211 minutesDeep Dive into LLMs like ChatGPT
Understand the modern LLM stack well enough to reason about tokens, training, tools and failures.
Curated library
Watch the clearest companion videos without browsing everything at once. Pick a path, continue where you left off, or use the filters when you know what you need.
Build confidence with AI basics, prompting, privacy, hallucinations, and everyday use.
Understand what AI can and cannot do before you automate anything.
Learn workflows for meetings, writing, research, no-code tools, and repeatable business tasks.
Turn AI from a chat box into a dependable work habit.
Go deeper into agents, RAG, MCP, structured outputs, evals, APIs, and local AI.
Evaluate and build AI systems without treating demos as production.
Cover governance, EU AI Act readiness, build-vs-buy decisions, ROI, and private AI choices.
Make safer AI adoption decisions for a team or company.
173 results
Nothing matches these filtersTry a different category or level, or clear the filters to see everything.
211 minutesUnderstand the modern LLM stack well enough to reason about tokens, training, tools and failures.
40 minutesEvaluate partial-autonomy product ideas where humans keep control over high-risk decisions.
190 minutesYou can build a LangGraph agent with typed state, conditional routing, checkpoints and tool use, and feel where the explicitness pays off.
66 minutesYou can stand up a CrewAI crew in the role-goal-backstory style and judge how its hidden execution loop compares with explicit graphs.
15 minutesDesign simpler agent loops with clear stopping rules, task boundaries and human control points.
18 minutesRecognize common agent-building pitfalls before adding multiple agents, complex prompts or hidden state.
66 minutesSee the full beginner workflow for building a small Cursor project, including setup, prompting, debugging, basic Git and the limits of AI-assisted coding.
5 minutesYou can name the three guardrails to set before letting AI write code for you, and know why each one prevents a specific failure.
31 minutesYou can assemble an n8n support workflow that answers tickets with RAG-backed replies and feeds solved tickets back into the knowledge base.
231 minutesSee how a support agent combines retrieval, escalation and workflow tools before production hardening.
37 minutesUse AI to challenge assumptions, compare options and surface counterarguments before making decisions.
10 minutesYou can tailor a cover-letter hook and rewrite resume bullets against a real job description using a multi-prompt workflow.
9 minutesUse AI to prepare outreach, interviews and follow-ups while keeping your story specific and honest.
17 minutesCombine active recall, practice problems and AI explanations into a repeatable learning routine.
22 minutesGenerate a realistic study plan from your goal, schedule and constraints, then adapt it as you learn.
13 minutesDesign a meeting workflow that captures transcripts, summaries and action items without losing human review.
4 minutesCompare a standalone transcription workflow with integrated meeting assistants before choosing a tool.
18 minutesUse ChatGPT to explain formulas and iterate on spreadsheet logic while verifying every result in Excel.
12 minutesSee how spreadsheet AI can structure messy text and classify data, then check formulas and labels carefully.
23 minutesSee how a long-running ChatGPT thread can support meal planning, errands, trip prep and other low-risk life-admin tasks.
4 minutesState one rule of thumb for telling AI homework help apart from AI cheating.
48 minutesLearn Midjourney prompting intuition while separating durable prompt concepts from changing UI controls.
48 minutesCompare image generators by task fit, failure modes and cost instead of memorizing a fixed ranking.
5 minutesList two visual tells that can suggest (not prove) an image is AI-generated.
5 minutesNote one example from the segment where an AI answer diverged from professional medical judgment - without treating the segment as medical advice.
11 minutesName gaps between AI conversation and licensed therapeutic care so you know when to seek a human professional.
20 minutesArticulate the difference between connection and companionship Turkle describes, and apply it to an AI chat habit.
24 minutesDesign a marketing workflow where AI drafts and routes work, but humans keep control over strategy, brand voice and publishing.
30 minutesMap the current marketing-tool landscape before deciding which workflows deserve automation.
17 minutesSet up a multi-agent coding workflow with explicit review boundaries so generated changes stay small, tested and owned.
90 minutesUse AI as a critical editor for structure, argument and revision without outsourcing your own voice.
18 minutesYou can chain Perplexity and NotebookLM into one research pipeline that finds sources and then reads and synthesises them.
26 minutesYou can set up a NotebookLM notebook and use it to summarise, question and cross-reference long documents from your own sources.
56 minutesBuild an ROI case for one AI workflow with a baseline, direct and indirect benefits, quality gates and an explicit stop decision.
26 minutesEvaluate where voice agents might fit sales workflows and where disclosure, consent and escalation become blockers.
30 minutesUnderstand the data-enrichment and personalization pipeline behind AI-assisted outbound without confusing automation with quality.
11 minutesLearn what recording quality and consent boundaries matter before creating a voice clone.
16 minutesUnderstand the main AI-audio workflow categories: narration, speech-to-speech, voice design and cloning.
