Settings
← Back to Development Overview

AI Systems & LLMs

Intermediate

Building agentic systems with large language models

Why This Skill Matters Now

AI Systems knowledge is the foundational skill for building My42's agent-based architecture. The product depends on multi-agent coordination, tool use patterns, and prompt engineering to deliver personalized life management insights.

Linked Goals: "Launch My42 MVP" (requires agent implementations), "Build AI expertise" (long-term career investment)

Linked Sprints: Launch Sprint (9/30 days elapsed) — AI Systems skill directly unblocking feature development

Learning Log (Recent Sessions)

Yesterday, 9:00am

Read

Anthropic tool use documentation — studied structured output patterns for agent function calling. Focus: reliability + error handling.

3 days ago, 2:00pm

Practice

Hands-on: built prototype multi-agent system (coordinator + 3 specialist agents). Tested message passing and state coordination. Worked.

5 days ago, 10:30am

Watch

Watched Andrej Karpathy talk on LLM agents (40min). Key takeaway: agents need clear tool boundaries to avoid context overflow. Applied to My42 design.

1 week ago, 9:00am

Read

OpenAI cookbook: agent memory patterns. Studied short-term vs long-term memory trade-offs. Relevant for My42 user context management.

1 week ago, 3:00pm

Practice

Implemented prompt chaining pattern for My42 insight generation. Agent 1 (data) → Agent 2 (analysis) → Agent 3 (recommendation). Reduced hallucination.

Output Log (Shipped Artifacts)

Agent Coordinator Implementation

Shipped yesterday to My42 production

Built multi-agent coordinator using Anthropic Claude. Handles tool use, state management, error recovery. Powers My42 insight generation pipeline. 340 LOC, tested, deployed.

Prompt Engineering Guide (Blog Post)

Published 4 days ago on personal blog + YouTube

1,800-word guide on prompt patterns for reliable agent behavior. Based on My42 learnings. 2.4k views, positive feedback. Positioned as AI systems expert.

Tool Use Pattern Library

Shipped 1 week ago to My42 codebase

Reusable TypeScript utilities for LLM tool calling. Handles validation, error boundaries, retry logic. Reduced agent implementation time by 60%. Open-sourced on GitHub (12 stars).

Progress Signals (What Indicates Growth)

1. Implementation Speed

Time from concept → working agent decreasing. Started: 3-4 days per agent. Now: 4-6 hours. Patterns internalized.

2. Debugging Intuition

Recognizing agent failure modes immediately. Example: seeing "context overflow" symptoms → know to refactor tool boundaries. Pattern recognition developing.

3. Teaching Ability

Writing coherent explanations of complex agent patterns (blog posts, docs). If you can teach it clearly, you've internalized it. Positive feedback loop: teach → learn deeper.

4. Design Confidence

Making architectural decisions without constant reference checking. Example: choosing prompt chaining over single-shot for complex tasks. Judgment improving.

Current Level Assessment: Intermediate

Can build production agents independently. Understand trade-offs. Still learning edge cases (multi-turn conversations, complex state management). Path to Advanced: ship 10+ agents, handle real user scale issues.

Suggested Next Actions

Study: Multi-agent orchestration patterns

Deep dive on agent-to-agent communication protocols. Read: LangChain multi-agent docs + AutoGPT architecture. Time: 1h. Goal: understand coordination patterns for My42's 5-agent system.

Apply: Build conversation memory agent

Implement persistent memory layer for My42 user conversations. Use embeddings + vector DB for context retrieval. Time: 4h. Output: working memory agent + blog post on implementation.

Teach: Record "Building AI Agents" video tutorial

Create YouTube tutorial covering agent basics → My42 case study. Time: 2h (script + record). Output: 15min video. Goal: solidify knowledge through teaching + build audience.

← Back to Development Overview