Machine-native routing for AI agents

One task in. An eligible provider out.

ATL routes supported search, extract, summarize, translate, and classify tasks to eligible providers, executes the selected route when ATL owns execution, applies bounded fallback when appropriate, and learns from durable outcomes.

Try a routeSee measured production resultsConnect in 30 seconds
1. Describe the taskNo provider identity required.
2. ATL checks eligibilityHealth, freshness, policy, budget and Gate.
3. Get primary + fallbackBounded failover route when available.
4. Report the outcomeFeed real latency, cost and success back.
Measured on the public production path · 2026-09-25

Less routing overhead. Smaller machine responses. Fail-closed behavior preserved.

After the first Decision hot-path performance pass, ATL was benchmarked from an external GitHub-hosted runner against the public production endpoint. These are measured results from that test set, not theoretical projections.

~1 msInternal Decision latency observed in the production comparison request.
1.75 sMedian external round trip from the GitHub runner to the public ATL endpoint and back.
91.3%Smaller serialized Decision response body with compact mode: 9,033 B → 783 B.
16 / 1612 supported routes returned the expected primary + fallback; 4 unsupported capabilities returned NO_MATCH.

Scope matters: the 91.3% figure is response-body reduction for this benchmark, not a claim about model tokens or total application bandwidth. The 16/16 figure describes this test set, not universal accuracy. Read the benchmark methodology and caveats.

Live Route Demo

Send a real Decision request to ATL's production entrance. ATL's safe V1 surface supports search, extract, summarize, translate, and classify; the demo uses summarize as a compact routing example.

Task
Ready.
Decision
Run a route to see the selected provider, alternatives and decision reference.

Connect where you already build

MCP

https://mcp.agenttrafficlab.com/mcp

Start with atl_decide, then follow its machine-readable next_step to atl_execute for ATL-owned execution.

Python

from agenttrafficlab import decide\n\nroute = decide("summarize this ticket")

Zero runtime dependencies.

JavaScript

import { decide } from "@agenttrafficlab/client";\n\nconst route = await decide("summarize this ticket");

Node.js 18+.

Why ATL exists

Not just model aggregation

ATL is focused on route eligibility, lifecycle state, Gate checks, authorization, bounded failover and outcome evidence.

Fail closed before routing

A provider is not treated as production-eligible just because an endpoint exists.

Machine traffic first

The target is agent-to-infrastructure traffic, not a dashboard that humans must operate manually.