Demo, CV, mock interviews and applications.

1.Try #40 Diameter of Binary Tree – untimed, AI-free

Trees · Easy. Aim for 15–20 minutes. No assistants, no autocomplete.

2.Stuck at 25 minutes? Use the NeetCode method

Read or watch the explanation, close it, then re-code the solution from memory.

3.Write the Big-O

Add a comment with the time and space complexity, and why.

4.Log it

Mark it Solved or Revisit, with minutes and whether you solved it unaided.

5.10 min revision

One item from reviews/relearn.md.

1.Try #41 Balanced Binary Tree – untimed, AI-free

Trees · Easy. Aim for 15–20 minutes. No assistants, no autocomplete.

2.Stuck at 25 minutes? Use the NeetCode method

Read or watch the explanation, close it, then re-code the solution from memory.

3.Write the Big-O

Add a comment with the time and space complexity, and why.

4.Log it

Mark it Solved or Revisit, with minutes and whether you solved it unaided.

5.10 min revision

One item from reviews/relearn.md.

1.Try #42 Lowest Common Ancestor of a BST – untimed, AI-free

Trees · Medium. Aim for 15–20 minutes. No assistants, no autocomplete.

2.Stuck at 25 minutes? Use the NeetCode method

Read or watch the explanation, close it, then re-code the solution from memory.

3.Write the Big-O

Add a comment with the time and space complexity, and why.

4.Log it

Mark it Solved or Revisit, with minutes and whether you solved it unaided.

5.10 min revision

One item from reviews/relearn.md.

1.Do

3-min QuickTime demo (problem → live question → citations → evals → cost); final READMEs.

2.Check you’re done

Done when: Video link in the README.

1.Work through: Section 6.2 checklists

CV and LinkedIn

2.Do

2-page UK CV; LinkedIn with P2/P5 featured.

3.Check you’re done

Done when: CV PDF saved.

1.Catch up first

Finish anything unticked from Mon–Fri this week before stretch work.

2.Then stretch work

GitHub profile README; pin 5 repos; send 2 thank-you/networking messages.

3.Level up: Vectors in Postgres (pgvector)

pgvector is a Postgres extension for vector similarity search. Search is exact by default; you add an index to trade a little recall for speed. One database then holds your documents, metadata, permissions and embeddings. Move P5’s chunks from Chroma into Postgres with pgvector, keep the same eval set, and compare hit@5 and latency. Done when: P5 runs from one Postgres database and the README compares it with the Chroma version.

1.Start with 20 min revision

Explain the P5 architecture in 3 minutes.

2.Work through: Hello Interview – Anthropic SWE guide

≈15 min

3.Work through: OpenAI – interview guide

≈15 min

4.Do

60-min progressive key-value store (4 levels); 1 LLM system design; 1 FDE decomposition; P2 and P5 deep dives; 6 STAR stories. Record and review.

5.Check you’re done

Done when: interview/self_review.md with 3 fixes per round.

6.Commit

interview/

1.Work through: Section 6.3 – where UK AI roles are posted

2.Work through: Section 6.5 – after Week 21

3.Do

Shortlist 15 roles; tailor the CV for 3; submit 3–5 applications; draft 5 referral messages; final retrospective.

4.Check you’re done

Done when: career/tracker.csv has 15 roles and 3–5 applications.

5.Commit

career/, reviews/final.md

6.Weekly review (last 30 min)

3 wins, 3 confusions, 1 thing to re-learn – written at the bottom of this page and saved with your progress.