10 minutesChoose between search, answer engines and chatbots based on source needs, freshness and the cost of being wrong.
23 minutesStudy a multi-agent newsletter pipeline and identify where sources, approval and failure handling belong.
20 minutesYou leave with a compact framework for prompt clarity and iteration, plus worked patterns for emails, summaries and analysis.
25 minutesBuild stronger prompts by adding role, task context, examples, constraints and output format one layer at a time.
17 minutesExplain the concept of the 'attention economy' and name one design tactic used to capture attention.
42 minutesYou will be able to apply core prompting best practices and tell zero-shot from few-shot prompting in your own work.
20 minutesYou leave with the five-part TCREI structure as a repeatable checklist for building and refining your own prompts.
24 minutesRecognize the browser-agent action loop, where it helps, and where human confirmation is still required.
2 minutesCompare desktop computer-use behavior with browser-only agents.
11 minutesSee the basic NotebookLM source-grounded workflow before building a personal document assistant.
26 minutesUnderstand the personal source-grounded workflow: collect documents, ask bounded questions, and verify citations before trusting the answer.
41 minutesMake AI build-vs-buy decisions around outcome, data control, workload economics, infrastructure readiness and operational ownership.
29 minutesUnderstand generate-score-prune reasoning patterns and when they are too expensive for real work.
25 minutesYou can layer role, structured sections and explicit thinking steps into a prompt without turning chain-of-thought into a ritual.
11 minutesUse AI to draft email faster, then pressure-test tone and clarity from the recipient's point of view.
26 minutesUnderstand why real-time conversational voice feels different from dictation or classic voice assistants.
3 minutesSee multimodal voice interaction quickly, especially interruption, tone and camera-aware conversation.
69 minutesBuild intuition for chunking choices before tuning a real retrieval system.
24 minutesSee how query rewriting, hybrid retrieval, reranking and corrective loops fit into one RAG pipeline.
20 minutesEvaluate practical access-control patterns for company knowledge RAG before indexing sensitive internal documents.
5 minutesUnderstand why screenshot-based computer use is powerful, slow, expensive and brittle compared with API-native automation.
8 minutesDecide where browser or computer-use agents might be commercially useful despite their operational risk.
25 minutesUse the OWASP LLM risk categories to review tool access, output handling and sensitive-data exposure.
11 minutesDistinguish direct and indirect prompt injection and why filtering alone is not enough.
1 minutesIn one sentence, say what a Content Credential is meant to record about a piece of media - then confirm details in current C2PA/Adobe docs, since a 30-second clip is only an intro.
22 minutesApply write, select, compress and isolate patterns to manage agent context deliberately.
8 minutesUnderstand how long context can fail under ambiguity and distractors, then design tests around that risk.
19 minutesYou can estimate when prompt caching pays off by weighing cache-write surcharges against read savings for your real workloads.
56 minutesUse prompt caching only when stable prefixes, latency and cost behavior match the workload.
12 minutesBuild a small reusable assistant with instructions, knowledge files and access settings.
13 minutesUnderstand project-level context and when it is a better fit than repeating the same background in every chat.
131 minutesUnderstand how a power user separates durable preferences from one-off context.
36 minutesConfigure personalization deliberately instead of letting memory, instructions and project context blur together.
22 minutesSee deep research and analysis modes applied to business research rather than only academic literature.
14 minutesScope a deep-research task, wait for the report, then verify citations and source quality before using it.
57 minutesIdentify two specific risks of AI companion apps for children discussed by the panel.
11 minutesDefine 'shadow AI' and name one category of data that should never go into a consumer AI chatbot.
30 minutesMap the Act's phased 2025-2027 deadlines to the vendor-evidence and ownership tasks an SME must schedule now.
107 minutesLearn the product-builder eval loop: inspect traces, label failures, define criteria, test changes and compare against human judgment.
3 minutesSee the smallest no-code version of a repeatable prompt eval.
55 minutesDesign an eval ladder that catches regressions before prompt or model changes reach users.
19 minutesSee how a production team layers assertions, human review and LLM judges so regressions surface before release.
1 minutesNote one Study Mode behavior claimed in the announcement (for example guiding instead of dumping answers) - then check current product docs, since features change.
42 minutesSee how examples change model behavior and learn when few-shot prompting is worth the extra setup.
25 minutesYou will be able to place examples inside a fuller prompt structure and anticipate how they change what the model produces.
157 minutesYou will be able to run quantisation, LoRA and QLoRA fine-tunes end to end on hardware most developers already have.
59 minutesPlace fine-tuning inside the broader training pipeline and decide when it is better than prompting or RAG.
26 minutesBuild a first n8n AI-agent workflow while recognizing where tool access, memory and guardrails belong.
92 minutesExtend a simple agent into multi-step workflows with memory, error handling and realistic business integrations.
