AI assistant

🚀 Early release

AI-powered features are in early release and may not be available in your organization yet. If you'd like to try them or want to know more, reach out to us and we'll get you set up.

The nullplatform AI assistant is a chat panel embedded directly in the console. You can ask questions about your applications, deployments, and scopes, generate np CLI commands on demand, and investigate failures, all without leaving your current view.

What you can do

💡 The assistant responds in the same language you write in, including English, Spanish, and more.

Explore resources: applications, deployments, scopes, and builds
Investigate failures: current state, recent changes, and audit logs
Generate CLI commands: ready-to-run np commands and shell scripts

The assistant is read-only

It can't create, update, or delete resources directly. For write operations, it generates the command or script for you to run.

Click the AI assistant icon in nullplatform to open the chat panel and ask a question.

You don't need to provide IDs or context

The assistant knows what entity you're currently viewing. If you're on a deployment page, a question like "Why did this fail?" is enough. No need to specify the deployment ID or application name.

"Why did this fail?" "Show me recent deployments" "¿Qué pasó con este scope?"

See it in action

Investigate a failed deployment

Prompt: "Why did my deployment fail?"

Assistant response

Let me investigate deployment #1847362 for your payment-service application.

🔍 Current state

Field	Value
Application	payment-service
Environment	production
Build	#284 (commit a7f3d91)
Status	Failed
Duration	5m 27s

🚨 Root cause analysis

The deployment failed during the health check phase:

Build & push: ✅ Successful — image built and pushed to registry
Container deployment: ✅ Successful — container started on prod-cluster-us-east-1
Health check: ❌ Failed — http://payment-service.internal:8080/health timed out after 10 attempts

📋 What I found

The container started but couldn't respond to health checks because of a database connection failure:

FATAL: password authentication failed for user "payment_svc"
Connection to postgres-prod.internal:5432 refused

The DATABASE_PASSWORD parameter is missing from the deployment:

Parameter	Status
`DATABASE_HOST`	✅ Set
`DATABASE_USER`	✅ Set
`DATABASE_PASSWORD`	❌ Not configured
`DATABASE_NAME`	✅ Set

💡 Timeline

Apr 27, 10:15 UTC — DATABASE_PASSWORD was removed from the production scope by admin@company.com during a credential rotation
Apr 27, 14:23 UTC — your deployment started without the updated parameter

✅ How to fix

Add the missing parameter and redeploy:

# Set the parameter
np scope parameter create \
  --scope-id 3847291056 \
  --key "DATABASE_PASSWORD" \
  --value "your-secure-password" \
  --secret true

# Trigger a new deployment
np build deploy \
  --application-id 5739284610 \
  --build-id 284

Build and deploy all applications

Prompt: "Create a script that builds and deploys all my apps in the production namespace"

Assistant response

#!/bin/bash
# Build and deploy all applications in production namespace
# Usage: ./deploy-all-apps.sh

set -e

NAMESPACE_ID="2847139502"

echo "🔍 Fetching applications..."
APPS=$(np application list --namespace_id "${NAMESPACE_ID}" --format json)

echo "$APPS" | jq -r '.[].id' | while read -r APP_ID; do
  APP_NAME=$(echo "$APPS" | jq -r ".[] | select(.id==$APP_ID) | .name")

  echo ""
  echo "🚀 Deploying ${APP_NAME}..."

  # Start build
  BUILD_ID=$(np build start --application_id "${APP_ID}" --format json | jq -r '.id')
  echo "   ⏳ Build ${BUILD_ID} in progress..."

  # Wait for completion
  while true; do
    STATUS=$(np build read --id "${BUILD_ID}" --format json | jq -r '.status')
    [ "$STATUS" == "success" ] && break
    [ "$STATUS" == "failed" ] && { echo "   ❌ Failed"; exit 1; }
    sleep 10
  done

  # Deploy
  np deployment create --body "{\"application_id\": ${APP_ID}, \"build_id\": ${BUILD_ID}}" > /dev/null
  echo "   ✅ Deployed successfully"
done

echo ""
echo "🎉 All applications deployed!"

Once you copy the script and run it, you'll see something like this:

🔍 Fetching applications...

🚀 Deploying api-gateway...
   ⏳ Build 7392841056 in progress...
   ✅ Deployed successfully

🚀 Deploying user-service...
   ⏳ Build 7392841057 in progress...
   ✅ Deployed successfully

🚀 Deploying payment-service...
   ⏳ Build 7392841058 in progress...
   ✅ Deployed successfully

🎉 All applications deployed!

