6 · Tools & workflowsAgentFleet (runtime + dashboard)

AgentFleet (runtime + dashboard)

At a glance

  • AgentFleet is the runtime where deployed agents live and execute.
  • AgentFleet Dashboard is the observability layer — HITL queue, per-agent SLAs, latency, accuracy, alert feed.
  • AgentFleet Builder is the configuration surface for creating and editing agents.
  • CS folks live in the Dashboard when monitoring live deployments.

Why this matters

Every agent in Part 4 · Agent catalog runs on AgentFleet. When a customer asks “how is the agent performing?”, you answer from the Dashboard. When you need to spin up a new agent for a POC, you start with the Builder. This is the tool you’ll use daily.

Three paths to build an agent

There are three ways to create agents on the platform, depending on your comfort level and the complexity of the use case:

PathWhat it isWhen to useWho uses it
InternalDashboard permissionsEnable agent capabilities on any existing Shipsy dashboardAdding AI to an existing product surfaceCS + product
AgentFleet Builder UIVisual builder for agent configurationStandard agent patterns, POCs, demosCS + solutions eng
Claude Code Shipsy ToolkitCode-level agent creation via the agentfleet skillBespoke agents, deep customizationSolutions eng

Pre-built agents available in the Builder

These agents are already templated and can be configured for a new customer without starting from scratch:

  • Rain mode (weather-triggered ops adjustments)
  • Address Intelligence
  • RFQ Agent (freight quotation)
  • POD Intelligence
  • Control Tower

Access

EnvironmentURLUse
Demo org (Builder)agentfleetdemo.portal.shipsy.ioBuild and test agents
Demo org (runtime)agentfleet.demo.shipsy.ioSee agent execution

Restriction: Demo orgs only for now. Production deployment requires AI team sign-off.

The Dashboard

The AgentFleet Dashboard surfaces real-time operational metrics. The first five things to look at when monitoring a live deployment:

  1. HITL queue — how many conversations are waiting for human review? If this is growing, the agent is under-confident or the escalation threshold needs tuning.
  2. Escalation rate — % of conversations that required human intervention. Benchmark: < 20% for a mature agent.
  3. Latency — first-response time and total resolution time. For voice agents, first-token latency matters most.
  4. Accuracy by intent — are there specific query types where the agent is underperforming?
  5. Alert feed — SLA breaches, anomalies, system errors.

These are live environments you can explore:

DemoURLWhat it shows
Freight rate intelligencefreight-rates.app.shipsy.aiRFQ agent in action
Carrix port dashboardcarrix.app.shipsy.aiPort operations control tower
POD quality checkfloward-pod-qc.vercel.appNexa-style POD validation
Invoice reconciliationinvoice-recon-australia.vercel.appNexa invoice recon
Charge intelligencecharge-intelligence.app.shipsy.aiCharge analysis agent

AgentFlow vs AgentFleet Builder

AgentFlowAgentFleet Builder
Standard pattern (CX agent, control tower)Best fitOverkill
Customer wants to self-serveBest fitToo technical
Heavy customization / new orchestrationLimitedBest fit
Tight integration with Shipsy-internal servicesLimitedBest fit
Engineering will own the agent long-termNot idealBest fit

See AgentFlow for the visual workflow builder.

Sources

Changelog

  • 26 May 2026: Enriched with Builder paths, demo URLs, sandbox links, and Dashboard guidance.