29 minutesYou can build your first Custom GPT end to end and judge which existing GPTs are actually worth adding to your toolkit.
44 minutesUnderstand how Custom GPT instructions, actions and knowledge files fit together before pushing a simple assistant beyond the beginner workflow.
30 minutesUnderstand triggers, actions and simple automation flow before adding AI to a business process.
12 minutesDecide when an AI agent should own the trigger, reasoning and action instead of a plain Zap with an AI step.
15 minutesDecide whether a paid ChatGPT plan is useful for your current workload instead of buying the most impressive-sounding tier.
15 minutesName one risk or concern the segment raises about AI chatbots that simulate a deceased loved one - without treating the podcast as clinical grief advice.
131 minutesSee how an experienced user switches tools, modes and context strategies while keeping verification in the loop.
60 minutesBuild a non-mystical mental model of LLMs as prediction systems with context windows, training data, sampling and failure modes.
17 minutesLearn how to design AI workflows that can pause, resume, ask for human judgment and keep business state separate from model guesses.
18 minutesSee how approval gates can be implemented as explicit workflow checkpoints rather than informal manual review after something goes wrong.
13 minutesUnderstand how integrated assistants can connect email, meetings and tasks into one reviewable work loop.
14 minutesIdentify practical AI email moves: summarize threads, draft replies, adjust tone and organize follow-up work.
32 minutesYou can run a project-first learning loop, letting AI surface only the knowledge you need to finish something real.
10 minutesTurn a topic into a study plan with explanations, practice questions and feedback loops you can verify.
14 minutesInstall a local model runner, pull a small model and understand the privacy/performance tradeoff before using it for real work.
6 minutesTry local AI through a GUI and compare small-model behavior with hosted frontier models.
20 minutesUnderstand the protocol roles: host, client, server, tools, resources, prompts and transports.
16 minutesExplain what MCP changes in plain language and decide whether a tool connection should use MCP or a simpler integration.
104 minutesUnderstand how MCP fits into agentic systems beyond a local demo server.
75 minutesBuild a first MCP server and understand how tools, schemas, prompts, resources and transports fit together.
19 minutesImprove tool design so agents select the right action with the right parameters.
29 minutesDecide which behavior belongs in the system prompt, tool description or tool precondition.
7 minutesSeparate short-term and long-term memory decisions and decide when agent memory should be written.
44 minutesYou can wire episodic, semantic, working and procedural memory into an agent in code, not just name the categories.
19 minutesCompare flagship, lite, mid-tier and specialized models so routing decisions are based on task fit, cost and latency instead of brand preference.
9 minutesEvaluate model-routing tradeoffs between quality, cost and reliability before adding orchestration complexity.
30 minutesMap which AI tool belongs in each workflow step instead of forcing every task into one chatbot.
14 minutesYou leave with a stock of concrete use-case ideas mapped to the tool each fits best, instead of defaulting everything to one chatbot.
32 minutesLearn how to introduce AI into localization without removing human ownership of meaning, tone, terminology and final approval.
4 minutesUnderstand why multilingual embeddings matter for private internal search and where local retrieval can reduce data-exposure risk.
10 minutesChoose an automation platform based on hosting, AI-agent fit, integrations and maintenance tradeoffs instead of product hype.
28 minutesExpand NotebookLM from a summarizer into a repeatable research and learning workflow.
35 minutesBuild a source-grounded research notebook and turn it into briefings, study guides or working notes.
9 minutesYou can navigate traces, projects and datasets in LangSmith and read off token cost, latency, error rate and per-span detail.
154 minutesConnect tracing, evaluation, feedback and production review into an operating loop for LLM systems.
93 minutesUnderstand that chatbot conversations are not automatically private, privileged or safe for sensitive business details.
13 minutesYou can name the three risk surfaces generative AI adds at work — data, model, usage — and describe the controls each one needs.
11 minutesExplain why personal AI accounts create workplace data risk and how to set safer boundaries.
37 minutesEvaluate private AI as an infrastructure and governance decision instead of defaulting to either SaaS or self-hosting by instinct.
69 minutesRecognize the failure modes your own agents will hit first and pre-plan the tests, fallbacks and kill criteria for each.
17 minutesUnderstand what breaks when RAG moves into regulated, high-stakes enterprise use.
19 minutesIdentify the production RAG controls missing from naive document-chat demos.
13 minutesModel prompt injection as untrusted-data mixing and design boundaries around tool use.
17 minutesReview prompt-injection defenses such as taint analysis, output-shape restrictions, user isolation, deterministic settings and redundant checks for critical paths.
3 minutesSee the original product/research framing that made reasoning models different from ordinary chat models.
28 minutesUnderstand why reasoning-model prompts should specify the problem, constraints and success criteria instead of asking for visible chain-of-thought.
