The AI engineering curriculum, one ticket at a time.

Episode 1

Your Access Badge Works!

Computer fundamentals: hardware vs software, the operating system, peripherals.

Episode 2

Thirty-Seven Browser Tabs

CPU, RAM, and storage — what each one does and its units.

Episode 3

The Feed Has Disappeared

LAN vs WAN, IP addresses, DNS, ports, client and server.

Episode 4

The Suspicious Welcome Pack

Recognising phishing; multi-factor auth; keeping software updated.

Episode 5

Nobody Is Counting Likes by Hand

PCEP 1.1-1.5: syntax, indentation, literals, numeral systems, numeric and bitwise operators, operator precedence, type conversion, console input and output.

Episode 6

Should This Comment Be Flagged?

PCEP 2.1: if / elif / else, nested conditions, comparison operators, Boolean logic (and / or / not), and truthiness.

Episode 7

Ten Thousand Comments

PCEP 2.2 and 3.1: for and while loops, range, break / continue / pass, the loop-else clause, nested loops, and basic list traversal.

Episode 8

Messy Data, Real People

PCEP 3.1-3.4: lists, tuples, dictionaries, strings, slicing, membership, copying (aliasing), comprehensions, and nested collections.

Episode 1

Stop Copying That Function

PCEP 4.1-4.2: decomposition, positional and keyword arguments, return and None, default arguments, local vs global scope, and simple recursion.

Episode 2

The Program Crashed, Politely

PCEP 4.3-4.4 and PCAP 2.1-2.2: the exception hierarchy, matching except clauses, propagation, raise and assert, and defining a small custom exception.

Episode 3

Someone Already Built It

PCAP 1.1-1.5: import forms, qualified names, module search path, `__name__` / `if __name__ == '__main__'`, selected `math` / `random` / `platform` calls, and building your own package.

Episode 4

Emoji Are Not Always One Thing

PCAP 3.1-3.3: character encoding and Unicode, code points, `ord` / `chr`, string operations and comparison, and string methods.

Episode 5

Meet the Creator Object

PCAP 4.1-4.3 and 4.6: defining classes, instances vs the class, attributes and methods, `self`, `__init__`, instance state vs class state, and name mangling.

Episode 6

The Inheritance Plot Twist

PCAP 4.4-4.5: introspection (isinstance / issubclass / hasattr), inheritance, method overriding, polymorphism, `super()`, and choosing inheritance vs composition.

Episode 7

The Export That Ate Memory

PCAP 5.1-5.5: list/dict comprehensions, lambdas, map/filter, closures and late binding, generators and lazy evaluation, and text I/O concepts (modes, encoding, cleanup, errors).

Episode 8

The Vector and the Table

NumPy ndarray creation, vectorization, and array broadcasting.

Episode 9

Python Promotion Review

All PCAP domains, plus the programme bridges: HTTP status handling, JSON shape validation, and parameterised SQL. This is a consolidation and retrieval episode.

Episode 1

Where Did the Desktop Go?

LPI 1.1, 1.3, 2.1-2.2, 4.1: Linux distributions and the shell, open-source licensing, command structure and options, quoting, environment variables, and reading man / --help.

Episode 2

Permission Denied, Again

LPI 2.3-2.4, 5.1-5.4: absolute and relative paths, hidden files, file operations, users and groups, permissions, ownership, and links.

Episode 3

The Logs Are Trying to Tell You

LPI 3.1-3.3, 4.3: text filters (grep, sort, cut, uniq), redirection and pipes, simple shell helpers, archives (tar/gzip), storage (df/du), and processes.

Episode 4

Please Stop Emailing Code

GH-900 basics and repositories: Git versus a hosting service, commits, branches, remotes, GitHub Flow, Markdown, and repository structure.

Episode 5

Your First Pull Request

GH-900 collaboration and projects: issues, pull requests, discussions, reviews, labels, milestones, project views, and resolving merge conflicts.

Episode 6

The Community Has Questions

GH-900 modern practices, security and community: hosted editors (Codespaces, dev containers, github.dev), repository visibility and roles, branch protection, a required status check, contribution files, and InnerSource vs open source.

