Enter the PIN separately for each Pro question or lesson. Opening one item does not unlock other items or topics.
How AI, RAG, and agents work
10 free of 92 questions / lessons
Example request: “What failed in last night’s pipeline?”
The user asks one sentence, but the system performs several
hidden steps.
User → Copilot/App → Instructions → Context/Search → GPT or
Claude → Response
Step 1: Receive the prompt. The application collects the
user’s question, conversation context, identity, and system
instructions.
Step 2: Decide what is needed. If the question can be
answered from supplied context, the model generates directly. If
current evidence is required, the application searches or uses a
tool.
Important: GPT and Claude are model families. Copilot is
an assistant or product experience that can use models together
with work data, search, tools, and safety controls.
How the model creates the text
A model does not write the full answer in one operation.
Example: After reading “The pipeline failed because…”,
the model estimates which next token is most suitable, selects
it, and repeats until the response is complete.
Result: The response can sound natural because the model
learned language patterns, but fluency alone does not prove
correctness. Grounding and validation provide evidence.
GPT vs Claude vs Copilot
People often compare items from different layers.
Model: GPT / Claude → Application: Copilot / Agent → Data and
Tools
GPT: A model family from OpenAI used for understanding
and generation. Claude: A model family from
Anthropic used for understanding and generation. Copilot:
A Microsoft assistant experience that combines a model with
prompts, grounding, search, applications, and enterprise
controls.
Simple memory: Model = engine. Copilot = complete car.
Agent = a car that can also choose a route and perform approved
work.
1 · The application builds the actual prompt
The visible text box is often only one piece of model input.
System/developer instructions + conversation + retrieved evidence
+ user message + tool definitions → serialized model input
A chat application may add system or developer instructions,
recent conversation turns, summaries of older turns, retrieved
passages, output-format rules, and tool schemas. It serializes
these messages into the model's expected format. Some APIs also
include image, audio, or other non-text inputs. The model only
receives what the application sends within the request; an
application may keep other data outside the model.
The context window is a finite token budget shared by the input
and, depending on the service, generated output. If history
grows too large, the product may truncate it, summarize it, or
reject the request. That is why a long conversation is not
guaranteed to be perfectly remembered.
Debugging question: What exact messages, retrieved
evidence, tool definitions, and token limits reached the model?
Log a privacy-safe request shape and token counts—not secrets or
sensitive prompt contents.
2 · Tokenization and embeddings
The network processes numerical representations, not words as humans see them.
A tokenizer splits text into model-specific pieces. A token can
be a whole common word, part of a word, punctuation, or
whitespace; token count is not the same as word count. Each
token ID maps to a learned vector. Position information is also
represented so the model can distinguish order and relative
location in the sequence.
Different tokenizers can encode the same text into different
numbers of tokens. Code, uncommon names, and some languages can
use more tokens than expected. More input tokens generally mean
more prefill work, more context memory, and higher usage cost
for metered APIs.
Practical impact: Keep instructions clear and context
relevant. Repeating large policy text in every agent round
wastes input budget unless the serving system can safely reuse
cached prefixes.
3 · What attention does inside a Transformer
Each position builds a context-aware representation using other allowed positions.
In a typical self-attention layer, learned projections produce
query, key, and value vectors. A position compares its query
with keys at permitted positions to calculate relevance
weights, then combines their values. Multiple attention heads
learn different relationships. A causal mask prevents a
next-token model from using future answer tokens that it has
not generated yet.
Transformer blocks also use feed-forward (MLP) layers,
residual paths, normalization, and learned weights. Repeating
these blocks transforms token representations into richer
contextual features. Attention is not a literal human thought
process or a guarantee that the model understands facts; it is
a mathematical operation inside a trained network.
Memory: Attention mixes context; MLP layers transform
each position's features; residual and normalization
operations help deep networks train and operate.
4 · From hidden state to the next-token choice
Generation repeatedly ranks possible next tokens, then applies a decoding policy.
Final hidden state → vocabulary logits → sampling/selection → token appended
The output head maps the current representation to a score
(logit) for each token in the model's vocabulary. A decoding
method converts those scores into a next-token choice. Greedy
decoding takes the highest-scoring option; sampling can use
temperature, top-p, or related controls to vary the choice.
These controls affect output variability; they do not add
knowledge or verify correctness.
The chosen token is appended to the context and the model
predicts again. Generation ends when it emits a stop token,
reaches a configured limit, or the service stops the request.
The result is decoded back into text. A tool-call response is
still model output: the application must validate the requested
tool, arguments, permissions, and result before continuing.
