🌙 Lesson 10 of 11 · 04:22:29 → 04:50:54

Codex Daemons & Overnight Crons

The context triad, agent archetypes, and work that happens overnight.

What you'll learn

  • Balance the context triad and pick the right agent archetype
  • Run Codex daemons as overnight emulated crons
  • Coordinate agents through natural-language loose coupling

In a nutshell

The context triad, agent archetypes, and work that happens overnight.

A richer, curated recap and references for this lesson are being prepared.

Key concepts

Context Triad
Agent Archetypes
Codex Demons
Overnight Emulated Crons
Natural Language Loose Coupling

Make it stick

Interactive exercises, a quiz, and hands-on challenges for this lesson are being prepared.

Moments worth pausing on

Screens captured from this part of the workshop — click any to open full size.

Terminal mapping execution output directly to a data log file ta
Text overview tracking the interaction loops between oracle pack
Core listing on screen breaking down the verification triad elem
Code surface overview detailing screenpipe setup logic and opera
Editor display outlining production goal text documents placed i
Ui panel showcasing image based design debugging instructions
Automation script rendering showcasing multi hour task loops ini
Terminal text showing connection flags routed to local infrastru

Questions from the room

assuming convex improvement in intelligence, Are you saving prototypes/ideas/convos/second-brain now, so future smarter models and better tools can synthesize and build them later? or are you planning for future in any way?Tyler Newman
not separately captured; see chunk final reconciliation.
What are your thoughts on learning new skills. How do you use AI to either accelerate it or optimize for something else? Irosa
not separately captured; see chunk final reconciliation.
do you use agents.md or claude.md, guardrails.md...? don't do this... tool usage specificity... etcTyler Newman
not separately captured; see chunk final reconciliation.
can you give some examples on how you prompt /goal?Jan
not separately captured; see chunk final reconciliation.
Any thoughts on security. For example this minimum package age setting in pnpm seems to be an idea people are converging on.rosa
not separately captured; see chunk final reconciliation.
in your view, what does a practical AI SDLC look like for a real engineering team, from requirements and design through implementation, testing, deployment, and maintenance?Artyom
not separately captured; see chunk final reconciliation.
are you using only agent-browser or also playwright?Jan
not separately captured; see chunk final reconciliation.
Did you show a /goal example for the packx ? For example I think I will convert 400 of my tests to QA or packages that are stable.rosa
not separately captured; see chunk final reconciliation.
so most of the time in /goal you don't define how the agent can check if the goal is achieved, correct?Jan
not separately captured; see chunk final reconciliation.