Vibe Engines is free, interactive AI engineering & system design — runs in your browser. Pick a learning path →
18 stations. 3 tracks. From rapid prototypes and enterprise RAG to customer VPCs, security reviews, and proving ROI — become the engineer who ships AI where the customer lives.
18 stations on 3 ladders, in order — each rung is written assuming the one above it. Mark them off as you go; your progress is saved in this browser.
6 rungs · ~6h · ends at Integration Glue.
F1 · Beginner · 40 min
Forward-deployed means embedded: you sit with the customer, own an outcome instead of a feature, and carry the product into a messy real-world environment. Learn where the role came from, why every AI lab now hires for it, and the tension you will manage forever — building for one customer while feeding a product that serves many.
Build itTake a real product you know and write the one-page brief for deploying it inside a specific company: the outcome, the blockers, the first two weeks.
✓ CheckpointExplain what an FDE is accountable for that an AI engineer usually is not — the answer is who defines correct.
F2 · Beginner · 55 min
The FDE superpower is the 48-hour demo: something real, on the customer’s actual data, days after the kickoff. Learn to scaffold fast with coding agents, fake the parts that do not matter yet, and get real data flowing early — because a mediocre demo on their data beats a perfect demo on yours.
Build itScope a demo you could ship in two days for a claims-processing team: what is real, what is mocked, and what data you need from them on day one.
✓ CheckpointExplain why the first prototype should be thrown away, and what it was actually for.
F3 · Intermediate · 60 min
Your raw material is the model. Learn the working toolkit — prompting that survives contact with users, structured outputs your code can parse, picking the right model for the job, and the token math that decides what a workflow costs at the customer’s volume.
Build itA customer wants 50K support tickets classified daily. Pick the model, design the output schema, and estimate the monthly bill.
✓ CheckpointJustify reaching for retrieval over fine-tuning on a customer problem, using know-versus-behave.
F4 · Intermediate · 65 min
The default FDE deliverable: the customer’s knowledge, answerable. Learn chunking, retrieval and reranking, grounding with citations, and access control — because in an enterprise, who may see which answer matters as much as the answer.
Build itDesign RAG over a company wiki where sales must not see HR docs. Where does permission filtering happen — index, query, or prompt?
✓ CheckpointExplain why enterprise RAG fails on permissions before it fails on relevance.
F5 · Intermediate · 60 min
Past Q&A lies automation: agents that file the ticket, update the record, draft the response. Learn tool calling, the plan-act-observe loop, and the judgment call FDEs make weekly — when the customer needs an agent, and when a boring script is the better product.
Build itA customer wants "an agent for invoice processing". Sketch the workflow, then mark which steps deserve a model and which deserve code.
✓ CheckpointSay whether the customer's task needs an agent or a workflow, and defend it by whether the steps can be written down in advance.
F6 · Intermediate · 55 min
Enterprise value lives inside Salesforce, SAP, SharePoint and twenty internal tools. Learn the glue: REST and webhook plumbing, MCP for standardized tool access, auth flows (SSO, OAuth, service accounts), and reading undocumented legacy APIs without crying.
Build itMap the integration plan for an AI assistant that reads CRM records and writes follow-up tasks: systems, auth, and failure points.
✓ CheckpointExplain why integration work dominates the timeline even when the model work is finished.
6 rungs · ~6h · ends at The Demo.
T1 · Intermediate · 55 min
The stated problem is rarely the real one. Learn to run discovery — shadow the workflow, find where hours actually go, define success as a number before writing code — and to scope ruthlessly: the pilot that ships beats the platform that does not.
Build itA COO says "we want AI for operations". Write the five discovery questions that turn that sentence into a scoped, measurable pilot.
✓ CheckpointTurn a vague customer ask into a question whose answer changes a decision. If no decision moves, it is not scoped.
T2 · Intermediate · 65 min
The data is always worse than promised: scanned PDFs, SharePoint labyrinths, CSVs exported from a system nobody remembers. Learn document extraction, cleaning pipelines, and triage — which data problems you fix, which you work around, and which kill the use case honestly and early.
Build itThe customer hands you 10K scanned invoices and an Excel of vendor codes. Design the pipeline from mess to queryable — and name the step most likely to fail.
✓ CheckpointDescribe a data problem you would find only by opening the customer's actual export.
T3 · Advanced · 65 min
Your beautiful stack meets their VPC, their on-prem cluster, or an air-gapped room. Learn to package for hostile territory — containers and Kubernetes, egress rules, model access constraints (their cloud, your API, or local weights) — and to debug through a bastion host with someone watching.
Build itThe customer allows no data egress. Redesign your architecture: where does the model run, and what breaks compared to your SaaS setup?
✓ CheckpointExplain what changes about your architecture when nothing may leave the customer's network.
