Forward Deployed Engineer
Take enterprise AI from a client’s problem to a production system — and prove the value it delivers.
A 35-day pathway that first builds a complete AI engineer, then adds what makes a Forward Deployed Engineer: client discovery, rapid prototyping, enterprise integration, production operations and proving business value.
- Duration
- 35 days
- Live sessions
- 52.5 hours
- Total learning
- 167.5 hours
- Capstone
- 80 hours · 2 projects
- Format
- Live, online, lab-first
What a Forward Deployed Engineer does
Forward Deployed Engineers work inside client organisations to turn an AI idea into a production system. They understand the problem first-hand, design the solution, build working prototypes fast, integrate with enterprise data and identity, take the system live and stay until it delivers measurable value.
Enterprises adopting generative AI need engineers who can deliver in the client’s environment, not just in a notebook. The clients we work with are actively hiring for this role and find it hard to fill.
Built for
Software developers who want to move into Forward Deployed Engineer roles. No prior AI engineering experience is assumed: Stage 1 builds the foundation.
Entry requirements
Python, plus the subscriptions below. Stage 2 requires completion of Stage 1.
By the end of Stage 2 you can
- Run client discovery and turn the findings into a justified architecture and delivery plan
- Build working prototypes of client use cases within a single session using advanced Claude Code workflows
- Design domain-specific evaluations with client experts and use them to drive improvements
- Deliver secure pilots on enterprise cloud AI platforms
- Engineer enterprise-grade AI: document intelligence, structured-data agents, identity-aware integrations, production agents and durable workflows
- Optimise models for client scale and operate solutions in production, including model upgrades, incidents and regulated-industry evidence
- Prove business value, hand over solutions and turn each engagement into reusable assets
Plus all seven AI Engineer outcomes from Stage 1.
What employers ask for — and where it is covered
| Employers expect | Covered | How |
|---|---|---|
| Custom evaluation frameworks built with client experts | Day 4 | Error analysis, expert labelling, judge calibration and synthetic edge cases |
| Enterprise cloud AI platforms | Day 5 | Pilot deployed to Amazon Bedrock, Microsoft Foundry or Google’s agent platform with Terraform, private networking and IAM |
| Enterprise data, single sign-on and legacy systems | Days 7–9 | Text-to-SQL with row-level security, identity-aware MCP integration, browser agents for legacy apps |
| Agents, subagents, skills and MCP servers for clients | Days 8–9 | Remote MCP server with OAuth; Claude Agent SDK agent with skills, subagents and hooks |
| Regulated-industry delivery and go-live incidents | Day 12 | Audit evidence pack, model-upgrade regression testing and a live incident drill |
| Reusable patterns, product feedback and the next use case | Day 14 | Reusable skill or MCP server, product feedback note and next use-case proposal |
How every session runs
Concepts with real examples and a short live demonstration
Hands-on build that applies the day’s concepts
Practical, job-relevant task that extends the lab
2.5 hours of learning a day: one 90-minute live session plus homework. Each stage also includes a 40-hour team capstone completed outside the live sessions.
Stage 2 — day by day
Open any day to see the theory, the lab, the homework and the outcome. Stage 1 is detailed on the AI Engineer pathway.
From Client Problem to Secure Pilot
Day 1FDE Role and Client DiscoveryLab: Discovery Session Role-Play
Theory · 30 min
- What a Forward Deployed Engineer does and how the role differs from an AI engineer
- The engagement lifecycle: discover, prototype, pilot, production and handover
- Running discovery: stakeholder interviews, process walk-throughs and pain-point mapping
- Turning conversations into measurable success criteria and a scoped first use case
Lab · 60 min — Discovery Session Role-Play
- Form teams and receive a fictional client case (retail returns, manufacturing maintenance, insurance claims, hospital discharge summaries or bank KYC review) to carry through Phase 2
- Run a 20-minute discovery interview with the trainer playing the client
- Use Claude to turn the transcript into a draft requirements document, then correct it against your notes
- Agree 3–5 measurable success criteria and the first use case to build
Homework · 60 min
Research the client's industry and list its top five process pain points and the regulations that apply.
Outcome Students can explain the FDE role and run a discovery session that ends in clear, measurable requirements.
