Less than 15 minutes

Learn GALEN

Three layers. Start with readable GALEN โ€” works with any AI immediately. Then learn compact GALEN for advanced use.

THE 3-LAYER ARCHITECTURE
INTENT
MANDATORY
:
SUBJECT
MANDATORY
MODIFIER
OPTIONAL
INTENT
Single uppercase letter โ€” what do you want? Optionally followed by a dot sub-type.
G.email
"Generate an email"
SUBJECT
After the colon โ€” what is it about or who is it for?
G.email: @finance
"Write an email to the finance department."
MODIFIER
After the subject โ€” adjust target, length, value, reference, and output format
G.email: @finance angle=compliance -length >txt
"Write a brief plain text email to the finance department about compliance"
Only INTENT and SUBJECT are mandatory ยท MODIFIER is optional ยท Add as much or as little as you need
01 ยท INTENT ยท separators 02 ยท SUBJECT 03 ยท MODIFIER ยท applying GALEN
Use GALEN without a system prompt Start with readable GALEN using ordinary words. Most AI systems understand this immediately. Then gradually shorten it into compact GALEN for advanced use.
Part One

Readable GALEN

Learn GALEN first using normal words. Works with any AI immediately โ€” no system prompt needed.

Start with Readable GALEN

Readable GALEN uses normal words instead of shorthand symbols, so any AI understands it without a special system prompt. Same 3-layer structure โ€” just full words instead of compact tokens.

1 ยท Intent

Use a full word: Generate, Query, Explain, Summarise.

2 ยท Subject

After the colon, write the main topic or recipient: email, invoice.risks, recipient=finance.

3 ยท Modifier

Add words after the subject: angle=compliance, short, text, list.

Same structure

Readable GALEN still follows the same 3-layer pattern. Later you structure full words into compact machine-readable instructions.

Natural English Write a brief plain text email to the finance department about compliance.
โ†“ convert into readable GALEN
Readable GALEN Generate.email: recipient=finance angle=compliance short text
โ†“ structure into compact GALEN instruction
G.email: @finance angle=compliance -length >txt
Readable wordCompact GALENMeaning
GenerateGCreate something
QueryQAsk for information
recipient=finance@financeWho the output is for
short-lengthMake it shorter
text>txtPlain text output

Once comfortable with readable GALEN, continue to Part Two and learn the compact tokens.

Part Two

Compact GALEN

Now learn the compact shorthand. Requires a system prompt pasted into your AI before use.

Step 01

INTENT

Every GALEN statement begins with a single uppercase letter โ€” the intent token. It tells the machine exactly what you want before it reads anything else. There are 7 intent tokens in GALEN Core.

TokenMeaning and Example
Q Q โ€” QUERY (Ask for information) Q: invoice.followup.outcomes "What are the outcomes of the invoice follow-up process?"
G G โ€” GENERATE (Create something new) G.email: @finance "Write an email to the finance department."
E E โ€” EXPLAIN (Educate or clarify) E: market.volatility "Explain what causes market volatility."
S S โ€” SUMMARISE (Compress existing content) S: #prev "Can you summarise the last response?"
D D โ€” DATA (Enter structured information) G.workflow: overdue.invoice.followup @customers +crm +notify.finance angle=compliance >step "Execute the invoice follow-up workflow for all customers, create CRM reminders, and notify finance, focused on compliance, as step-by-step instructions."
C C โ€” COMMAND (Instruct an action) C: analyse.data "Please analyse this data."
R R โ€” REVISE (Modify a previous response) R: #prev -length "Can you revise the last response and make it shorter?"
Exercise 1.1
"What are the key clauses in an employment contract?"
Which intent token fits? You want information.
Q: employment.contract.clauses
"What are the key clauses in an employment contract?"
Q = QUERY. You are asking for information.
Exercise 1.2
"Write me a report on quarterly outcomes."
Which intent token fits? You want something created.
G.report: quarterly.outcomes
"Write a report on quarterly outcomes."
G = GENERATE. The dot and colon are explained in the next section.
Next โ€” separators โ†’

separators

Two symbols connect the three layers. Both follow INTENT โ€” the colon is mandatory, the dot is optional.

The colon : โ€” mandatory

Always follows INTENT. Separates INTENT from SUBJECT. Every GALEN statement has one.