T4 · Advanced · 60 min
Before production comes the gauntlet: the security review, the DPA, the compliance checklist. Learn to speak SOC 2, GDPR and HIPAA at working depth, handle PII (redaction, retention, residency), and wire guardrails so the AI cannot be talked out of the rules.
Build itPrepare the one-page answer to "where does our data go?" for a RAG deployment — every hop, every store, every retention clock.
✓ CheckpointExplain what a compliance requirement demands of your design that a security best practice does not.
T5 · Advanced · 60 min
The customer will judge the system on examples you never saw. Learn to build the golden set from their real cases, agree acceptance criteria before launch, score with LLM-as-judge where labels are scarce, and rerun the suite before every change — so "did it get worse?" is a lookup, not a fight.
Build itDefine the eval for a contract-review assistant: 30 documents, what is measured, and the number below which you do not ship.
✓ CheckpointExplain the negotiated eval: two of the customer's experts disagree on the same case, and the gate depends on it.
T6 · Intermediate · 50 min
Deals move on demos. Learn the craft: their data on screen, one rehearsed wow moment, graceful handling when the model fumbles live, and the discipline to show real limits — because a demo that overpromises writes a check the deployment cannot cash.
Build itScript a 10-minute demo of a RAG assistant for a skeptical buyer: the opening question, the wow beat, and the planned recovery when an answer is weak.
✓ CheckpointExplain why a demo that impresses can still fail — and what you would show instead.
6 rungs · ~6h · ends at The Career.
P1 · Advanced · 55 min
Deployments die politically before they die technically. Learn to map champions and blockers, translate model behaviour into business language, and manage the 80% problem — the demo amazed everyone, now you must explain what the other 20% costs and who handles it.
Build itDraft the three-paragraph email that resets expectations after a flashy demo: what ships now, what needs data, what stays human.
✓ CheckpointName the stakeholder who can kill your deployment without ever being in a technical review.
P2 · Advanced · 65 min
The prototype won the pilot; now it must survive Monday morning. Learn the hardening pass — auth, logging, tracing, SLOs, on-call handoff — and the discipline of turning demo shortcuts into either real engineering or documented debt.
Build itList the ten things that must change before your demo RAG app serves 500 employees — and which three you refuse to launch without.
✓ CheckpointExplain what has to be true before a pilot becomes production, beyond it working.
P3 · Advanced · 60 min
It broke inside their network, and you cannot SSH in. Learn safe rollout machinery — feature flags, staged releases, kill switches — plus remote debugging etiquette and the incident write-up that turns a bad Tuesday into renewed trust.
Build itDesign the rollout plan for a risky model upgrade at a customer: stages, the metric watched at each, and the exact rollback trigger.
✓ CheckpointExplain who is on call for your deployment after handover, and what you owe them.
P4 · Advanced · 55 min
Renewals are bought with numbers, not vibes. Learn to instrument the metrics the buyer cares about — hours saved, deflection rate, accuracy versus the old process — baseline them before launch, and ship the dashboard the executive actually opens.
Build itFor a support-triage deployment, define the three numbers on the renewal slide and exactly how each is measured.
✓ CheckpointState the number that proves your deployment worked, and say who agreed to it in advance.
P5 · Advanced · 60 min
One heroic deployment is a story; ten repeatable ones are a business. Learn to turn bespoke work into playbooks and templates, keep customer variants as configuration instead of forks, and feed field learnings back to the product team as their sharpest signal.
Build itAfter three similar deployments, extract the template: what is identical, what is config, and what was never worth customizing.
✓ CheckpointExplain what makes a deployment repeatable for the next customer, and what stays bespoke.
P6 · Intermediate · 45 min
FDE is a launchpad: the rare role that compounds engineering, product sense and customer judgment at once. Learn the paths out — solutions architecture, product, founding — why AI labs pay a premium for it in 2026, and how to keep your engineering edge sharp while living in the field.
Build itWrite your six-month FDE development plan: one craft skill, one field skill, one outcome skill — and the deployment that proves each.
✓ CheckpointExplain what transfers if you move from FDE to product engineering, and what does not.
The common questions before you start — how long it takes, whether to follow it in order, and how it stays current.
It runs 18 stations across 3 tracks — roughly ~17h of focused learning, plus the time you spend actually building. It is self-paced, so most people work through it over a few weeks, an evening or a single station at a time.
The tracks are ordered so each station builds on the one before, and following them start to finish is the intended path. But every station also stands alone — if you already have the foundations, jump straight to the part you need.
Yes. The whole roadmap, and every handbook, lab, and challenge it links to, is free and open — no sign-up and no paywall.
It teaches the durable fundamentals of the role first, then the tooling and the AI-era shifts on top — so most of it stays relevant as individual tools churn, and it is revised as the role itself changes.
Anyone stepping into or leveling up in the Forward-Deployed Engineer role — whether you are switching in, early-career, or a senior filling gaps. Start where you are; the ladder shows what is left.
See this alongside everything else on the same subject — handbooks, system designs, challenges and tools, in one place.