The Groundwork Guide.
The complete, open program: six standing orders, built in sequence. Fifteen documents, one Operator, one loop. Nothing gated, nothing held back.
Start here: your first 30 minutes Take the scorecard
Want it on paper? Download the Field Guide as PDF.
How this program runs
Groundwork is not a promise. It is a folder of files. You build fifteen plain-text documents in a fixed order, and those documents become the foundation any AI can stand on. The sequence is not optional, because each order depends on the one before it.
The first three orders come first: Know me, Know my information, Know your limits. Who you are, what the system may trust, and what it may do. These three alone improve output quality immediately, before you automate anything.
Order 4 activates one Operator. A single scoped agent. Not autonomous. Not a swarm. It drafts, cites authority, and stops when it should.
Orders 5 and 6 are the standing half: Remember and Improve. What survives failure, how you know it is working, and the rhythm that keeps it from decaying.
The rule: do not automate chaos. Most teams skip the foundation and go straight to agents. The result is generic output, invented policy, and systems that cannot tell doctrine from a draft. If your identity is unclear, your knowledge is unclassified, and your rules are unwritten, an agent will amplify the mess faster than you can catch it.
The build line, then the loop
Foundation install
Identity, Knowledge, and Limits. Ten files. Output quality and decision boundaries improve immediately, before a single agent exists.
First Operator live
The scope written as file eleven, then one governed agent running real work inside the foundation. Lock the scope, load the package, run real Draft & Wait work, and correct the documents from actual misses.
Built to last
Remember and Improve. Four documents and one loop (capture, understand, decide, act, verify, remember, improve) that make the foundation survive time, people, and drift.
The map of the guide
Eight parts, plus two notes. Read Foundations first, work the orders in sequence, activate the Operator at order four, then score yourself. Every part is open.
Foundations
Understand the machine you are feeding: the model, the agents, the instructions, and the data, all in plain language.
Outcome: the mental model. You know why context beats prompts and why the build order is not optional.
Order 1: Know me
Who you are and how you are allowed to behave. Charter, brand voice, and decision principles.
Outcome: a context file any AI can load, so output sounds like you and decisions follow your rules.
Order 2: Know my information
What the system is allowed to trust and use. Authority Classification, the Context Vault, priorities, and constraints.
Outcome: an AI that cites your files at the right authority level, not the internet's guesses.
Order 3: Know your limits
What the system is allowed to do. Auto-Execute, Draft & Wait, Never Automate, plus escalation rules and allowed tools.
Outcome: written rules a human signs off on, so automation stays inside boundaries you set.
Order 4: Help me operate
One scoped agent, activated only after the first three orders exist. The scope, the context package, the prompt, and the rules for adding roles later.
Outcome: a competent internal operator that drafts, cites authority, and stops when it should.
Order 5: Remember
What survives time, people, and failure. Succession rules, override authority, and working memory discipline.
Outcome: a foundation that survives the founder being gone for ninety days.
Order 6: Improve
Whether the foundation is actually working, and how it is maintained so it does not decay. The signals, the correction loop, ownership, cadence, and the update protocol.
Outcome: you know when it is working, and it stays that way: a living foundation, not a one-time build.
The Readiness Scorecard
A weighted self-assessment across all six orders. Runs entirely in your browser.
Outcome: a score, your weakest order named, and a clear answer to “what do I fix first?”
The Atlas story, the operator dashboard & the lineage
Three companion reads: what one finished foundation carries in production, the morning-screen pattern any owner can hold their own version to, and where the eighty-year-old idea behind Authority Classification comes from.
Outcome: proof the method holds weight, the pattern for your own screen, and the honest history of its sharpest tool.
What you have when it is done
- Fifteen plain-text documents that define who you are, what your system trusts, and what it may do. Yours, on your machine, readable by any AI.
- An AI that sounds like you. Output stays on-voice without re-prompting, because the voice is written down.
- Authority the system must cite. Five levels, 0–4, so a rumor and a contract are never treated as equal.
- One working Operator. A scoped agent running real Draft & Wait work with a human signing off where it matters.
- Platform independence. Markdown files work with Claude, ChatGPT, Gemini, or any future AI. No lock-in. Ever.
- A foundation that outlives you being busy, absent, or gone. Succession, override authority, and a review rhythm that keeps it honest.
What this costs
Nothing. The whole program is on this site and in the Field Guide PDF, free and ungated. No email required. No paywall. No locked chapters. If you want a second set of eyes, book the free Audit: sixty to ninety minutes mapping your current state and your biggest gaps. Questions: adam@adamabdalla.com.