cleandataengineering.aiAgent Harness, drawn simply
You are here: Tech stack › L15 · Release & config

Agent Harness Tutorial · Tech stack

L15 · Release & config

Prompt, model and policy versioned and rolled back together. Family: Change · between releases.

AZURE OPTIONSApp Configuration✓ usedContainer Apps revisions✓ usedContainer Registry✗ dropped: GitHub's registry insteadOUR CHOICEApp Configurationkill switch, limits, model per jobContainer Apps revisionsGitHub Actions + OIDCBicep + azdOPEN-SOURCE OPTIONSOpenFeature + flagd, Unleash· considered: not pickedTerraform, Argo CD· considered: not pickedWHO DOES THE WORKAzure gives 50% · we code once 35% · each agent team still does 15%
Dark boxes are what we run. Solid boxes are used or planned; dashed boxes were considered or dropped (crossed). The bar: grey is what Azure gives, dark is what we code once, hatched is what each agent team writes.
Why our choiceA versioned prompt + model + policy bundle on Azure's config and revisions gives a canary and a rollback without extra tooling.
OptionWhere fromVerdictWhy
App Configurationours✓ chosenkill switch, limits, model per job
Container Apps revisionsours✓ chosen
GitHub Actions + OIDCours✓ chosenBicep + azd
App ConfigurationAzure✓ used
Container Apps revisionsAzure✓ used
Container RegistryAzure✗ droppedGitHub's registry instead
OpenFeature + flagd, Unleashopen source· considerednot picked
Terraform, Argo CDopen source· considerednot picked

How it works inside the harness: The gate.

Compared: How do config and releases change safely?

Azure App Conf…AzurechosenOpenFeature + …open sourcealternativeUnleashopen sourcealternativeContainer Apps…AzurechosenBicep + azdAzurechosenTerraformopen sourcealternativeArgo CDopen sourcenot used
Dark: what we chose. Crossed and dashed: rejected or not for us. Added here (not a Series table).
OptionFromVerdictJobAzure-nativePortable off AzureOps burdenStatus
Azure App ConfigurationAzurechosenflags, model per job, thresholdsyesnolow: managedbuilt: agent.enabled, limits
OpenFeature + flagdopen sourcealternativestandard flag API + flag daemonnoyeswe run flagdlisted open source option
Unleashopen sourcealternativefeature-flag server and UInoyeswe run a server, or SaaSlisted open source option
Container Apps revisionsAzurechosencanary traffic split, rollbackyesnolowfinal
Bicep + azdAzurechoseninfrastructure as codeyesno: Azure onlylowbuilt
Terraformopen sourcealternativeinfrastructure as codevia azurerm provideryes: many cloudsstate file to manage"Bicep or Terraform"
Argo CDopen sourcenot usedGitOps deploys to Kubernetesnoyesneeds Kubernetes (AKS)listed open source option
DecisionFlags, thresholds and model per job live in App Configuration, releases roll out as Container Apps revisions, and infrastructure is Bicep with azd. Terraform is the swap if the team already uses it or needs more than one cloud.

How it is done: the real code

Cut from the live repositories each time the site is built, so it always matches what runs.

  config:
    adapter: app-configuration
    endpoint: {env: AZURE_APP_CONFIGURATION_ENDPOINT}
    label: dev
      scale: {
        minReplicas: 0
        maxReplicas: 1
        rules: [