Conceptual pseudocode · not a provider SDK
tokens = tokenize(messages)
state = transformer_prefill(tokens)
while not stopped:
logits = output_head(state.last_position)
next_token = decode(logits, policy)
if is_stop(next_token):
break
tokens.append(next_token)
state = transformer_decode_next(tokens, cached_state)
Important: A fluent sentence is not proof of truth. The
next-token objective rewards plausible continuation, not a
built-in fact-check. Use trusted retrieval, tool verification,
structured constraints, and evaluation when correctness matters.
5 · Why the first token and the rest have different latency
Prompt processing is parallelizable; autoregressive output has a sequential dependency.
During prefill, the model processes the supplied prompt
to build representations and attention state. Hardware can
parallelize much of this work across input positions, although
a longer context still takes more compute and memory. The
service then produces the first output token; user-perceived
time-to-first-token (TTFT) also includes network, queueing,
routing, and service overhead.
During decode, each new token depends on previous
generated tokens, so output proceeds step by step. A KV cache
stores reusable keys and values from earlier positions so the
model need not recompute the full prefix each time. It saves
repeated work, but the cache consumes memory and each token
still requires model computation. Long input and long output
therefore affect different portions of total latency.
Measure separately: time-to-first-token, output tokens
per second, total latency, queue time, input/output token
counts, and retry/tool time. “Fast” can mean quick first
response, high generation throughput, or low end-to-end time;
these are not interchangeable.
6 · Why one model feels fast and another reasons more deeply
Speed and reasoning are product/model trade-offs—not a single “smartness” switch.
A model can feel faster because it is smaller, uses fewer or
more efficient active computations, runs on faster or closer
hardware, has an optimized serving stack, receives a shorter
prompt, emits fewer tokens, or is less busy. Quantization,
batching, speculative decoding, caching, routing, and
streaming can also change the measured experience. Providers
do not always publish enough details to identify which factor
dominates.
A fast model may show less reasoning depth if it uses a smaller
capacity, has been tuned for concise answers, receives less
inference-time thinking budget, or simply answers before
exploring enough alternatives. A reasoning-focused model may
take longer because it runs additional internal computation,
generates more tokens, uses more complex decoding, or calls
tools. More reasoning is not automatically more correct; extra
steps can still make mistakes.
Model-name caution: “Astra” is not enough to identify a
specific model and deployment. Exact speed and reasoning
behavior depend on its provider, version, settings, region,
prompt, load, and benchmark. Compare the exact model IDs under
the same task and conditions rather than inferring internals
from a name.
Choose with evaluations: Test representative easy,
multi-step, coding, grounded, and no-answer tasks. Compare
correctness, latency percentiles, token use, tool success, and
cost—not one demo answer.
7 · Why “reasoning level low” can happen
A model cannot reason over evidence, steps, or budget it never received.
Common causes include an underspecified question, missing
constraints, irrelevant or incomplete context, a small output
limit, a model optimized for quick responses, low reasoning
effort settings, or a request that does not ask for a
structured explanation. In a multi-step task, the model may
also need retrieval, calculation, code execution, or another
tool rather than more prompt wording.
Improve the task contract: state the goal, assumptions,
constraints, evidence sources, expected format, and what to do
when information is missing. For critical calculations, use
deterministic code; for current facts, retrieve trusted sources;
for consequential actions, validate and require approval.
Increasing the token budget can allow a longer response but does
not guarantee better reasoning.
Prompt structure · guide the work, do not demand hidden chain-of-thought
Goal: Compare these two API designs for our stated workload.
Context: [trusted requirements and measured traffic]
Constraints: p95 under 200 ms; preserve tenant isolation.
Task: Identify assumptions, compare failure modes, and recommend one option.
Evidence: Cite the supplied requirement IDs; say when evidence is missing.
Output: Decision, trade-offs, risks, and validation plan.
Do not invent measurements or claim a test was run.
Evaluation over vibes: Score answer correctness,
evidence use, coverage of constraints, calibration, latency,
and cost on a repeatable test set. Do not rely on the model
exposing private reasoning traces as proof of correctness.
Premium question 11
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 12
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 13
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 14
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 15
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 16
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 17
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 18
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 19
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 20
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 21
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 22
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 23
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 24
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 25
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 26
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 27
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 28
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 29
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 30
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 31
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 32
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 33
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 34
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 35
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 36
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 37
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 38
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 39
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 40
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 41
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 42
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 43
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 44
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 45
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 46
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 47
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 48
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 49
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 50
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 51
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 52
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 53
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 54
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 55
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 56
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 57
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 58
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 59
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 60
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 61
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 62
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 63
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 64
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 65
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 66
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 67
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 68
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 69
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 70
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 71
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 72
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 73
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 74
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 75
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 76
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 77
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 78
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 79
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 80
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 81
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 82
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 83
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 84
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 85
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 86
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 87
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 88
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 89
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 90
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 91
Detailed answer, worked example, and practice explanation.
Pro only
Premium question 92
Detailed answer, worked example, and practice explanation.