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
- Contrasting the role with that of ML and solutions engineers
- Focusing on delivering outcomes rather than just hitting milestones
- Collaborating with product, research, and security teams
Discovery in Messy Enterprises
- Tracking a workflow from start to finish
- Mapping out systems, data flows, and handoffs
- Identifying the primary constraints that hinder value delivery
Problem Scoping and Prioritisation
- Assessing the feasibility of potential use cases
- Evaluating candidate workflows based on required effort
- Selecting the initial workflow to validate
Value Framing and Acceptance Criteria
- Establishing baseline metrics prior to development
- Communicating the business case to finance sponsors
- Defining acceptance criteria in collaboration with end-users
Model Selection: Frontier and Open Weights
- Evaluating GPT-6, Claude 5.5, and open-source models
- Balancing context window, latency, and unit costs
- Determining when data policies necessitate locally hosted models
Context Engineering and Prompt Design
- Structuring instructions to ensure reliable model behaviour
- Aggregating context from systems of record
- Optimising via prompt caching and token reduction
Retrieval and Knowledge Grounding
- Chunking and indexing corporate content
- Implementing hybrid search, reranking, and citation
- Assessing retrieval quality independently of generation
Agents and Tool Use
- Designing tools and defining typed interfaces
- Developing solutions using OpenAI and Claude agent SDKs
- Managing approvals, retries, and error handling
MCP and Enterprise Integration
- Understanding the Model Context Protocol 2026-07-28 revision
- Creating and securing MCP servers
- Enforcing tool permissions against enterprise identity systems
Evaluation as the Delivery Language
- Creating golden sets derived from real-world work
- Using automated scoring and LLM-based judges
- Setting release gates based on evaluation thresholds
Guardrails, Safety and Human Oversight
- Applying guardrails at prompt, tool, and policy levels
- Defining escalation paths and human review checkpoints
- Maintaining audit trails and adhering to data handling obligations
Deployment Architecture in the Customer Estate
- Navigating identity, network, and data residency requirements
- Implementing model gateways and multi-provider abstraction
- Managing infrastructure as code and release workflows
Observability, Cost and Token Economics
- Tracing agent executions and tool invocations
- Creating dashboards for quality monitoring and expenditure tracking
- Reducing costs while maintaining quality standards
Adoption and Change
- Enabling the workforce performing the tasks
- Building champion networks and feedback mechanisms
- Tracking adoption speed and progress
From Engagement to Reusable Capability
- Packaging validated workflows
- Developing playbooks, blueprints, and accelerators
- Transferring ownership to internal teams
Requirements
- Proficiency in Python, including API integration and virtual environment management
- Knowledge of cloud platforms, containers, and version control systems
- Previous experience calling LLM APIs or developing prompt-based features
- Foundational understanding of enterprise systems such as CRM, ERP, or ticketing platforms
Audience
- Forward deployed and applied AI engineers
- Software engineers transitioning to customer-facing AI delivery
- Technical consultants and solutions architects managing AI rollouts
- Platform engineers supporting production AI workloads