Episode 7

The Integration Ticket

Engineering bridge: HTTP methods and status codes, request headers and bearer auth, keeping secrets out of URLs, retrying transient failures with a cap, SQL joins and the fan-out problem, GROUP BY and COUNT, and parsing JSON safely.

Episode 8

First Team Release

GitHub Foundations consolidation: the full issue -> branch -> review -> merge -> verify -> release flow, a release checklist and its residual risk, and rejecting a confident bad fix. Spirals Linux verification, Python, and the API/SQL bridge.

Episode 1

Why Not Just Buy Servers?

AZ-900 cloud concepts: the shared responsibility model, cloud service models (IaaS, PaaS, SaaS), deployment models (public, private, hybrid), consumption-based pricing, and the core benefits of cloud — elasticity, scalability, agility, and moving capital expense to operating expense.

Episode 2

A Home in Azure

AZ-900 Azure architecture and services: the resource hierarchy (subscription, resource group, resource), regions and availability zones, compute choices (VM, containers, serverless), object storage with redundancy (local, zone, geo) and access tiers (hot, cool, archive), private connectivity, and co-locating chatty resources.

Episode 3

Who Gave Them Access?

AZ-900 identity, access and security: identities vs roles vs scope, authentication vs authorisation, multi-factor authentication, role-based access control (RBAC), least privilege, Zero Trust, defence in depth, and using positive and negative access tests to prove a change.

Episode 4

The Bill Has a Plot Twist

AZ-900 management and governance: cost drivers, tags, budgets and budget alerts, the difference between Cost analysis, Advisor, Service Health and Monitor, governance through policy, and infrastructure as code (deployment templates).

Episode 5

Meet SignalNest

CLF-C02 cloud concepts and technology: the value of cloud (agility, not rewriting what works), comparing provider terminology without assuming equivalence, AWS global infrastructure (regions, availability zones, edge locations), migration as a deliberate decision, integration boundaries, and Well-Architected thinking.

Episode 6

The Other Cloud Console

CLF-C02 technology and services: AWS compute (EC2, Lambda, containers), object storage and storage classes (S3), databases (RDS relational, DynamoDB key-value), networking (VPC, DNS, CDN), load distribution, event-driven routes, and distinguishing managed services from learner-owned responsibilities.

Episode 7

An IAM Policy Walks into a Bucket

CLF-C02 security and compliance: the shared responsibility model for security, IAM policy evaluation (default deny, explicit allow, explicit deny wins), least-privilege policy scoping, root-account protection, encryption at rest and in transit, audit logs as evidence, and who owns which control.

Episode 8

Two Clouds, One Budget

CLF-C02 billing, pricing and support: purchase models (on-demand, savings plans / reserved, spot), budgets and cost tools, organisations and consolidated billing, support plan tiers, and reasoning about multi-cloud cost and resilience honestly.

Episode 1

Do We Need AI for That?

AI-901 / AIF concepts and machine-learning foundations: supervised vs unsupervised learning, features and labels, classification / regression / clustering, the model lifecycle, training and inference, train/test splits, and deciding when a model is the right tool versus rules.

Episode 2

The Model Audition

AI-901 model capabilities and implementation: reading a model card (context window, cost, regions, modalities), deployment as a state change, generation parameters like temperature, system vs user prompts, and writing a lightweight Python client against a model SDK.

Episode 3

The Anatomy of a Token

Subword Byte-Pair Encoding (BPE) and token vocabulary lookup.

Episode 4

The Caption Heard Around the Office

AI-901 language and speech implementation: speech-to-text (transcription) and its failure modes, language detection, translation, sentiment and entity analysis, confidence scores, and deciding when an automated caption is safe to publish versus needs a human.

Episode 5

Give the Feed Eyes

AI-901 vision and extraction implementation: image description and alt text, structured extraction from documents against a schema, handling a schema mismatch, grounding output in the source media, and recognising fabricated detail.

Episode 6

8-BIT Needs Boundaries

AI-901 single-agent implementation and responsible AI: constraining an agent with a system prompt and supplied knowledge, restricting its tools, evaluating safety / bias / refusal probes, scoping its access to least privilege, and configuring it to document uncertainty instead of fabricating an answer. Responsible-AI principles: fairness, reliability, privacy, inclusiveness, transparency, accountability.

