Talk to an Expert

Built on Google Cloud

Halo runs in your Google Cloud

Talk to an Expert

The Challenge

Modern IT organizations in retail and CPG have spent years consolidating systems and building the fundamentals for becoming data-driven companies. On their own, those fundamentals don’t produce business value: that requires additional investment in the user-facing applications built on top of them, including Crisp.

These solutions have traditionally been delivered as external applications, hosted outside the customer’s own environment. That model has real advantages: short time to value, and a simple, predictable total cost of ownership. It also comes with real drawbacks for enterprise IT: an extended data governance perimeter, complex access control across systems, and contractual hurdles related to data rights. Although Crisp has always been able to integrate with a customer’s data systems, significant portions of the Crisp technology stack have still run externally, carrying those same drawbacks.

The Solution

Crisp Halo deployed within your own infrastructure

The Crisp Halo platform can now be fully deployed inside customers’ Google Cloud, Databricks and Snowflake environments.

Uniform access control

User management and authorization is done using the existing capabilities (such as Dataplex) within the target environment. The retail-specific semantic layer can easily be integrated with row level security based on client needs.

Zero data exports or sharing

Ingestion happens within the client platform and no proprietary data ever leaves the client’s environment. Only non-proprietary log and telemetry data is shared and monitored by central Crisp systems.

Easier data integration

Halo Agents and Applications can connect to any authorized dataset within the data warehouse without data pipelines.

Seamless user experience

Users can still enjoy the rich Halo user experience.

Flexible resource allocation

Halo can leverage existing or new compute and inference commitments.

Full support and maintenance

Crisp manages and supports the entire platform even without being able to see any of the data under management.

Architecture

How Halo is deployed in Google Cloud

Built on your Google investment

Crisp Halo uses the Google Cloud capabilities you already operate rather than introducing a separate platform.

Google Cloud capability

How Crisp Halo uses it

Dataplex

Governs all Crisp Halo data and files. Your existing grants, lineage, and audit apply, and each Crisp Halo service gets only the grants it needs.

Cloud Run

Hosts the Crisp Halo web app and agents, background tasks and schedules, and the semantic query service.

AlloyDB for PostgreSQL

One managed database holds conversations, projects, agent memory with vector search, the live response stream, and the task queue.

Vertex AI & Model Armor

Runs every model call, with the models you choose from Vertex AI, under your guardrails. Model Armor applies safety controls to each request.

BigQuery

Runs semantic queries for chat, apps, and boards as your SQL compute.

BigQuery + Malloy

Rosetta models ship with each release and compile to BigQuery SQL through Malloy.

Dataflow & Cloud Run jobs

Load and standardize retail data inside your project. Scheduled reports and background agent tasks run in the Crisp Halo services.

Identity & secrets

Signs users in through your existing SSO; roles and groups decide who can use and administer Crisp Halo.

Terraform modules

Each Crisp Halo release installs and upgrades through standard Google Cloud deployment tooling.

What gets installed in your project

Each release is a set of Terraform modules that creates or upgrades these resources in your Google Cloud project.

Resource

What it does

Cloud Run services

The Crisp Halo web app and agents, a worker for schedules and background tasks, and the semantic query service.

AlloyDB for PostgreSQL

Application state, agent memory with vector search, the live response stream, and the task queue.

BigQuery datasets

Retail data tables, governed by your Dataplex grants, lineage, and audit.

Dataflow & Cloud Run jobs

Pipelines that ingest and standardize retail data inside your project.

Vertex AI & Model Armor

The models you choose, from any provider you enable, with your guardrails.

Secrets

Keys that encrypt stored credentials.

Roles & groups

Who can use Crisp Halo, and who administers it.

Deployment and operations

Installed in minutes, kept current automatically.

The installation of Crisp Halo is fully automated and all resources will be fully provisioned within minutes. Once the system is deployed, it will be kept up to date by listening to new versions being published by the central Crisp package systems. System operational logs (no proprietary data) will be replicated to Crisp central systems to detect operational anomalies and uptime issues. Built-in AI Agents help debug issues automatically and share sanitized bug reports with central Crisp systems.

Customers can choose between weekly and daily release schedules. Regular releases have zero down-time.

Support and maintenance

Support maintenance contracts are similar to existing Crisp support contracts; we also accept contractor status for named personnel with custom security training, NDAs and system access through customer provisioned laptops / endpoints, as needed.

See Halo run in your cloud

Speak with one of our retail experts to plan a deployment in your Databricks, Snowflake, or Google Cloud environment.

Talk to an expert