Gen AI Lingo

A little more confidence, every day

Find your next AI skill.

Explore the course, then put each idea into practice with short interactive lessons.

  1. AI is already around you

    Meet AI through small, familiar tasks.

    8 activities →
  2. Your first safe conversation

    Build a useful invitation, one choice at a time.

    8 activities →
  3. Useful help, sensible limits

    Choose useful assistance and check what matters.

    8 activities →
  4. Learning from examples

    Follow data to model to output, with no mathematics.

    9 activities →
  5. How an answer is made

    Why answers vary, and why plausible details can be invented.

    7 activities →
  6. What the app can actually see

    Inspect what a particular interaction really has available.

    9 activities →
  7. Give a useful brief

    Supply what a task needs, without relying on prompt tricks.

    8 activities →
  8. Improve one thing at a time

    Diagnose a disappointing result and revise it on purpose.

    7 activities →
  9. Work from material you provide

    Transform a source while preserving its meaning and limits.

    9 activities →
  10. Check an answer

    Use evidence to accept, correct or hold each claim.

    8 activities →
  11. Protect people and information

    Decide what to send, and what to do if too much went out.

    8 activities →
  12. Images, voices and trust

    Judge generated media, and refuse to be hurried.

    9 activities →
  13. Learn with AI

    Keep the thinking and the recall with the learner.

    7 activities →
  14. Write and create with AI

    Produce original work that still sounds like you.

    7 activities →
  15. Plan and decide with AI

    Treat a generated plan as a draft to be made workable.

    8 activities →
  16. Tools and agents

    Tell a suggestion from an action, and supervise the difference.

    8 activities →
  17. AI, people and society

    See the human choices behind a system's behaviour.

    8 activities →
  18. Your everyday AI toolkit

    Build a routine you will still follow when busy.

    8 activities →
  19. Files and Markdown without mystery

    Read and edit the small text files agents work from.

    8 activities →
  20. Configuration is data with a format

    Read small configuration files and keep credentials out of them.

    9 activities →
  21. Different jobs for different models

    Describe a model by the job it does, not by its design.

    9 activities →
  22. Different ways to learn

    Find where a training setup's signal comes from.

    10 activities →
  23. The examples shape the model

    Inspect a collection for the faults that matter.

    10 activities →
  24. Use it: choose a model for the job

    Turn three chapters of theory into one defensible decision.

    7 activities →
  25. A neural network, one small part at a time

    Trace a numerical model through connected layers.

    9 activities →
  26. One training step at a time

    Predict, measure, adjust — and which numbers are which.

    10 activities →
  27. Learning that works on new examples

    Judge generalisation with separate evidence.

    9 activities →
  28. Use it: read a model card and find the gap

    Find the absence that would change your decision.

    7 activities →
  29. From text to small pieces

    Tokens, identifiers, and what a budget is counted in.

    7 activities →
  30. Representing relationships with numbers

    Learned rows, similarity, shares and weighted mixing.

    10 activities →
  31. The problem attention helps solve

    Order, distance, and the fixed-summary bottleneck.

    8 activities →
  32. Use it: budget a long document

    Fit a long source into a small window, honestly.

    7 activities →
  33. Attention: match, weight and mix

    Query, key, value, scores, shares, and the weighted mixture.

    10 activities →
  34. Attention across a sequence

    Self and cross attention, order signals, masking, many heads.

    9 activities →
  35. Build the Transformer picture

    The block, the stack, and what 2017 actually contributed.

    10 activities →
  36. Use it: diagnose a lost detail

    Why a supplied fact went missing, and what to do about it.

    7 activities →
  37. Language models have different designs

    Encoder, decoder, encoder-decoder, embeddings, and the alternatives.

    8 activities →
  38. Seeing, hearing and combining media

    Pixels, patches, sound over time, and reading a capability card.

    9 activities →
  39. Different ways to generate media

    Denoising, latents, adversarial training and learned paths.

    9 activities →
  40. Use it: choose a media capability

    Direction, capability table, route, and a written disqualifier.

    7 activities →
  41. From a base model to a useful assistant

    Pretraining, fine-tuning, demonstrations, and where a change lives.

    9 activities →
  42. Learning from feedback

    Preferences, reward models, RLHF, DPO, and reward gaming.

    9 activities →
  43. Why models become more capable

    Data, capacity, compute, synthetic examples and answer-time work.

    9 activities →
  44. Use it: judge a model release claim

    The claim, the mechanism, the missing baseline, a fair line.

    7 activities →
  45. Give a model useful outside information

    Finding, chunking, ranking, grounding, freshness and permission.

    9 activities →
  46. What happens while an answer is generated

    Distributions, greedy, sampling, temperature, top-p, caching.

