escalate only what is uncertain

charged twice, want a refund
billing · 0.96decision model
app crashes when I log in
technical · 0.91decision model
can't reset my password
account · 0.88decision model
invoice shows the wrong address
billing · 0.79escalate to LLM
error 500 after the update
technical · 0.72escalate to LLM
delete my account, please
account · 0.95decision model
double charge again
billing · 0.84decision model
something is off, not sure what
? · 0.41escalate to LLM

auto-handled

5/8

escalated

3

est. cost / batch

$0.0305

avg latency

0.97s

This is the System One / System Two split from the LLM domain, applied as infrastructure: a fast, typed decision layer absorbs the high-volume easy cases and hands the genuinely hard ones to a reasoning model. Lower the threshold and you escalate more — safer, slower, dearer. Figures are illustrative.

Slide the confidence threshold and watch the cost and latency move as more or fewer cases get escalated.

The pattern

  • Classify — a fast model returns a typed decision with a probability: route, intent, or a yes/no gate.
  • Gate on confidence — above the threshold, act on the decision; below it, escalate to the reasoning agent or a human.
  • Act — the route decides which tools, prompts, or agents handle the request downstream.

Why a decision model

This is the System One / System Two split from the LLM domain, used as plumbing. A decision model returns typed values and calibrated probabilities instead of text — no chain of thought, no parsing, no fabricated prose — which makes it fast, cheap, and a natural fit for high-frequency classification. The reasoning model still handles anything open-ended.

Careful

The threshold is a product decision, not a technical default. Set it too low and the fast layer guesses on cases it should have escalated (confident mistakes); too high and you have rebuilt the expensive path with extra steps. Calibration matters: a 0.94 should be right about 94% of the time, and you should measure that rather than trust the vendor's number.

Check yourself

Eduspheria wiki · Agentic AI, Multi-agent & orchestration

0 / 4 answered

  1. 1What does a decision layer return instead of prose?
    Multiple choice
  2. 2Setting the escalation threshold is a technical default, not a product decision.
    True / false
  3. 3What should you measure rather than trust, when a vendor claims a 0.94 score is right 94% of the time?
    Short answer
  4. 4What happens if the confidence threshold is set too low?
    Multiple choice

Next: what happens when agents hand work to each other directly.