Day 2Solution Design: Data Readiness, Architecture and Delivery PlanLab: Solution Design Pack
Theory · 30 min
- Assessing client data: quality, formats, access, PII and compliance constraints
- Choosing the pattern: prompting, RAG, agents, fine-tuning or an existing product
- Non-functional requirements (security, latency, cost, data residency) recorded in architecture decision records (ADRs)
- Phased delivery (proof of concept, pilot, production) with effort and run-cost estimates
Lab · 60 min — Solution Design Pack
- Profile the client's sample data and flag quality, access and privacy issues
- Design two candidate architectures and compare them on cost, risk and time to value
- Write an ADR for the chosen architecture
- Produce a phased delivery plan with effort and monthly run-cost estimates
Homework · 60 min
Turn the discovery findings into a user journey map and a prioritised backlog of use cases.
Outcome Students can turn discovery findings into a justified architecture and a realistic delivery plan.
Day 3Prototype in a Day with Advanced Claude CodeLab: Prototype Sprint
Theory · 30 min
- Prototyping to test the riskiest assumption, with a strict cut list
- Advanced Claude Code for delivery speed: specs, subagents, skills and parallel sessions with git worktrees
- Headless Claude Code (claude -p) for scripted and CI tasks
- Reusing Phase 1 components: RAG, tool calling, evaluation and UI templates
Lab · 60 min — Prototype Sprint
- Write a one-page spec and cut list for the client use case
- Build a working prototype with Claude Code, running parallel sessions for UI, backend and tests
- Add a headless Claude Code step to CI that reviews every pull request
- Demo the prototype against the success criteria agreed in discovery
Homework · 60 min
Build one feature from the prototype's cut list and write three acceptance tests for it.
Outcome Students can build a credible working prototype of a client use case within a single session.
Day 4Domain-Specific Evaluation with Client ExpertsLab: Client Evaluation Set
Theory · 30 min
- Why generic metrics fail in client domains
- Error analysis: reviewing real outputs, building a failure taxonomy and prioritising fixes
- Working with subject-matter experts: annotation guidelines, labelling and inter-rater agreement
- Calibrating LLM judges against expert labels, and generating synthetic edge cases
Lab · 60 min — Client Evaluation Set
- Review 50 prototype outputs and build a failure taxonomy
- Label a sample with the trainer acting as the domain expert and measure agreement
- Build and calibrate an LLM judge for the two most frequent failure types
- Generate synthetic edge cases, fix the biggest failure and show before-and-after scores
Homework · 60 min
Expand the evaluation set to 100 cases and write the labelling guidelines.
Outcome Students can build evaluations that reflect a client's definition of quality and use them to drive improvements.
Day 5Enterprise Cloud AI Platforms and Secure Pilot DeploymentLab: Pilot on a Client Cloud
Theory · 30 min
- Why clients standardise on managed platforms: Amazon Bedrock, Microsoft Foundry (formerly Azure AI Foundry) and Google Gemini Enterprise Agent Platform (formerly Vertex AI)
- Platform services: model access, managed knowledge bases, guardrails, evaluation and agent runtimes
- Deploying inside client environments: private networking, IAM roles, secrets and data residency
- Infrastructure as code (Terraform) and cost quotas
Lab · 60 min — Pilot on a Client Cloud
- Port the prototype's model calls and knowledge base to one managed platform using a free-tier or trial account
- Deploy the app from a starter Terraform template with a private endpoint, an IAM role and a secrets manager
- Apply the platform's guardrails and re-run the Day 4 evaluation
- Set a spending quota and record the platform decision in an ADR
Homework · 60 min
Compare the other two cloud AI platforms for the client case on cost and features, and update the ADR.
Outcome Students can deliver a secure pilot on a major enterprise cloud AI platform.
Enterprise AI Engineering
Day 6Document Intelligence at ScaleLab: Client Document Extraction Pipeline
Theory · 30 min
- Why document-heavy processes (claims, KYC, invoices) are core FDE use cases
- Parsing layouts, tables and scans: OCR, layout-aware parsers (Docling, Unstructured) and vision-language models
- Schema-based extraction with field-level confidence and human validation queues
- Processing thousands of documents: batch APIs, throughput and cost
Lab · 60 min — Client Document Extraction Pipeline
- Extract structured fields from 200 mixed scanned and digital client documents
- Compare a parser-plus-LLM approach with a vision-language model on accuracy and cost
- Route low-confidence fields to a human validation queue
- Run the full set through a batch API and report field-level accuracy, throughput and cost
Homework · 60 min
Add a new document type to the extraction pipeline and measure field-level accuracy.
Outcome Students can build accurate, cost-efficient document extraction pipelines for high-volume client processes.
