Week 12 — Protocols, memory, vendor SDKs (light) — interview-3¶
At a glance
Phase 3: Agents + Protocols · Starts: Mon 14 Dec 2026 · Planned: 11h 00m · Light week
Build: Capstone: A2A/AG-UI spike + Mem0 memory prototype + vendor SDK comparison notes
Interview checkpoint: interview-3
Run the full mock loop and score it with the rubric.
By day¶
Monday 14 Dec · 1h 20m¶
- System Design · 30 min · Distributed job scheduler write-up review; data pipeline for trace → eval dataset → Batch & stream data pipelines
w12-sd-1 - DSA · 15 min · Permutations + Subsets II → Backtracking · resource
w12-dsa-1 - Python · 15 min · Rep: Protocol + generics for a typed Memory store interface → Advanced typing: generics, Protocols, ParamSpec, TypedDict · resource
w12-py-1 - Communication · 20 min · Grammar: Linking words and cohesion → Week 12 drills · day 1
w12-comm-1
Tuesday 15 Dec · 1h 20m¶
- Agentic AI · 40 min · A2A v1.0 (signed Agent Cards, JSON-RPC/gRPC/REST) + AG-UI event stream — where each fits next to MCP → A2A & AG-UI protocols · resource
w12-ai-1 - DSA · 20 min · Combination Sum II → Backtracking · resource
w12-dsa-2 - Communication · 20 min · Vocabulary: Review, spaced repetition round → Week 12 drills · day 2
w12-comm-2
Wednesday 16 Dec · 1h 20m¶
- DSA · 15 min · Word Search → Backtracking · resource
w12-dsa-3 - Architecture · 30 min · API contracts & schema evolution: backward/forward compatibility, consumer-driven contracts, versioning MCP tool schemas → API contracts, versioning & schema evolution
w12-arch-1 - Python · 15 min · Rep: getattr/slots trade-offs on high-volume event objects → Python data model & dunder protocols
w12-py-2 - Communication · 20 min · Speaking drill: Shadowing practice 2 → Week 12 drills · day 3
w12-comm-3
Thursday 17 Dec · 1h 20m¶
- Agentic AI · 40 min · Vendor SDK tour: Claude Agent SDK, OpenAI Agents SDK, Google ADK 2.0, MS Agent Framework 1.0 — same toy task in 2 of them, compare → Vendor agent SDKs: Claude Agent SDK, OpenAI Agents SDK, Google ADK, MS Agent Framework · resource
w12-ai-2 - Java/Spring AI · 20 min · Spring AI agent with ChatMemory + tool calling + MCP client end-to-end → Agentic patterns with Spring AI
w12-java-1 - Communication · 20 min · Idioms & phrasal verbs: Idiom review round → Week 12 drills · day 4
w12-comm-4
Friday 18 Dec · 1h 15m¶
- System Design · 30 min · Kafka vs Pulsar vs SQS/Service Bus decision table → Message queues & streaming (Kafka)
w12-sd-2 - DSA · 15 min · Palindrome Partitioning → Backtracking · resource
w12-dsa-4 - Python · 10 min · Rep: functools.wraps, cache, singledispatch in a tool registry → Decorators, descriptors & metaclasses
w12-py-3 - Communication · 20 min · Writing: Executive summaries → Week 12 drills · day 5
w12-comm-5
Saturday 19 Dec · 2h 15m¶
- Agentic AI · 75 min · Capstone build: add Mem0 (or Letta) long-term memory for per-team preferences; expose the orchestrator via AG-UI events to a minimal UI → Agent memory systems (Mem0, Letta, Zep) · resource
w12-ai-3 - DSA · 20 min · Timed coding mock (interview-3): Number of Islands + Clone Graph in 30 min → Graphs: BFS, DFS, topological sort, union-find · resource
w12-dsa-5 - Java/Spring AI · 20 min · Evaluate where Spring AI agent patterns are enough vs needing LangGraph → Agentic patterns with Spring AI
w12-java-2 - Communication · 20 min · Record & shadow: Shadowing practice 2 → Week 12 drills · day 6
w12-comm-6
Sunday 20 Dec · 2h 10m¶
- System Design · 30 min · Timed 45-min AI SD mock (interview-3): design a ChatGPT-style assistant (sessions, memory, tools, streaming, safety, cost) → Design a ChatGPT-style assistant
w12-sd-3 - Architecture · 20 min · Write ADR 012 for capstone: tool schema versioning policy (additive changes, deprecation window) → API contracts, versioning & schema evolution · resource
w12-arch-2 - Staff+ · 20 min · Read an incident-command model; note how you'd lead a Sev-1 involving an AI agent misbehaving → Incident leadership & blameless postmortems
w12-staff-1 - Communication · 20 min · Soft skills + weekly review: Cross-cultural communication — checkpoint comm-3: re-record and compare against the baseline rubric → Week 12 drills · day 7
w12-comm-7 - Review · 40 min · interview-3: full mock — SD + coding + AI SD + behavioral, score with the unified interview rubric and log gaps into next week's plan → Interview framework & back-of-envelope estimation
w12-rev-1
By track¶
| Track | Tasks | Time |
|---|---|---|
| Agentic AI | 3 | 2h 35m |
| System Design | 3 | 1h 30m |
| DSA | 5 | 1h 25m |
| Architecture | 2 | 50m |
| Python | 3 | 40m |
| Java/Spring AI | 2 | 40m |
| Staff+ | 1 | 20m |
| Communication | 7 | 2h 20m |
| Review | 1 | 40m |
End-of-week¶
- Weekly retro written in
docs/log/retros/(template: retro) - Flashcards / explain-it-back done for this week's topics
- Progress synced (close the daily GitHub issues)