Mr. HitssAI
All flowsPortfolio

Learning path · AI · 24 layers

AI advanced: generative, RAG, agents

Read left to right. You already generate. Tokens through the window, then prompt, schema, tools. Knowledge and adapters sit on one row. Then the application — agents through traces. Traps crossed out.

Click a shape or a question

Questions this tree answers

A generation · prompt through traces

Generative AI
Inside the call — tokens through the window, then the API
LLMs
Using models
Ground, then specialize
Adding knowledge
Customizing models
AI applications
don’t
Does not: skip the ladderDoes not: skip gold
rootArtificial intelligence
  • you already picked generate
sampleGenerative AI
  • draw from a distribution · fluent ≠ true
lmLLMs
  • next token at scale
  • weights are not your wiki
piecesTokens
  • subwords · the budget
  • count ids, not words
vectorEmbeddings
  • near = similar in this space
  • version the model
mixAttention
  • QKᵀV over the window
  • KV cache is the systems tax
stackTransformers
  • the same block, stacked
  • causal decode
windowContext window
  • finite attention span
  • not a disk
apiUsing models
  • call · constrain · loop
  • no cluster required
specPrompting
  • system / user / examples
  • version + test
schemaStructured output
  • JSON schema · parse
  • fail closed on money
fnFunction / tool calling
  • model proposes · you execute
  • IAM lives here
pixelsMultimodal
  • image / audio in context
  • measure extraction
corpusAdding knowledge
  • facts outside the cutoff
  • attach · cite
indexVector database
  • ANN + metadata ACL
  • reindex on embedder change
searchSemantic search
  • paraphrase recall
  • hybrid with keywords
loopRAG
  • retrieve then generate
  • failures are retrieval first
weightsCustomizing models
  • climb the ladder
  • prompt+RAG first
sftFine-tuning
  • your distribution
  • not a CMS for facts
adapterLoRA / PEFT
  • small delta · freeze base
  • swap adapters
pretrainTraining from scratch
  • lab · cluster
  • almost never the product path
productAI applications — the model is one box
  • state · tools · policy · measurement
loopAgents
  • cap the steps
stateMemory
  • you store it
handsTools
  • verbs + IAM
protocolMCP
  • USB for tools
policyGuardrails
  • untrusted model
gateEvaluation
  • goldens · graders
traceObservability
  • stack of a generation
rejectedFine-tune first
  • skip prompt · skip RAG
  • burns the quarter
rejectedShip on vibes
  • no goldens · no traces
  • every tweak is folklore
72%

Click a box · three arrows off a layer are what it allows

What generative systems are