InfoWok
Categories
AI EngineeringSoftware ArchitectureTech Career Growth
HomeGuidesAuthorsAboutContact
AI Engineering · for senior software engineers

Where senior engineers learn to build with AI — at the depth the job actually demands.

61 guides · real Python · no toy examplesBrowse all guides →
// Choose your path

Two Python-agent series. They’re not a choice — they’re a sequence.

Start with Foundations if you’re new — build an agent by hand, no framework. Move to Production once the basics click. Pick by where you are right now.

1Level 1Foundations — build it by hand
2Level 2Production — ship a real one
★ Start here
01Beginner · Foundations

AI Agents from Scratch in Python

Build a working agent with nothing but Python and one LLM call — no frameworks, so you actually understand the loop.

Start here if you…
are new to agents, or want to know how one actually works before reaching for a framework.
Length
6 parts (00–05)
Approach
Pure Python + a raw LLM call
Prereq
Can read basic Python (Part 0 teaches it)
You'll build
Your own agent loop — tools, reasoning, memory — by hand
Start Part 00 — Python basics →
02Intermediate · Production

Agentic AI in Python: Zero to Production

Take a real agent all the way to a deployed, observable service using LangGraph — state, tools, memory, and shipping.

Start here if you…
already get the basics (or finished Level 1) and want to ship something production-grade.
Length
7 parts (01–07)
Approach
LangGraph + deploy & observability
Prereq
Comfortable with agent fundamentals
You'll build
A real agentic app, deployed as an observable service
Start Part 01 — first build →
Software Architecture

Design systems that hold up

All 7 guides →
Guide · 5 minAgent Orchestration Patterns: A 2026 GuideThe five agent orchestration patterns (supervisor, hierarchical, sequential, parallel, swarm), why the supervisor wins in 2026, what multi-agent really costs, and when a single agent was the right call all along.Navmeet Kaur · Jun 26, 2026Guide · 4 minHuman-in-the-Loop Architecture: A 2026 GuideHuman-in-the-loop architecture decides what an agent does alone and what a person approves. The patterns, how to pause without blocking, the approval-fatigue trap, and where to put the human.Navmeet Kaur · Jun 26, 2026Guide · 4 minLong-Running AI Workflows: A 2026 GuideLong-running AI workflows can't live in a request/response. How durable execution checkpoints and resumes instead of restarting, why every side effect needs an idempotency key, event-driven triggers, and when a plain call is enough.Navmeet Kaur · Jun 26, 2026Guide · 5 minAI Agent Memory Architecture: A 2026 GuideAI agent memory is the storage tier behind the context window. The three long-term types (episodic, semantic, procedural), the write-recall-forget lifecycle, where it breaks, and when an agent needs no memory at all.Navmeet Kaur · Jun 25, 2026

One email when something good ships

New guides across every category. No digest spam, unsubscribe anytime.

InfoWok
Where senior software engineers learn AI Engineering.
Hands-on guides to agents, RAG, and MCP servers in real Python — with the architecture and career depth to ship them in production.
Sections
AI EngineeringSoftware ArchitectureTech Career Growth
Publication
AboutEditorial standardsAuthorsContact
Subscribe
SeriesAll guidesRSS feed
© 2026 InfoWokIndependent · no sponsored reviews · code-first