Agent Launch Accelerator

Overview

A fixed-price, time-boxed professional services engagement delivering a working AI assistant prototype using the customer's existing Elastic data and a provisioned LLM, configured through Elastic's Agent Builder framework. Elastic experts configure data retrieval, connect the language model, set up the agent and tools, and tune the experience for relevant responses — delivering a validated working prototype within a fixed engagement window.

This engagement delivers a prototype/demo outcome only. It is not intended as a production-ready system. Production concerns — including high availability, scale testing, security certification, compliance hardening, and operational support — are expressly out of scope.

Scope

• Phase 1 (Day 0–1): Internal preparation; project kickoff with customer stakeholders; prerequisite validation; success criteria agreed
• Phase 2 (Days 2–3): Use case discovery and business outcome definition; data and LLM provider review including security and PII requirements; retrieval design — search method selection (BM25, ELSER, vector, or hybrid) and data modelling tradeoffs
• Phase 3a (Days 4–6): LLM connector configuration and validation; retrieval tuning for optimal context retrieval
• Phase 3b (Days 7–9): Agent setup — persona definition, system prompt configuration; built-in Elasticsearch tool configuration pointed at the relevant index; up to 2 custom tools developed collaboratively with customer engineers using Elasticsearch
• Phase 4 (Days 10–13): Testing and validation against up to 10 test prompts; prompt and tool tuning as needed; Results Review Workshop showcasing the prototype to customer stakeholders
• Phase 5 (Day 14): Knowledge Transfer and Documentation Handover; artifact transfer

Out of scope

This engagement does not include:

• Production-ready deployment, hardening, or operational readiness
• High availability configuration or scale testing
• Security certification or compliance hardening
• Observability, alerting, or operational support tooling
• More than 1 LLM connector or LLM provider
• More than 1 Elasticsearch index connected to the agent
• More than 2 custom tools
• More than 10 test prompts validated
• Data ingestion, transformation, or indexing — source data must be already loaded in Elasticsearch before Day 1
• Custom ingest pipelines or data modeling beyond what is required for retrieval tuning
• LLM provider provisioning — Customer is responsible for selecting, provisioning, and credentialing the LLM provider before the engagement begins
• Post-engagement support, managed services, or production rollout assistance

Any work outside the scope above requires a mutually executed change order and may result in additional fees, revised assumptions, and schedule changes.

Engagement timeline

• Scheduled to commence approximately 6–8 weeks after purchase, subject to resource availability and Customer readiness
• Delivered by an Elastic Consultant or a certified partner resource under Elastic oversight
• Unless otherwise agreed in writing, the services will be delivered remotely
• Delivery is expected to occur over contiguous business days or contiguous calendar weeks, as scheduled by Elastic
• If delivery is delayed, interrupted, or rescheduled due to Customer availability, access issues, environment readiness, or other Customer dependencies, Elastic may reassign resources, adjust the schedule, or require an Order Form (change order)
• Time scheduled for the engagement that cannot be used due to Customer delay, unavailability, failure to meet dependencies, or inability to provide required access will count against the total consulting days

Fixed-price conditions and assumptions

• An active Elastic cluster is running and all relevant source data is indexed in Elasticsearch before Day 1 — the engagement does not include data ingestion
• The LLM provider is provisioned and API credentials are available before the engagement begins
• Customer designates a technical resource (security engineer, platform admin, or developer) available throughout the engagement; customer engineers must be available for collaborative custom tool development sessions
• Customer provides sample queries and examples of desired and undesired results before or by Day 2
• The engagement is scoped to a prototype/demo outcome; Customer understands and accepts that this is not a production system
• Scope is limited to 1 agent, 1 LLM connector, 1 Elasticsearch index, 1 retrieval method, 1 built-in Elasticsearch tool, and up to 2 custom tools; any additions require a change order

If any of the above assumptions are not met, Elastic may adjust the schedule, limit the services performed to fit the fixed-price scope, count impacted time against the engagement, or require a change order.

Deliverables

• One (1) AI assistant prototype configured and operational in Elastic Agent Builder
• One (1) LLM connector configured and validated
• One (1) Elasticsearch index connected to the agent
• One (1) retrieval method configured and tuned (BM25, ELSER, vector, or hybrid)
• One (1) built-in Elasticsearch tool configured
• Up to two (2) custom tools implemented (collaborative development with customer engineers)
• Up to ten (10) test prompts validated with documented results
• One (1) Results Review Workshop conducted with customer stakeholders
• Project documentation delivered (use case summary, configuration notes, retrieval approach, tool specifications)
• Artifacts transferred to customer

Completion

The engagement will be considered complete upon delivery of the working AI assistant prototype, the Results Review Workshop, and project documentation. The engagement may also be deemed complete if Customer delays, is unavailable, fails to meet required prerequisites, or is otherwise unable to participate after Elastic has made commercially reasonable efforts to deliver within the agreed engagement window.

General terms

Capitalized terms used but not defined in this package description have the meanings given to them in the Order Form, the applicable Service Description, or the Elastic Services Agreement.

No formal Customer signoff and no milestone or deliverable acceptance process applies to this fixed-price Services Package. Each Service is deemed accepted upon Completion.

"Completion" means, with respect to a Service, the point at which Elastic has performed the activities within the scope of this Services Package, including (where applicable) delivery of any written report, materials, or knowledge transfer session described in this package's scope, or the expiry of the time-boxed engagement period for this package, whichever occurs first. Completion does not require Customer sign-off or acceptance of any deliverable.

Customer is solely responsible for the backup, maintenance, and security of its environment, systems, and data. Elastic is not responsible for any configuration changes, data loss, downtime, or other impact to Customer's environment arising from or in connection with the Service.

This engagement delivers a configured net-new, self-managed Elastic document search solution, including search use case analysis, data modeling and ingestion, advanced example query implementation, advanced RBAC configuration, infrastructure provisioning, and a final report, within the defined fixed-price scope. Elastic does not guarantee any specific performance, cost, operational, or business outcome beyond the deliverables defined above. Customer remains solely responsible for ongoing operations, configuration changes made outside the engagement scope, and all post-engagement activities related to its environment.

References in this package to validation, testing, acceptance tests or acceptance test harnesses, golden queries, launch readiness, or go-live describe activities performed, demonstrated, or delivered by Elastic and do not create any Customer acceptance, signoff, testing, or payment condition. Completion occurs as defined in this package regardless of any such activity, and no portion of the fees is withheld or deferred pending any test result, validation, or go-live event.