PGM-AUA V1.0 AIMs - Prompt Token Analyser

Go to PGM-AUA V1.0 AI Modules

Function

Ref. Model

1. Function

The Prompt Token Analyser (PGM‑PTA) AIM parses the Text Object and Context Descriptors received from the environment into a Meaning structure carrying the results of part-of-speech tagging, named entity tagging, dependency structure analysis, and semantic role labelling. It queries A‑User Storage via PRC IH to retrieve relevant past interaction context that may inform tokenisation and entity recognition.

PGM‑PTA does not infer intent, resolve referents, or produce goal or expressive configurations. It establishes what was said and how it was structured, and leaves interpretation to the downstream Sub-AIMs of Prompt Creation.

2. Reference Model

Figure 1 depicts the Reference Model of the Prompt Token Analyser (PGM‑PTA) AIM.

Figure 1 – The Prompt Token Analyser (PGM‑PTA) AIM

3. Input/Output Data

Table 1 specifies the Input and Output Data of the Prompt Token Analyser (PGM‑PTA) AIM.

Table 1 – I/O Data of the Prompt Token Analyser (PGM‑PTA) AIM

Input	Description
Text Object	Text input received from the environment representing the User’s utterance or query.
Context Descriptors	Structured descriptors of the current interaction context produced by Context Description, providing domain and situational framing for tokenisation and entity recognition.
PRC Directive	Directive from A‑User Control specifying scope, depth, and policy constraints for prompt construction.
PRC IH Response	Interaction History response from A‑User Storage providing relevant past interaction context to inform tokenisation and named entity recognition.
Output	Description
Meaning	Structured linguistic analysis of the Text Object carrying part-of-speech tagging, named entity tagging, dependency structure, and semantic role labelling results.
PRC Status	Status signal reporting the processing outcome of the AIM.
PRC IH Request	Request for Interaction History issued to A‑User Storage.

4. Sub-AIMs

No Sub-AIMs.

5. JSON Metadata

https://schemas.mpai.community/PGM1/V1.0/AIMs/PromptTokenAnalyser.json

6. Profiles

No Profiles.

7. Reference Software

Not part of this specification.

8. Conformance Testing

Table 2 provides the Conformance Testing Method for the Prompt Token Analyser (PGM‑PTA) AIM.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present, and conform with the Qualifier, if present.

Table 2 – Conformance Testing Method for the Prompt Token Analyser (PGM‑PTA) AIM

Receives	Text Object	Shall validate against the Text Object schema. Text Data shall conform with the Text Qualifier.
	Context Descriptors	Shall validate against the Context Descriptors schema.
	PRC Directive	Shall validate against the PRC Directive schema.
	PRC IH Response	Shall validate against the PRC IH schema.
Produces	Meaning	Shall validate against the Meaning schema.
	PRC Status	Shall validate against the PRC Status schema.
	PRC IH Request	Shall validate against the PRC IH schema.

9. Performance Assessment