Day 7AI on Structured Enterprise DataLab: Ask the Client's Data
Theory · 30 min
- The enterprise data landscape: warehouses and lakehouses (Snowflake, Databricks) and operational databases
- Text-to-SQL: schema context, semantic layers and example queries
- Safe query execution: validation, read-only access, cost limits and row-level security
- Evaluating analytics agents on real business questions
Lab · 60 min — Ask the Client's Data
- Build a text-to-SQL agent over a sample client warehouse (DuckDB locally or a Snowflake trial) with a curated semantic layer
- Validate every query before it runs: read-only, approved tables and row limits
- Enforce row-level security for each user
- Evaluate on 30 business questions and fix the most common failure
Homework · 60 min
Add 20 harder business questions (joins, time periods, ambiguous terms) and improve the semantic layer.
Outcome Students can build accurate, secure AI access to a client's structured data.
Day 8Enterprise Integration and IdentityLab: Connect the Pilot to Client Systems
Theory · 30 min
- Integration patterns: APIs, remote MCP servers and event-driven triggers (webhooks, queues)
- Enterprise identity: single sign-on with OAuth, OpenID Connect and SAML, and acting on behalf of the signed-in user
- Connecting to systems of record (CRM, ticketing, ERP) without bypassing their permissions
- Meeting users where they work: Slack and Microsoft Teams
Lab · 60 min — Connect the Pilot to Client Systems
- Build a remote MCP server over a mock CRM and ticketing system, protected with OAuth
- Pass the user's identity through so every tool call respects that user's permissions
- Trigger the agent from a webhook when a new ticket is created
- Deliver answers and approval requests in Slack or Microsoft Teams
Homework · 60 min
Connect a second client system to the MCP server and test permissions for three different user roles.
Outcome Students can connect AI solutions securely to client systems and identity providers.
Day 9Production Agents with Agent SDKs and Computer UseLab: Client Operations Agent
Theory · 30 min
- Building production agents with agent SDKs (Claude Agent SDK, OpenAI Agents SDK)
- Agent skills, subagents, permission controls and hooks
- Sandboxed code execution for data analysis tasks
- Computer-use and browser agents for legacy applications that have no API
Lab · 60 min — Client Operations Agent
- Build an agent with the Claude Agent SDK that uses the Day 8 MCP tools
- Package the client's procedures as agent skills and delegate research to a subagent
- Add permission hooks that block risky actions and log every tool call
- Use a browser agent (Playwright MCP) to complete a task in a legacy web app that has no API
Homework · 60 min
Write two more agent skills for the client's procedures and test them with the agent.
Outcome Students can build production-grade agents with modern agent SDKs, including agents that operate legacy applications.
Day 10Durable Agentic Workflows for Business ProcessesLab: Automate the Client Process End to End
Theory · 30 min
- Automating multi-step business processes that run for hours or days
- Durable execution with workflow engines (Temporal or Prefect): state, retries and idempotency
- Human approval steps, escalation rules and SLA tracking
- Event-driven triggers and running many workflows in parallel
Lab · 60 min — Automate the Client Process End to End
- Model the client process (for example a claim or KYC review) as a durable workflow
- Use the Day 6 extractor, Day 7 data agent and Day 9 agent as workflow steps
- Add retries, idempotent actions and a human approval step for high-risk decisions
- Stop the worker mid-run and show the workflow resumes without duplicate actions
Homework · 60 min
Add SLA breach escalation to the workflow and a monitoring view of running workflows.
Outcome Students can automate long-running business processes reliably by combining agents, human approvals and durable workflows.
Production, Scale and Client Success
Day 11Model Customisation and Optimisation for Client ScaleLab: Distil for Cost and Speed
Theory · 30 min
- When prompting is not enough: accuracy, latency and cost targets at client volumes
- Generating synthetic training data from client documents and expert examples
- Distilling a large model into a smaller, cheaper one; managed fine-tuning on cloud platforms
- Choosing between prompt caching, model routing, batching and distillation using unit economics
Lab · 60 min — Distil for Cost and Speed
- Generate a synthetic training set for the client task with a large model and filter it with the Day 4 judge
- Fine-tune a small model using managed fine-tuning or LoRA
- Compare the large model, the tuned small model and a routed combination on quality, latency and cost per 1,000 cases
- Recommend the option that meets the client's targets, backed by the numbers
Homework · 60 min
Run a second distillation experiment with a different small model or more data, and update the recommendation.
Outcome Students can meet a client's quality, latency and cost targets by customising and optimising models with evidence.
