Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 28 hours
Course Outline
The AI Forward Deployed Engineer
- Distinction from ML engineers and solutions engineers.
- Focusing on outcomes rather than delivery milestones.
- Collaborating with product, research, and security teams.
Discovery in Complex Enterprises
- Observing workflows from start to finish.
- Mapping systems, data flows, and handoffs.
- Identifying the key constraints that hinder value creation.
Problem Scoping and Prioritisation
- Assessing use cases for feasibility.
- Evaluating candidate workflows based on effort.
- Selecting the initial workflow for validation.
Value Framing and Acceptance Criteria
- Establishing baseline metrics before development begins.
- Using business case language for finance sponsors.
- Defining acceptance criteria in collaboration with users.
Model Selection: Frontier and Open Weights
- Comparing GPT-6, Claude 5.5, and open models.
- Balancing context, latency, and unit cost.
- Situations where data regulations require locally hosted models.
Context Engineering and Prompt Design
- Structuring instructions for consistent behaviour.
- Gathering context from systems of record.
- Utilising prompt caching and minimising token usage.
Retrieval and Knowledge Grounding
- Chunking and indexing enterprise content.
- Implementing hybrid search, reranking, and citation.
- Evaluating retrieval performance independently from generation.
Agents and Tool Use
- Designing tools with typed interfaces.
- Building using the OpenAI and Claude agent SDKs.
- Managing approvals, retries, and failure handling.
MCP and Enterprise Integration
- Implementing the Model Context Protocol 2026-07-28 revision.
- Developing and securing MCP servers.
- Assigning tool permissions based on enterprise identity.
Evaluation as the Delivery Language
- Creating golden sets from real-world work.
- Using automated scoring and LLM judges.
- Setting release gates based on evaluation thresholds.
Guardrails, Safety and Human Oversight
- Applying guardrails at prompt, tool, and policy levels.
- Defining escalation and human review points.
- Maintaining audit trails and data handling responsibilities.
Deployment Architecture in the Customer Estate
- Addressing identity, network, and data residency constraints.
- Implementing model gateways and multi-provider abstraction.
- Using infrastructure as code and structured release processes.
Observability, Cost and Token Economics
- Tracing agent runs and tool calls.
- Creating dashboards for quality and expenditure.
- Reducing costs without compromising quality.
Adoption and Change
- Enabling the individuals performing the work.
- Building champion networks and feedback loops.
- Measuring adoption speed.
From Engagement to Reusable Capability
- Packaging validated workflows.
- Creating playbooks, blueprints, and accelerators.
- Transferring ownership to internal teams.
Requirements
- Proficiency in Python, including working with APIs and virtual environments.
- Familiarity with cloud platforms, containers, and version control.
- Prior experience calling an LLM API or building a prompt-based feature.
- Basic understanding of enterprise systems such as CRM, ERP, or ticketing platforms.
Audience
- Forward deployed and applied AI engineers.
- Software engineers transitioning into customer-facing AI delivery.
- Technical consultants and solutions architects responsible for AI rollouts.
- Platform engineers supporting production AI workloads.
