Day 5 · Fri 2026-10-09 · ChatGPT CORE

Production LLM design: RAG freshness, tenant boundary, context budgets, evals, and fallback

Week 11 trains two designs with one operating spine: admission, isolation, durable work, queue/backpressure, streaming/reconnect, derived state, evals, and recovery.

3contiguous 1-D DP slots
25-35mattempt + follow-up window
Staffinvariant, failure, recovery, metrics

Exact Daily Schedule

No drift: the same six blocks run every day.

TimeBlockContract
08:50-09:00TargetWrite one Staff-level invariant and one failure window before reading.
09:00-10:05Project design25-35m production LLM extension prompt, then RAG/evals/tenant-boundary decision pass.
10:05-10:45DDIA / source groundingMap the design to exact DDIA anchors and only direct applied-AI sources.
10:45-10:55Spoken closeRecord the architecture in English, then say the Chinese invariant aloud.
14:30-16:151-D DP contiguous blockThree NeetCode slots below; each slot is 25-35 minutes plus follow-up.
20:30-21:15Recall / artifactRun English Senior+/Staff recall and patch the scorecard evidence.

Canonical Hello Interview Anchors

Direct day-page anchors only. Source titles were verified live before build.

Canonical anchorDispositionDesign decision
Some additional deep dives you might considerCORE extensionUse only extensions that alter serving, eval, security, or operations.
What is Expected at Each LevelCORE barUse level rubric to decide Staff depth.
Mid-LevelCORE barMid-level must have a coherent serving path.
SeniorCORE barSenior owns scheduler, streaming, and context trade-offs.
StaffCORE barStaff owns tenant boundaries, eval loops, fallback, and operating controls.

Exact DDIA Mapping

Only Ch5, Ch9, and Ch13 sections are in scope.

ChapterExact sectionInterview use
Ch13维护派生状态Vectors, summaries, prompt-cache keys, and leaderboards are derived state.
Ch13观察派生数据状态Freshness, ACL rejects, stale retrieval, and drift must be observable.

Applied AI Source Gate

First-party/original sources appear only when they change a serving, eval, security, or operating decision.

First-party/original sourceConcrete decision it changes
OpenAI - RetrievalRAG freshness, chunking, and source attribution are part of product correctness.
OpenAI - Evaluation best practicesGolden datasets and graders gate prompt or model changes.
OpenAI - Evaluate agent workflowsTrace-level evals catch multi-step regressions that output-only scoring misses.
OpenAI - Data controls in the OpenAI platformTenant isolation, retention, and zero-data-retention choices constrain feature design.
Anthropic - Effective context engineering for AI agentsContext selection is an engineered budget with tools, memory, and state, not unlimited chat history.
Anthropic - Demystifying evals for AI agentsAgent evals should inspect process, tool use, and failure modes, not just final answers.
Anthropic - How we contain Claude across productsUntrusted code/tool execution requires sandboxing, egress control, and per-product isolation boundaries.

21-Slot 1-D DP Runway

Today is slot 13-15 of 21, contiguous across the week.

BlockNeetCode problemModeInvariant25-35m follow-upComplexity
14:30-15:05Combination Sum IVOrdered countdp[target] sums ways from previous targets, and order matters.Ask how answer changes if order does not matter.O(target * nums) / O(target)
15:05-15:40Coin Change IIUnordered countIterate coins outside and amounts forward to avoid permutation duplicates.Ask contrast with Combination Sum IV.O(amount * coins) / O(amount)
15:40-16:15Target SumSubset transformConvert signs to subset sum when total plus target is even and nonnegative.Ask for zeros multiplying counts.O(n * target) / O(target)

Artifacts And Recall

Use these in the evening block and scorecard.

Required spoken close: explain one invariant, one failure window, one recovery path, and one metric in English. Then restate the same design decision in Chinese without adding new components.
Local study materials
Detailed lecture notes, audio, recall scripts, PDFs, Staff Q&A, and mock packs are archived locally and are intentionally not published on this site.