    9 activities →
  47. Useful models can be smaller and simpler

    Linear models, trees, ensembles, routing, distillation, precision.

    9 activities →
  48. Use it: fix a wrong answer three ways

    Classify the failure, repair in the right layer, attribute the fix.

    8 activities →
  49. What does better actually mean?

    Criteria, precision, recall, thresholds, subgroups and sample size.

    9 activities →
  50. Test reliability beyond a headline score

    Fair conditions, contamination, robustness, calibration, judges.

    8 activities →
  51. Choose, monitor and keep learning

    Model cards, licences, deployment routes, updates and monitoring.

    8 activities →
  52. Use it: run a fair comparison

    One task, one criterion, conditions held, and an honest limit.

    7 activities →
  53. From hidden states to an answer

    Vocabulary, scores, the output head, targets and stop reasons.

    8 activities →
  54. What is actually in a conversation

    Roles, precedence, templates, assembly, compaction and memory.

    8 activities →
  55. Why responses take time and cost money

    Prefill, decode, caches, memory limits and end-to-end budgets.

    8 activities →
  56. Reasoning and adaptation after initial training

    Few-shot, written steps, self-consistency, further training, unlearning.

    7 activities →
  57. Use it: read your own request receipt

    Split the time, attribute the cost, find the reuse, total the task.

    7 activities →
  58. A workspace and its change history

    Folders, repositories, diffs, commits, worktrees and publication.

    8 activities →
  59. From a request to a tool result

    APIs, tools, schemas, proposals, results and failure classes.

    8 activities →
  60. The software around the model

    The harness, workflows, plans, context selection, state and stops.

    7 activities →
  61. Reliable actions over several steps

    Retries, idempotency, permissions, sandboxes, handoffs, checkpoints.

    9 activities →
  62. Which instruction file does what?

    READMEs, agent guidance, scope, saved notes and what enforces nothing.

    8 activities →
  63. A skill packages reusable know-how

    Triggers, entrypoints, staged loading, resources and a small evaluation.

    8 activities →
  64. Hooks, plugins and reusable systems

    Events, scripts, packages, provenance, dependencies and versions.

    8 activities →
  65. MCP connects an application to capabilities

    Host, client, server, messages, versions and mutual support.

    8 activities →
  66. Tools, resources and prompts

    Operations, addresses, templates, prepared workflows and errors.

    8 activities →
  67. Transport and authorized access

    Local processes, endpoints, streaming, scopes, tokens and revocation.

    9 activities →
  68. MCP and its neighboring ideas

    APIs, tool calling, skills, retrieval, agent delegation and packages.

    7 activities →
  69. Inspect, connect and troubleshoot

    Narrow scope, provenance, manual inspection, selection and layers.

    7 activities →
  70. Advanced MCP features and version changes

    Progress, cancellation, input requests, interfaces, long tasks, eras.

    9 activities →
  71. Brief a coding task

    Observed problems, acceptance criteria, scope, exploration, reproducers and right-sized plans.

    7 activities →
  72. Check the work an agent returns

    Diffs, matching a check to the risk, regression tests, failure output and shared blind spots.

    7 activities →
  73. Keep work recoverable and shareable

    Checkpoints, worktrees, conflicts, handoff notes, pull requests and release verification.

    8 activities →
  74. Meet Claude Code and start a session

    Model against agent program, surfaces and execution location, setup stages, the right checkout and the first prompt.

    7 activities →
  75. Guide Claude Code with context and extensions

    Project guidance, diagnosing a rule that did not apply, skills, narrow connections, delegation and hooks.

    7 activities →
  76. Claude Code use cases and recovery

    Exploring a path, repairing a bug, narrow tests, refactors, documentation from real code, and stalled sessions.

    8 activities →
  77. Meet Codex and choose a workspace

    Product against model, surfaces, local and cloud state, access stages, the starting state and a first read.

    7 activities →
  78. Guide Codex and inspect its reach

    AGENTS.md discovery, overrides, skills, connected servers, the three permission dials and surviving compaction.

    7 activities →
  79. Codex use cases and handoffs

    Scoped changes, evidenced diagnosis, review against a contract, delegation, reports, and an honest close.

    8 activities →
  80. Editor and cloud coding agents

    Pending changes, assistance modes, briefs for detached runs, review surfaces and choosing by review fit.

    7 activities →
  81. Other coding agents and interfaces

    Terminal, editor and cloud examples, open clients with configured providers, explicit file context and frameworks.

    7 activities →
  82. Start one small task in another tool

    The same four checks in five unfamiliar products, and what makes a comparison between them fair.

    7 activities →
  83. Useful agent work beyond a demo

    Research briefs, data cleanup, rendered documents, live interfaces, automation limits and the simplest adequate system.

    8 activities →