The AI Proposal

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.