Day 12Production Operations: Rollout, Model Upgrades and IncidentsLab: Operate the Pilot
Theory · 30 min
- Production readiness and regulated-industry evidence: model risk documentation, audit trails and data residency
- Rollout strategies: shadow mode, canary releases and feature flags
- Model version upgrades: regression testing, prompt migration and rollback
- Incident response with clients: triage from traces, status updates and post-incident reviews
Lab · 60 min — Operate the Pilot
- Run the pilot in shadow mode on recorded traffic and compare it with the current process
- Upgrade to a newer model version, run the Day 4 evaluation as a regression test and fix prompt regressions
- Live incident drill: the trainer breaks the system; diagnose it from traces, fix it and send client status updates
- Write a post-incident review and an audit evidence pack for a regulated client
Homework · 60 min
Write an incident runbook for the three most likely failures and a model upgrade checklist.
Outcome Students can run AI solutions safely in production, handle model upgrades and incidents, and provide the evidence regulated clients need.
Day 13Adoption, Business Value and Stakeholder CommunicationLab: Value Review with the Client
Theory · 30 min
- Why AI solutions stall after launch: trust, habits and workflow change
- Measuring value (usage, time saved, quality, cost) and reporting it to executives
- Technical storytelling and demos for mixed business and technical audiences
- Handling objections about accuracy, cost, security and impact on jobs
Lab · 60 min — Value Review with the Client
- Build a value dashboard from pilot logs: usage, time saved, quality and cost
- Write a one-page executive update with a clear recommendation
- Deliver a 5-minute demo to a mixed panel
- Role-play five common client objections
Homework · 60 min
Prepare answers to ten likely executive questions about the solution's risks, cost and value.
Outcome Students can prove the business value of an AI solution and communicate it convincingly to client stakeholders.
Day 14Handover, Reusable Assets and Field FeedbackLab: Handover and Reuse Pack
Theory · 30 min
- Designing for handover: runbooks, ADRs, operations guides and knowledge transfer
- Turning engagement work into reusable assets: agent skills, plugins, MCP servers and reference architectures
- Giving structured feedback from the field to product and engineering teams
- Identifying the client's next high-value use case
Lab · 60 min — Handover and Reuse Pack
- Use Claude Code to draft the runbook and operations guide from the repository, then review them
- Run a 10-minute knowledge-transfer session for another team acting as the client's engineers
- Package one component as a reusable agent skill or MCP server with documentation
- Write a product feedback note and a proposal for the client's next use case
Homework · 60 min
Complete the handover pack and publish the reusable asset in the team's shared repository.
Outcome Students can leave clients self-sufficient and turn each engagement into reusable assets and insights.
Day 15FDE Capstone: Client ShowcaseLab: Final Client Showcase
Theory · 30 min
- What the panel assesses: business value, technical quality, production readiness and handover
- Habits of effective FDEs: ownership, speed and judgement
- The first 90 days on a client site
- FDE career paths
Lab · 60 min — Final Client Showcase
- Each team gives an 8-minute showcase: problem, live demo, evaluation results, architecture, production plan and value delivered
- Answer 3 minutes of questions from a panel playing business and technical stakeholders
- Receive scored feedback on technical quality, delivery and communication
- Write a personal FDE development plan
Homework · 60 min
Write an engagement retrospective and a personal 90-day plan for your first FDE client assignment.
Outcome Students can lead a client engagement from discovery to production and present it convincingly to business and technical stakeholders.
A 40-hour team project, presented at a client showcase
Each team turns its fictional client case into a production-ready solution, working outside the live sessions alongside all 15 days. Assessed on business value, technical quality, production readiness, client communication and handover at the Day 15 client showcase.
- M1Discovery and solution design
Complete the discovery pack, data readiness assessment, architecture ADR and delivery plan
Discovery and solution design pack · Days 1–2 · 4 h - M2Prototype, evaluation and pilot
Build the prototype, create the domain evaluation set and deploy a secure pilot on a cloud AI platform
Running pilot with evaluation results · Days 3–5 · 8 h - M3Enterprise engineering
Build the document or data pipeline, identity-aware integration, production agent and durable workflow
End-to-end automated client process · Days 6–10 · 16 h - M4Scale and production operations
Optimise the model for cost and latency, run in shadow mode, test a model upgrade and write the incident runbook
Optimisation report and operations pack · Days 11–12 · 6 h - M5Value, handover and reuse
Build the value dashboard, complete the handover pack and publish a reusable asset
Value dashboard, handover pack and reusable asset · Days 13–14 · 4 h - M6Showcase preparation
Rehearse the client showcase and finalise the executive summary
Showcase presentation · Day 15 · 2 h
Tools you will use
Join a cohort
Live, instructor-led cohorts with labs every session, practical homework and a team capstone you can show employers.
Enquire about the next cohortRun it for your team
A private cohort for your engineers, scheduled around your teams, with the capstone built on a use case from your own organisation.
Talk to us about a team cohort