Q: invoice.followup.outcomes
"What are the outcomes of the invoice follow-up process?"
E: market.volatility
"Explain what causes market volatility."
The dot . โ€” optional

Sits between INTENT and the colon. Adds a sub-type โ€” what kind of output you want.

G.email: @finance
"Write an email to the finance department."
G.report: outcomes
"Generate a report on outcomes."
G.workflow: invoice.followup
"Execute the invoice follow-up workflow."
The full pattern so far

INTENT.subtype: SUBJECT โ€” the colon always present, the dot only when you want to specify the output type

Next โ€” SUBJECT โ†’
Step 02

SUBJECT

The SUBJECT comes after the colon. It is the core noun or concept โ€” stripped of all unnecessary words. Three structuring rules only.

RuleInstead ofWrite
Drop articlesthe customer ยท a report ยท an outcomecustomer ยท report ยท outcome
Join compounds with a dotrate of return ยท invoice settlementreturn.rate ยท invoice.settlement
Drop hedge wordscould you ยท perhaps ยท I think ยท please(remove entirely)
E: GLP1.mechanism
"Can you explain how GLP-1 receptor agonists work?"
Q: investment.property.risks
"What are the risks of a commercial property investment?"
Exercise 2.1
"Please explain what causes market volatility in financial markets."
Drop "please" and "what...means" โ€” the E token already says that
E: market.volatility.causes
"Explain the causes of market volatility."
E = EXPLAIN ยท drop hedge words ยท join concept with dots.
Exercise 2.2
"Can you summarise the key risks of a commercial property investment?"
S intent ยท structure the subject into dot-joined phrase
S: commercial.property.investment.risks
"Summarise the key risks of a commercial property investment."
S = SUMMARISE ยท "commercial property investment" โ†’ commercial.property.investment ยท "risks" โ†’ risks.
Next โ€” MODIFIER โ†’
Step 03

MODIFIER

MODIFIERS sit after the SUBJECT separated by a space. They adjust the output โ€” who it is for, how long it should be, what angle to take, what to reference, and what format to use. There are 10 core modifiers in two groups.

5 Adjustment Symbols

SymbolMeaning and Example
@ @ โ€” TARGET (Who the output is directed at) G.email: @finance "Write an email to the finance department."
+ + โ€” MORE (Increase detail, length or depth) E: inflation.mechanism +detail "Explain inflation mechanism in detail."
โˆ’ โˆ’ โ€” LESS (Reduce length or complexity) G.email: @finance -length "Write a brief email to the finance department."
= = โ€” VALUE (Assign a specific value or angle) G.email: @finance angle=compliance "Write an email to the finance department focused on compliance."
# # โ€” REFERENCE (Point to a previous response) S: #prev ยท R: #prev3 "Summarise the last response." ยท "Revise the last three."

5 Format Tokens โ€” always placed last

TokenMeaning and Example
>txt >txt โ€” TEXT (Plain prose output) G.email: @finance >txt "Write an email to the finance department as plain readable text."
>list >list โ€” LIST (Bullet point output) Q: employment.contract.clauses >list "What are the key clauses in an employment contract โ€” as a list."
>brief >brief โ€” BRIEF (3 to 5 sentences maximum) S: #prev >brief "Summarise the last response in a few sentences."
>full >full โ€” FULL (Comprehensive detailed response) E: market.volatility >full "Explain market volatility comprehensively."
>step >step โ€” STEPS (Numbered step-by-step output) E: 2FA.setup >step "Explain two-factor authentication setup as numbered steps."
Complete Pattern

INTENT.subtype: SUBJECT @TARGET =VALUE +/- #ref >FORMAT

G.email: @finance angle=compliance -length >txt
"Write a brief plain text email to the finance department focused on compliance."
Exercise 3.1 โ€” Full statement
"Write a brief plain text email to the finance department focused on compliance."
G ยท .email ยท @target ยท =value ยท -length ยท >txt
G.email: @finance angle=compliance -length >txt
"Write a brief plain text email to the finance department focused on compliance."
G = INTENT ยท .email = sub-type ยท @finance = TARGET ยท angle=compliance = VALUE ยท -length = LESS ยท >txt = FORMAT. All 3 layers used together.
Exercise 3.2
"Summarise the last three responses as a bullet list."
S intent ยท # reference with number ยท >list format
S: #prev3 >list
"Summarise the last three responses as a bullet list."
S = SUMMARISE ยท #prev3 = last three responses ยท >list = bullet output.
Exercise 3.3 โ€” Patient data
"Summarise the key risks of a commercial property investment for management."
D intent ยท .med domain ยท | separates groups ยท = assigns values
S: commercial.property.investment.risks +management.summary >brief
"Write a brief report on last month's customer complaints, highlighting the top three issues, with a management summary."
G = INTENT ยท .report = sub-type ยท +top3 = scope ยท +management.summary = additional output ยท >brief = FORMAT.
โœ“ Complete

You now know all three layers โ€” INTENT ยท SUBJECT ยท MODIFIER. Use the reference card below any time.

