Setting up and configuring Scout

Scout is designed to work out of the box. Once enabled, it automatically starts analyzing monitors, tests, and incidents in Coalesce Quality. That said, you can customize how Scout behaves by configuring triage settings, providing context, and selecting the right data sources.

​

Setting up Scout

Navigate to Scout’s settings by going to Settings → Scout AI (if you don’t see this, contact the Coalesce Quality team). There are three areas to configure: Context (details about your business), Infrastructure (data access and deployment), and SRE (triage and resolution). In the Infrastructure section, you’ll be asked if you want to deploy Scout on-premise or managed in the cloud.

​

Context

Help Scout understand your business and data environment — think of this like onboarding a new analytics engineer.

1. About your business — Describe your critical datasets, workflows, and known quirks in your data model. Example: “We operate a B2B payment provider solution. Our key datasets are around payments and customer orders, especially if they’re used for billing. We monitor many variables across key metrics, which should be assumed independent unless proven otherwise.”
2. Triage instructions — Define how Scout should triage issues, group incidents, and prioritize based on business impact. For example: “Group issues only when there is clear evidence of correlation.” or “Issues on the payments schemas are critical as they may signal customer-facing problems.”
3. Testing strategy — Define your preferred testing approach so Scout’s Testing & Monitoring Advisor can align with it. Examples:
   • Data product layer: Validate KPIs and critical aggregates to catch unintended logic changes.
   • Operational layer: Focus on monitoring sources, not every intermediate table, to avoid alert fatigue.

​

Infrastructure

Scout uses metadata and direct access to data sources to run diagnostics and profiling queries.

1. Deployment method sources — Select between on-premise and managed deployment. In managed mode, Coalesce Quality handles LLM calls and proxies data warehouse queries. In on-premise mode, you manage both the LLM and data warehouse queries yourself. See more about the on-premise setup here: On-Premise Setup
2. Data sources — Select the databases and systems Scout can query for profiling, sampling, and diagnostics. The more relevant sources you provide, the better Scout can analyze impact and suggest meaningful tests.

​

SRE

Scout’s triage and incident logic can be configured to match your operational needs.

1. Auto triage settings — Choose which assets and severity levels Scout should automatically triage. For example, triage Error and Fatal issues, but leave out Warnings to reduce noise.
2. Issue grouping — You can instruct Scout AI to group issues based on specific criteria, such as the severity of the issue or the type of issue

​

Models

You can change which LLM model Scout uses for reasoning and summarization under Settings → Scout AI → Models. Available options include stable and latest model versions. Opus-class models are available on request. Each model in the list shows where it runs for your workspace: your region (for example EU), a location outside your region (Singapore, for Claude models in the AU region), or Global for a model served from the Google Vertex AI global endpoint. The location of the selected model is also shown under the picker. See AI Processing for where each region runs inference. The global endpoint may process requests on any continent, so models served from it are off by default. When your region offers such a model, an Admin can turn on Allow models served from the global endpoint in the same section. With the setting off, a selected model that needs the global endpoint falls back to the default model.

​

Using prompts across the Coalesce Quality platform