Service specification with PostgreSQL and Redis

Prompt: "I need to add PostgreSQL and Redis to my application. Show me the service spec"

Assistant response

{
  "name": "backend-datastore",
  "application_id": 5739284610,
  "specifications": [
    {
      "name": "postgres",
      "type": "postgresql",
      "version": "15",
      "parameters": {
        "database_name": "appdb",
        "instance_class": "db.t3.medium",
        "storage_size_gb": 100,
        "backup_retention_days": 7
      }
    },
    {
      "name": "redis",
      "type": "redis",
      "version": "7",
      "parameters": {
        "node_type": "cache.t3.small",
        "num_cache_nodes": 1
      }
    }
  ]
}

To create the service, run:

np service create --body '{
  "name": "backend-datastore",
  "application_id": 5739284610,
  "specifications": [
    {"name": "postgres", "type": "postgresql", "version": "15",
     "parameters": {"database_name": "appdb", "storage_size_gb": 100}},
    {"name": "redis", "type": "redis", "version": "7",
     "parameters": {"node_type": "cache.t3.small"}}
  ]
}'

Nullplatform automatically injects these environment variables into your deployments once the service is provisioned:

POSTGRES_HOST, POSTGRES_PORT, POSTGRES_DATABASE, POSTGRES_USER, POSTGRES_PASSWORD
REDIS_HOST, REDIS_PORT

Rollback to the previous deployment

Prompt: "Create a script that rolls back my application to the previous deployment if the current one is failing"

Assistant response

#!/bin/bash
# Rollback to previous deployment
# Usage: ./rollback.sh <application_id>

set -e

APP_ID="${1}"

if [ -z "$APP_ID" ]; then
  echo "Usage: $0 <application_id>"
  exit 1
fi

echo "🔍 Fetching deployment history..."

DEPLOYMENTS=$(np deployment list \
  --application_id "${APP_ID}" \
  --limit 2 \
  --format json)

CURRENT_ID=$(echo "$DEPLOYMENTS" | jq -r '.[0].id')
CURRENT_STATUS=$(echo "$DEPLOYMENTS" | jq -r '.[0].status')
PREVIOUS_BUILD=$(echo "$DEPLOYMENTS" | jq -r '.[1].build_id')

echo "📊 Current deployment: ${CURRENT_ID} (${CURRENT_STATUS})"

if [ "$CURRENT_STATUS" == "healthy" ]; then
  echo "✅ Current deployment is healthy. No rollback needed."
  exit 0
fi

echo "⚠️  Current deployment is ${CURRENT_STATUS}"
echo "🔄 Rolling back..."

NEW_DEPLOYMENT=$(np deployment create --body "{
  \"application_id\": ${APP_ID},
  \"build_id\": ${PREVIOUS_BUILD}
}" --format json)

NEW_ID=$(echo "$NEW_DEPLOYMENT" | jq -r '.id')
echo "✅ Rollback deployment created: ${NEW_ID}"

Once you copy the script and run it, you'll see something like this:

$ ./rollback.sh 5739284610

🔍 Fetching deployment history...
📊 Current deployment: 9374628510 (failed)

⚠️  Current deployment is failed
🔄 Rolling back...
✅ Rollback deployment created: 9374628587

Summary

Prompt	What the assistant generates
"Why did my deployment fail?"	Root cause analysis with timeline, logs, and a fix with ready-to-run CLI commands
"Build and deploy all apps"	Script that iterates applications and deploys each one
"PostgreSQL + Redis spec"	Service spec JSON and the `np service create` command
"Rollback script"	Script that reverts to the previous deployment if the current one is failing

Next steps

AI usage and quotas: monitor token and session consumption for your organization and individual users
AI-powered features: overview of all AI capabilities in nullplatform, including Insights and Action items

What you can do​

You don't need to provide IDs or context​

See it in action​

Investigate a failed deployment​

Build and deploy all applications​

Service specification with PostgreSQL and Redis​

Rollback to the previous deployment​

Summary​

Next steps​

What you can do

You don't need to provide IDs or context

See it in action

Investigate a failed deployment

Build and deploy all applications

Service specification with PostgreSQL and Redis

Rollback to the previous deployment

Summary

Next steps