Try the Converter โ†’ Reference Card
Bringing it together

Readable โ†’ Compact GALEN

Here is how readable GALEN structures into compact GALEN instructions.

Natural English
Write a brief plain text email to the finance department about compliance
โ†“ readable GALEN
Readable GALEN
Generate.email: recipient=finance angle=compliance short text
โ†“ compact GALEN
Compact GALEN
G.email: @finance angle=compliance -length >txt
Readable GALENCompact GALEN
GenerateG
recipient=finance@finance
short-length
simple-complexity
text>txt
list>list
previous3#prev3
Example
Summarise: previous3 list
โ†“
S: #prev3 >list
Example
Explain: market.volatility simple
โ†“
E: market.volatility -complexity
After the 3 Steps

How to use GALEN with any AI

Every AI conversation starts fresh. Before sending GALEN statements to ChatGPT, Claude, Gemini, or any other AI โ€” paste the system prompt below as your very first message. It tells the AI what GALEN means. You only need to do this once per session.

Step 1

Copy the system prompt below โ€” click the Copy button

Step 2

Open your AI โ€” ChatGPT, Claude, Gemini, or any other โ€” and paste it as your first message

Step 3

Now type your GALEN statements โ€” the AI will understand every one correctly

GALEN System Prompt โ€” copy and paste into your AI
You are a GALEN-aware AI assistant. GALEN is a compact structured language for human-to-AI communication.

GALEN uses 3 layers:
INTENT: SUBJECT MODIFIER

INTENT tokens:
Q โ€” Query (ask for information)
G โ€” Generate (create content)
E โ€” Explain (educate or clarify)
S โ€” Summarise (condense content)
D โ€” Data (structured data input)
C โ€” Command (instruct an action)
R โ€” Revise (modify previous output)

INTENT can have a dot sub-type: G.email G.report D.med D.fin

SUBJECT: Core noun after the colon. Articles and hedge words removed. Compound concepts joined with dots.

MODIFIERS (after subject, space separated):
@ โ€” target recipient e.g. @finance @hospital-director
+ โ€” more/increase e.g. +detail
- โ€” less/decrease e.g. -length -complexity
= โ€” value assignment e.g. angle=compliance tone=formal
# โ€” reference previous e.g. #prev #prev3
>txt >list >brief >full >step โ€” output format (always last)

Data input uses pipe separator:
G.workflow: overdue.invoice.followup @customers +crm +notify.finance angle=compliance >step

Examples:
G.email: @finance angle=compliance -length >txt
โ†’ Write a brief plain text email to the finance department focused on compliance

Q: invoice.followup.outcomes >brief
โ†’ Summarise the key investment risks briefly

S: #prev3 >list
โ†’ Summarise the last three responses as a bullet list

When you receive a GALEN statement, interpret it correctly and respond accordingly. Do not ask for clarification โ€” act on the GALEN instruction directly.

Alternatively use the GALEN Converter โ€” it already has the system prompt built in.

GALEN Core โ€” Quick Reference Card
INTENT โ€” 7 tokens
Q QUERY G GENERATE E EXPLAIN S SUMMARISE D DATA C COMMAND R REVISE
INTENT.subtype: SUBJECT
MODIFIER โ€” 10 tokens
@ TARGET + MORE โˆ’ LESS = VALUE # REFERENCE >txt >list >brief >full >step
SUBJECT โ€” structuring rules
Drop: the ยท a ยท an ยท is ยท are ยท please ยท could you
Join: invoice.followup.status ยท investment.risk.summary
Full pattern
INTENT.subtype: SUBJECT @target =value +/- #ref >format
G.workflow: overdue.invoice.followup @customers +crm angle=compliance >step
Ready to practise?
Type plain English into the converter and see GALEN output instantly.
Open Converter โ†’ Full Specification

Want to go deeper?

Full Reference Guide โ€” The complete GALEN technical reference โ†’