---
title: Crest Data Quick Start Services
description: Quick Start Professional Services for Full-Stack and Agent Observability
breadcrumbs: Docs > Integrations > Crest Data Quick Start Services
---

> For the complete documentation index, see [llms.txt](https://docs.datadoghq.com/llms.txt).

# Crest Data Quick Start Services
marketplace
{% callout %}
# Important note for users on the following Datadog sites: us2.ddog-gov.com

{% alert level="info" %}
To find out if this integration is available in your organization, see your [Datadog Integrations](https://app.datadoghq.com/integrations) page or ask your organization administrator.

To initiate an exception request to enable this integration for your organization, email [support@ddog-gov.com](mailto:support@ddog-gov.com).
{% /alert %}

{% /callout %}
  Full-Stack Observability Quick Start ServiceAgent Observability Quick Start Service
## Overview{% #overview %}

Crest Data's Full-Stack and Agent Observability Quick Start Services accelerate your Datadog implementation with high-velocity, expert-led engagements designed to get your team to production.

Our Full-Stack Quick Start covers Infrastructure Monitoring, Log Management, and APM, delivering customized dashboards, intelligent alerting, and out-of-the-box integrations for immediate impact.

Our Agent Observability Quick Start delivers comprehensive AI observability using Datadog to give teams visibility into model performance, quality, and cost.

### Benefits{% #benefits %}

- **Full-Stack Observability**:

  - **Complete visibility**: Infrastructure, logs, and application monitoring in one place
  - **Rapid implementation**: Preconfigured dashboards, pipelines, and monitors from day one
  - **Cloud support**: AWS, GCP, and Azure integration
  - **End-to-end tracing**: Service mapping, transaction tracing, and application insights

- **Agent Observability**:

  - **LLM cost management**: Track token costs by workflow and model for data-driven decisions
  - **AI cost optimization**: Realize cost savings through caching, routing, model selection, and prompt tuning
  - **AI workflow reliability**: Pinpoint latency bottlenecks, failing tools, and degraded workflows
  - **AI-specific tracing**: Comprehensive pipeline traces with metadata
  - **Model quality and performance**: Compare models and build repeatable quality frameworks

- **Expert knowledge transfer**: Hands-on training and documentation

- **Proven ROI**: Value assessment templates to measure impact

- **Enterprise-grade Security**: RBAC and SSO for access control and compliance

### Project Scope{% #project-scope %}

#### Full-Stack Observability: Three-week engagement:{% #full-stack-observability-three-week-engagement %}

**Week 1: Discovery and Infrastructure Monitoring**

- Conduct platform discovery, architecture review, and Datadog setup with RBAC and SSO
- Deploy Datadog agents across 10-15 hosts (servers, VMs, containers)
- Deliver up to four infrastructure dashboards and monitors for CPU, disk, memory, and host availability

**Week 2: Log Management**

- Onboard up to two log sources
- Integrate with two hyperscaler services and two log pipelines for parsing and filtering
- Build one log analytics dashboard and up to three monitors for anomaly and pattern detection

**Week 3: APM, Knowledge Transfer, and Documentation**

- Instrument up to two services
- Enable service maps
- Implement end-to-end tracing for three transactions, one APM performance dashboard, and up to two latency or error anomaly detection monitors
- Deliver a two-hour knowledge transfer workshop
- Provide value assessment templates and Day-2 roadmap

#### Agent Observability: Four-week engagement:{% #agent-observability-four-week-engagement %}

**Week 1: Discovery, Architecture Review, Setup**

- Conduct AI use case discovery and architecture review; validate RBAC and SSO
- Build an inventory of AI components
- Define baseline KPIs and establish a tracking framework

**Week 2: Instrumentation and Trace Collection**

- Instrument up to two AI workflows
- Capture traces across the full chain
- Integrate up to two model providers and instrument up to five MCP and tool integrations
- Capture metadata (prompts, model version, token counts, session context, errors, tool outcomes)
- Build up to three dashboards around throughput, latency, failures, and token consumption

**Week 3: Quality, Cost, and Reliability**

- Build dashboards: Summary, Token Usage, Cost by workflow and model, Latency, Failure Modes
- Build up to five monitors (for example, latency spikes, error rates, and token and cost anomalies)
- Define an initial quality framework
- Validate the service map

**Week 4: Operationalization and Handover**

- Develop an AI observability runbook for common incident scenarios
- Deliver governance guidance and prompt, model, and workflow tracking recommendations
- Identify cost optimization opportunities
- Deliver a two-hour knowledge transfer workshop and Day-2 roadmap for evals, guardrails, and production SRE practices

## Support{% #support %}

For support or feature requests, contact Crest Data through the following channels:

- Sales email: [datadog-sales@crestdata.ai](mailto:datadog-sales@crestdata.ai)
- Support email: [datadog.integrations@crestdata.ai](mailto:datadog.integrations@crestdata.ai)
- Website: [Crest Data website](https://www.crestdata.ai/)

This application is made available through the Marketplace and is supported by a Datadog Technology Partner. Click Here to purchase this application.