Episode 7

SignalNest's Model Menu

AIF-C01 AI/ML fundamentals: predictive vs generative AI, the ML lifecycle, foundation models and generative AI (benefits and limits), and choosing among AWS AI options — pre-built AI services, managed foundation models (Bedrock), and custom model training/hosting (SageMaker) — for a specific need.

Episode 8

Prompt, Retrieve or Fine-Tune?

AIF-C01 generative AI in practice: prompting and context, retrieval-augmented generation (RAG), embeddings and vector search, model adaptation and fine-tuning, evaluation, and choosing the lightest approach that meets a knowledge or style requirement.

Episode 9

The Fairness Review

AIF-C01 responsible AI, governance and compliance: reading subgroup (fairness) evaluation results, classifying control gaps across fairness, privacy, security and evaluation, data minimisation and retention, model cards and audit evidence, and defending a launch / no-launch recommendation against competing constraints. A risk register as a lifecycle control.

Episode 1

Code Nexus Assist Gets a Real Brief

AI-103 planning and generation: choosing services and regions against a brief, deployments and quotas, project connections, managed identity instead of shared keys, bounded retries, and turning requirements into measurable acceptance criteria.

Episode 2

The Assistant Invented a Refund

AI-103 retrieval and grounding: ingestion (published-only, latest-version, chunking, OCR and enrichment for scanned sources), embeddings, semantic, keyword and hybrid retrieval, chunk-size trade-offs, document-level access control, freshness, and proving an answer is grounded in permitted sources.

Episode 3

Creators Want Visual Superpowers

AI-103 vision and media: reading image and video analysis (text, objects, regions, scene, confidence), writing supported alt text and visual descriptions, video understanding as timed segments, masked edits limited to a region, image generation controls and policy, embedded-text injection, provenance labelling and human review.

Episode 4

Lost in Translation, Found in Tests

AI-103 text and speech: language detection, sentiment, entities, structured JSON output contracts, translation and tone, transcription confidence, speech translation and synthesis as separate stations, audio reasoning and its limits, explicit error handling, regression tests with known-answer fixtures.

Episode 5

Receipts, Screenshots and Voice Notes

AI-103 content extraction: analyzers for documents, images, audio and video, OCR and layout, structured and Markdown output, per-field confidence, evidence-linked records, indexing clean representations, reconciling contradictory readings, and routing uncertainty to review instead of inventing values.

Episode 6

Give the Assistant Tools

AI-103 agents: roles and goals, tool contracts (name, parameters, side effects, approval), function calling, separating user data and tool output from instructions, object-level authorisation inside tools, scoped and per-user memory, per-agent tool grants, supervised multi-agent hand-offs, and traces as evidence.

Episode 7

The Agent Did What?

AI-103 responsible AI, security and operationalisation: trust boundaries and indirect prompt injection, guardrails, scoped tools and per-agent grants, output checks, human approval for consequential actions, auditing through traces, and safety and quality evaluation with attack and benign regression sets and error analysis.

Episode 8

The AI Engineering Review

AI-103 across all domains: planning and quotas, retrieval and search health, vision, language and speech, extraction, agents and memory, and security — plus monitoring for quality, latency, cost and drift, held-out evaluation, prompt and configuration tuning, failure analysis, staged release, and recording model, index and prompt versions.

Episode 1

It Works on My Laptop

Docker practice: images and containers, layers and build cache, build context and .dockerignore, ordering a Dockerfile, pinning inputs, non-root execution, avoiding embedded secrets and checking local build reproducibility.

Episode 2

Where Did the Data Go?

Docker skills: container-local versus persistent storage, named volumes and mounts, restart versus replacement, user-defined networks and service discovery by name, why localhost inside a container is the container, publishing ports, environment configuration and secrets at run time, and proving restart behaviour with evidence.

Episode 3

The Secret in the Image

Docker security and supply chain: what image layers and history retain, secrets in files, ENV and ARG, non-root execution, scanning for vulnerabilities and secrets, tags versus digests, pinning a deployment to a digest, rotating a leaked credential, unpublishing an image, and verifying both the remediation and the service.

Episode 4

We Went Viral

Kubernetes fundamentals: what a cluster is made of (control plane and nodes, API server, etcd, scheduler, controllers, kubelet), declarative resources, Deployments, ReplicaSets and Pods, reconciliation, resource requests and limits, and how the scheduler places pods.

