PRODUCT OVERVIEW

Fleet

Monitors Agentforce behavior, detects changes from an approved baseline, and helps teams trace and resolve issues.

PRODUCT FAMILY

Testing and QA

BUILT FOR

AI Operations, Quality Assurance, Platform Engineering

PLATFORM

Salesforce

LICENSE

MIT

PRICING

Free

VERSION

1.0.0

THE NEED

The problem it solves

Teams need to know when a deployed agent stops behaving as expected, understand what changed, and resolve the issue.

THE PRODUCT

How it works

Fleet helps teams check whether an Agentforce agent still behaves as approved. It captures agent activity, replays a curated set of test cases, and compares results with an approved baseline. Teams can investigate changes in behavior alongside deployments, knowledge updates, model changes, and prompt edits, then manage remediation through an approval trail. Fleet runs in Salesforce with an Apex backend and a React interface.

CAPABILITIES

Key features

  • Capture layer: the Fleet_Turn__e platform event taps every agent turn and a trigger archives it into the Fleet_Trace__b big object

  • Golden-set replay: curated cases with assertions, replayed against each monitored agent and scored for trueness against a blessed baseline

  • Drift attribution: deviations tied to the change that caused them (deploy, KB edit, model rollforward, prompt edit) with a confidence score

  • Remediation with an approval trail: rollback and hold are one click from a finding, with quarantine state tracked per agent

  • Admin config in Custom Metadata (Fleet_*__mdt): thresholds, detectors, severity policy, assertion types and console views, changeable without a deploy

  • React 18, Vite and Tailwind console surfaced as the Fleet Lightning app, with 8 feature routes and a mock data adapter for standalone development

  • Five least-privilege permission sets: Administrator, Operator, Approver, Viewer and Integration

USE CASES

Where it helps

  • QA lead checks each morning whether every monitored agent is still inside its trueness threshold

  • Release manager lines a trueness drop up against the deploy or prompt edit marked on the same timeline

  • Operator quarantines a drifting agent and rolls it back to the blessed version straight from the finding

  • Approver signs off on a remediation before it reaches production, leaving an approval trail

  • Admin tunes drift thresholds and severity policy in Custom Metadata without a deploy

  • Team builds and demos the console standalone against seeded mock data before any Apex exists