One search. Connected ideas.
Find the lesson, understand the concept, and prepare your answer.
20 results shown · grouped by type
Lessons8
AI and LLM fundamentals
Smaller models often reduce cost/latency but may perform worse on complex tasks; stronger models may justify higher cost for difficult reasoning or synthesis. Routing sends different tasks to appropriate paths. The right split comes from evaluation, not model…
Token optimization removes unnecessary model input/output while preserving task information. Prompt compression shortens instructions or evidence; context trimming selects only relevant history and sources. Shorter is useful only if important conditions…
Exact caching reuses results for the same normalized request and dependencies. Provider prompt caching can reduce processing/billing for supported repeated prefixes. Semantic caching reuses results for similar meanings, which is more risky because similar…
Batch processing groups noninteractive tasks; bounded concurrency controls simultaneous requests; rate limits constrain traffic over time. Streaming exposes progress earlier. Fallback uses an approved alternative after eligible failures.
Model selection chooses a model for a task. Routing chooses among models or processing paths per request, while fallback handles a failed or unavailable preferred path. Latency is waiting time; cost includes tokens, tools, retrieval, infrastructure, and…
Beginner — What do you trace in an AI request?
Artificial intelligence, or AI, is the broad field of making software perform tasks such as recognizing speech, finding patterns, or understanding language. Machine learning, or ML, learns patterns from examples instead of requiring a rule for every case.…
Interview questions8
Smaller models often reduce cost/latency but may perform worse on complex tasks; stronger models may justify higher cost for difficult reasoning or synthesis. Routing sends different tasks to appropriate paths. The right split comes from evaluation, not model…
Token optimization removes unnecessary model input/output while preserving task information. Prompt compression shortens instructions or evidence; context trimming selects only relevant history and sources. Shorter is useful only if important conditions…
Exact caching reuses results for the same normalized request and dependencies. Provider prompt caching can reduce processing/billing for supported repeated prefixes. Semantic caching reuses results for similar meanings, which is more risky because similar…
Batch processing groups noninteractive tasks; bounded concurrency controls simultaneous requests; rate limits constrain traffic over time. Streaming exposes progress earlier. Fallback uses an approved alternative after eligible failures.
AI and LLM fundamentals
Model selection chooses a model for a task. Routing chooses among models or processing paths per request, while fallback handles a failed or unavailable preferred path. Latency is waiting time; cost includes tokens, tools, retrieval, infrastructure, and…
Beginner — What do you trace in an AI request?
Artificial intelligence, or AI, is the broad field of making software perform tasks such as recognizing speech, finding patterns, or understanding language. Machine learning, or ML, learns patterns from examples instead of requiring a rule for every case.…
Modules4
AI Engineering learning module
AI Engineering learning module
AI Engineering learning module
AI Engineering learning module