Episode 5

Three Pods Are Not Ready

Kubernetes workload health: readiness, liveness and startup probes and what each one does when it fails, reading Running versus Ready, restart counts and exit codes, container logs and pod events, environment configuration errors, labels and selectors, Services and endpoints, and diagnosing in layers without disabling health checks.

Episode 6

Service, Meet Network

Kubernetes networking and storage: Service selectors, DNS-style addresses, PersistentVolumeClaims and access modes; test the specific ingress rules in the fixture without claiming complete tenant or geographical isolation.

Episode 7

Deploy Without the Dramatic Music

Kubernetes application delivery: declarative rolling updates with maxSurge and maxUnavailable, reading rollout status and revision history, rollback with kubectl rollout undo, the difference between metrics, logs and events as observability signals, why a stuck rollout isn't fixed by scaling harder, and verifying user-facing health after recovery.

Episode 8

The Platform Readiness Review

Combined Docker and Kubernetes practice: audit a runbook, inspect build inputs and digests, rehearse deployment and compatible rollback, diagnose a fixture failure and record evidence and remaining production requirements.

Episode 1

Stop Deploying by Memory

Branch protection with a required review and a required status check that actually blocks an unready merge; reading the commit/PR audit trail to find who changed what and when; using it to diagnose and recover from an unreviewed regression; team-scale collaborator roles.

Episode 2

From Commit to Candidate

CI/CD stages and explicit dependencies; triggers; dependency-cache keys; artifact and commit traceability; inspect repeat-build evidence while accounting for mutable external inputs and environment differences.

Episode 3

The Environment Is Part of the Code

Infrastructure as code: parameterised templates, declared-versus-observed state, reviewed plans, scoped deployment identities and workload federation; distinguish fixture snapshot restore from a production rollback or backup strategy.

Episode 4

The Security Gate Says No

Security and compliance gates in a delivery pipeline: separating blocking risk from noise; scanning shipped dependencies against advisories at a chosen severity; checking where a dependency came from; scoped, short-lived pipeline credentials; independent approvals; rotating an exposed secret; and keeping scan evidence linked to a traceable artifact.

Episode 5

The Tests Passed. The AI Got Worse.

Separate unit, integration, security and AI-evaluation gates; AI-quality metrics with sample size and margin of error; conservative thresholds; holdout contamination; releasing gradually with a canary; rolling back to the last known-good release; and recording a release decision that says what the measurement can and can't support.

Episode 6

Creator Night: The Feed Is Failing

Incident response under pressure: ordering actions into stabilise, diagnose and follow up; scoping a failure from logs; recording hypotheses with evidence; mitigating with a verified rollback; reasoning about a latent defect and the missing guard that spread it; communicating accurately without overclaiming; and writing a blameless, checkable incident record.

Episode 7

Creator Night: The Bill and the Breach

Bounded incident evidence, least-privilege containment and approval checks; capacity controls distinct from budget alerts; distinguish attack traffic from a client fault; test retry and cost changes and record the security and cost findings.

Episode 8

You Are the Engineer

Owning an engineering recommendation end to end: clarifying a brief into constraints, gaps and assumptions; building and testing a safe core; securing and staging a release through the gates; diagnosing an unfamiliar fault; and defending a release decision language by language with evidence, a tested rollback and an operational handover.

Episode 1

The Runaway Ticket

Autonomous agent architectures: the Perception-Reasoning-Action loop (perception of state, tool planning, invocation, observation injection, termination).

Episode 2

The Universal Connector

Model Context Protocol (MCP) architecture: host applications, protocol clients, and decoupled servers communicating over JSON-RPC 2.0.

Episode 3

The Swarm and the Supervisor

Multi-agent system architecture: Supervisor-Worker pattern, intent routing, and compound query decomposition.

Episode 4

The Judge and the Benchmark

Trajectory evaluation: tool-call precision, tool-call recall, argument accuracy, and excess-turn penalty scoring.

Episode 5

The Vault and the Thread

Recent-message buffers: slice a positive-size window, append evicted text and identify unbounded history growth and overflow cases.

Episode 6

The Autonomous Release

Worker topology: task routing and controlled catalog aggregation using fictional tool-server aliases, with host-side authorisation kept explicit.