9 minutesExplain when retrieval is the right fix and when fine-tuning may actually help.
13 minutesChoose between prompt engineering, RAG, fine-tuning or a combination based on the actual failure mode.
77 minutesHear how production prompt engineers revise instructions, examples and behavioral constraints under real pressure instead of treating prompts as one-off text.
25 minutesWatch a vague insurance-claims prompt become a structured, testable prompt with clearer examples, output rules and refusal behavior.
39 minutesCompare agentic retrieval and graph retrieval in a concrete implementation.
16 minutesUnderstand the Microsoft-style GraphRAG flow: entity extraction, communities, summaries and query-focused synthesis.
13 minutesName risks O'Neil associates with harmful scoring systems (for example opacity, scale, and damage) without treating the talk as a complete technical definition.
10 minutesUse the C.R.A.F.T. structure as a reusable meta-prompt for generating more consistent prompts across a team library.
20 minutesTurn one-off prompts into reusable patterns with evaluation notes and iteration rules.
131 minutesLearn to route work across fast, cheap, deep-reasoning and source-grounded tools instead of using one model for everything.
17 minutesSee a structured comparison method you can reuse when deciding which model is good enough for a task.
5 minutesExplain in one sentence why an AI chatbot can sound confident while being factually wrong.
7 minutesUnderstand why document parsing, structure preservation and ingestion quality gates matter before building RAG over PDFs and mixed file formats.
32 minutesUnderstand why serving engines, batching and KV-cache memory dominate self-hosted inference economics.
14 minutesChoose a few low-risk everyday AI tasks and test prompts by comparing the result to your own judgment.
4 minutesYou can use the camera as an input, showing ChatGPT handwritten work and getting tutoring instead of a spoiled answer.
42 minutesAssess when vertical AI agents create real defensibility and when they are only thin wrappers.
34 minutesEvaluate AI product pricing and specialization around measurable outcomes rather than seat counts.
131 minutesYou can recognize when to follow up, when to switch models and when to start a fresh conversation, calibrated against real day-to-day usage.
41 minutesYou can explain what strict mode guarantees, how it differs from old JSON mode, and how refusal handling fits the structured-output contract.
18 minutesLearn why schema-first LLM calls need typed objects, validators, retries and explicit handling for malformed or hallucinated fields.
5 minutesBorrow one privacy, fairness, or responsibility talking point from the video to start an AI conversation with a teenager.
8 minutesUse multiple AI future scenarios to plan adoption without betting the company on one forecast.
60 minutesFrame AI adoption around workflow change, capability building and realistic organizational risk.
34 minutesYou can push back on the slop, magic and theft framings with a clearer picture of what generative models actually do.
12 minutesYou can argue a sober middle position between the doom and utopia extremes of the AI debate, and know which questions actually matter.
9 minutesYou can assemble task, context, exemplars, persona, format and tone into working prompts for everyday office tasks.
26 minutesRecognize reusable prompt patterns and combine them into clearer instructions, examples and evaluation steps.
16 minutesWrite one tutor-mode prompt that asks AI to guide with questions rather than give the answer directly.
6 minutesRecognize the core architecture of a voice agent and the failure points that affect customer trust in real calls.
4 minutesAgree on a private verification phrase with your family for urgent calls - confirm details against current consumer-protection guidance, not news alone.
36 minutesYou leave with a realistic sense of what AI is good at today, where it falls short, and which opportunities are worth taking seriously.
8 minutesYou can explain in plain words how an LLM predicts the next token and why calling it autocomplete on steroids is fair but incomplete.
8 minutesSummarize what the news segment claims the study found about AI-assisted writing - then treat replication and limits as open, not settled.
19 minutesUnderstand the product and model-family landscape well enough to choose one starting tool and stop endlessly comparing tabs.
10 minutesYou can name the four kinds of hallucination and recognize which one you are looking at when a chatbot gets something wrong.
36 minutesYou can explain why a model trained to predict plausible text will sometimes invent facts, no matter how polished it sounds.
90 minutesUse AI for research, structure and revision while keeping final wording and judgment under human control.
36 minutesRecognize the main ChatGPT surfaces so you can explore deliberately instead of clicking at random.
39 minutesGet oriented inside ChatGPT without treating every new sidebar item as something you must master on day one.
Recently checked videos and companion picks from the AI Expert library.

Patients Compare Using AI Versus Doctors for Medical Advice
Note one example from the segment where an AI answer diverged from professional medical judgment - without treating the segment as medical advice.

Why AI can't be your therapist | Candice Thompson | TEDxApex
Name gaps between AI conversation and licensed therapeutic care so you know when to seek a human professional.

What are Content Credentials || Content Authenticity
In one sentence, say what a Content Credential is meant to record about a piece of media - then confirm details in current C2PA/Adobe docs, since a 30-second clip is only an intro.