Codez
@0xCodez

Content creator | AI researcher & builder | AI insights from 2030 | @beyond_xai

 San Francisco
Based in Ukraine
substack.com/@0xmovez
Joined May 2026
153 Photos and videos
Article

How to Build a team of AI Agents that actually work together in 8 Steps (Full-course)

Most people who say they run a team of AI agents run five chat windows. Same model, five tabs, and one human copy-pasting context between them. That number is real: across Raft’s beta, more than

13
63
366
766,019
Article

Grok Bot Agents: how to automate your life in 10 Steps (Full-tutorial)

Every AI tool you have used so far waits for you. You open it, you ask, it answers, you close it. The work still happens in your hands - the model just talks you through it. Follow my Substack to get

97
372
3,057
6,502,255
Article

AI Agent Engineer in 2026: 12 steps roadmap - Loops, Graphs, Evals, Context, Harness (Full-Course)

This is the complete 12-step roadmap through the seven pillars that actually decide whether an agent works: context, tools, memory, loops, graphs, harness, evals - each with the Claude workflow that

20
81
509
78,015
Article

How to become a Forward Deployed Engineer in 10 Steps: $785K / year (full-course)

Forward Deployed Engineer went from a Palantir curiosity to the most-recruited role in AI in twelve months - postings up 729%. This is the 10-step roadmap into it: what the job actually is, the stack

39
126
975
418,286
Article

Context Engineering with Claude: 14-step roadmap from 0 to context architect ( Full-course )

Most people who try to make Claude behave end up writing a longer file. Every surprise becomes a new rule, every rule a new line, until CLAUDE.md is a thousand-line rulebook nobody has read end to end

17
16
150
88,246
Article

Graph Engineering with Claude: 14-Step roadmap from 0 to graph architect (Full Course)

Most people who try to build a multi-step agent end up with a straight line. Step one, step two, step three - each waiting politely for the last to finish before it starts. 9/10 notice that half those

127
798
4,562
7,628,224
Article

Agent harness engineering with Claude: 14-step roadmap from one agent to a self-improving system.

Everyone’s talking about loops. Almost no one is talking about what the loop runs on. 9 out of 10 builders run Claude Code on the default harness - no rules, no subagents, no hooks, no memory. Then

27
118
770
219,504
Article

Build self-improving agent system with Fable 5 in 14 steps : loops, dynamic workflows, routines

Most people are using Claude Fable 5 like Sonnet 4.6 with a bigger context window. They prompt it. It works for 5 minutes. They close the tab. 9 out of 10 users have never run an agent system that

65
439
2,658
6,836,038
Article

Loop engineering: the 14-step roadmap from prompter to loop designer.

Most developers still prompt their coding agents by hand. They type, they wait, they read the diff, they type again. 9out of 10 builders have never written a single loop that prompts the agent for

151
1,229
7,576
9,838,040
Article

How to run Claude on autopilot in 14 steps: /loop, Routines, and the full automation stack.

You’re paying $20–$200/month for Claude and using it like a paid version of ChatGPT. 9 out of 10 users have never set up automation that runs without them clicking buttons. No /loop, no scheduled

42
89
736
1,223,037
Article

How to master Dynamic Workflows in Claude Code: 6 patterns and 14 steps Anthropic engineers actually

Most Claude Code users still write their workflows by hand. They chain prompts, copy outputs, paste them into the next prompt, fix what went wrong, repeat. 9 out of 10 builders haven’t tried Dynamic

42
176
1,274
2,283,869
Article

Master 97% of Codex in 30 Minutes (Full Course)

Most people open Codex, see the chat window, and treat it like ChatGPT with a fancier sidebar. 9 out of 10 users miss 97% of what it actually does. They don’t build Skills, don’t deploy to live URLs,

5
7
70
30,261
Load more