Everything you ship

Build the tracker exactly to the spec in the tech section: five commands, JSON persistence, function-per-operation structure, main loop under a guard, and graceful handling of every listed failure. Work from the spec lik

Build the analyzer exactly to the tech-section spec: LogEntry dataclass, streaming LogReader composed around Day 13's parse_lines, an accumulate-once Report with counts by level, top-5 error messages, top-5 IPs, junk cou

Assemble the week into a release. Work through the shipping checklist in tech order: structure, correctness, legibility, operability, distribution. Close the two GitHub issues you filed on Day 20 (do the work, reference

Simulate the real thing: timer visible, no notes, no patterns.md, think-aloud protocol OUT LOUD for every problem. The set, one per drawer: (1) hashing — given two strings, return all characters that appear in both with

Create interview/error_log.md in your practice repo — the living document that follows you to Day 179. Sections: (1) today's mock scores with per-problem entries (miss type, cause, fix ritual); (2) the Week 5 pattern-rec

Finish the notes service as a portfolio-grade mini-repo: working CRUD API (SQL confined to db.py), 10 passing TestClient tests covering all routes' happy and failure paths, the tag index justified by recorded EXPLAIN pla

Implement shortener/ in your practice repo using the Day 45 layered template: routes / service / repo, with Day 47's cache. Endpoints: POST /v1/links (validates the URL, honors Idempotency-Key, generates a 7-char base62

Create linreg_by_hand.py + linreg_report.md. The build: import your Day 55 gd (or reimplement), train (w, b) from (0, 0) on the generated data, logging loss per step. Produce: (1) the loss-curve table (or matplotlib plot

Run the week's capstone decision. The starter recipe: with rng = np.random.default_rng(seed=63), simulate 60 shared eval questions with per-question difficulty d = rng.uniform(0.05, 0.6, size=60), then case-level results

Execute the full pipeline on your fresh dataset in a hard 75-minute timebox: EDA per your checklist, cleaning with logged repairs and a validation before/after count, and the feature plan with encodings and exclusions —

Write week11_competition/MODEL_CARD.md: (1) framing — target, features, who would use this prediction; (2) metric declaration written before modeling, with the harm-model sentence; (3) data notes — at least two observati

Ship churn_project/ as a self-contained repo directory: config-driven training on the synthetic churn data (or Telco), one persisted pipeline honoring the inference contract, MLflow-tracked experiments, tests passing, an

Ship week12_viva/ in your practice repo: (1) WALKTHROUGH.md — the four-beat churn presentation (problem, approach incl. the leakage story, result with caveat, next steps), ≤ 350 words, rehearsed aloud at least twice, plu

Assemble the day into a mnist-lab/ folder in your practice repo: train_mnist.py (both architectures, driven by trainer.py), predict.py (standalone inference), experiments.md (baseline + 3 ablations + your practice hypoth

Refactor mnist-lab/ into the Day-82 template: src/data.py (transforms + loaders, defined once), src/models.py (MLP, SmallCNN), src/train.py (config-driven entry point), src/predict.py (imports the SAME transform from dat

Ship the model file that Day 99 will train. It must contain: the config block at top (vocab_size, n_embd, n_head, n_layer, block_size); Head, MultiHead, FeedForward, Block, and TinyGPT classes; a generate(idx, max_new_to

Assemble week14_dossier.md in your journey repo: your corrected blank-page attention computation (photographed or retyped), the block diagram, both graded explanation transcripts with rubric scores, the pre-flight result

Turn today's work into a small, reproducible repo folder: train.py, generate.py (loads the checkpoint and takes a --temperature flag via argparse, Day 16 payoff), your sample diary, and a README with the loss table, the

Write how-an-llm-works.md: one page, for a non-technical executive. Requirements: one analogy sustained throughout; covers prediction objective, training data and cutoff, why capability emerges, why hallucination is stru

Write week16-lab-report.md in the llm-toolkit repo — one page, receipts only: the adversarial table (attack category, before, after, note on the surviving attack), the extraction scoreboard (all four metrics, both modes

Deliver the v0 slice end-to-end in the new docs-qa repo: authored corpus (12–20 docs with the planted structures), ingest with metadata + stable IDs, hybrid retrieval + reranking, and answer() returning grounded text wit

Deliver triage/ complete in the practice repo: 20 labeled tickets, the assembled agent (router + RAG tool + evaluator-gated drafting + escalation approval queue + memory + guards), the scorer, and a README reporting the

Write docs/redteam-findings-w19.md in the capstone repo — the deliverable a customer's security team and your own PM will both read. Sections: (1) scope and method (what "compromise" meant, how many attacks, reproducibil

Ship the Week 20 capstone gate. Commit to the capstone repo: (1) evals/golden_set.jsonl with ≥ 40 cases covering all topics, all four intents, ≥ 5 negatives, plus red-team (D133) and feedback (D138) cases; (2) evals/harn

Bring the capstone to "instruments all green." Produce observability_report.md that demonstrates, with real artifacts, each gate criterion: (1) a sample trace ID resolved to its span tree; (2) a feedback record joined to

Deploy your containerized docs-QA service to one real, publicly reachable HTTPS URL and prove it works from outside your network, then tear it down cleanly. Deliver in deploy/RUNBOOK.md: the live URL (while up), the plat

Prove the assembly line runs end to end. Deliver staging_pipeline_report.md demonstrating, with real artifacts: (1) a push to main triggering the full pipeline — test → eval-gate → build+SHA-tag → push → deploy to stagin

Assemble the evidence pack and declare production. docs/cutover_log.md must show: production URL serving externally; canary green ×3; fallback drill executed in prod with metrics evidence; load sanity results (10 concurr

Phase 2, timed — 55 minutes, templates allowed, transcript allowed, this week's finished examples NOT allowed. Produce in docs/sim1/: (1) requirements.md — all eight sections for Copperline; every FR traced to a transcri

Assemble everything into portfolio/fde-sim-2/ in your practice repo: 01-requirements.md, 02-proposal.md (with demo script), 03-objection-ciso.md, 04-objection-cfo.md, 05-change-request-response.md, and 06-self-grade.md.

Commit three artifacts: (1) 07-rewrite.md in the sim package with its diff notes and the habit line; (2) the triaged error log with every entry dispositioned and the ≤ 12-item DRILL list extracted to portfolio/interview-

Execute every D176-assigned punch-list item through the three passes: perimeter (auth on all routes verified by tests, rate limiting live, validation strict), honest failure (five-row failure table implemented and break-

Complete docs/quality-gates.md: six gates, each with pre-committed threshold, measured result, PASS/FAIL, and an evidence link (eval report file, attack log, trace IDs, load output, checklist, cost calc). Attach the rege

Finish the day with: production serving the v1.0 tag, verified by smoke tests and one live cited answer; all four documents finalized and cross-linked; open tickets visible and triaged in the tracker; demo rehearsed twic

Execute portfolio/launch-checklist.md today, checking items live: (1) Portfolio: capstone repo public with v1.0 tag, README cold-read-verified, demo video or screenshots linked; fde-sim-2 package and interview-prep folde