Tanaga Poetic Agent

The Agent

System Architecture The agent is powered by a FastAPI backend that manages asynchronous requests to the Ministral 14B Reasoning model. It utilizes a custom Prosodic Constraint Engine to audit syllabic density and rhyme schemes in real-time. To ensure the secure handling of creative data, the system implements a local Regex-based PII Scrubber that redacts sensitive identifiers before the data is processed by the model.

Architect’s Note on Syllabic Veracity This agent utilizes the Ministral 14B Reasoning engine. While it is programmed with strict syllabic anchoring ($7-7-7-7$ for Tagalog), users may notice occasional discrepancies. This is due to a known constraint in AI tokenization, where models process characters as data chunks rather than vocalized phonemes. This tool is intended as a collaborative partner for poetic inspiration rather than a definitive mathematical authority.

Methodology: The Prosodic Constraint Engine

The Tanaga Poetic Agent utilizes a Syllabic Counting & Rhyme-Scheme Protocol designed to honor traditional Tagalog roots while accommodating modern English adaptations through a "Phonetic-First" logic.

• Bimodal Syllabic Mapping & Anchoring: The engine dynamically detects input language to shift its architectural "anchors." For Tagalog, it targets the traditional 7-7-7-7 structure; for English, it adapts to an 8-8-8-8 structure. This process uses Language-Logic Anchoring, in which the model internally aligns the theme in its strongest reasoning language before generating the verse in the target language.

• Staccato-Phonetic Guardrails: To mitigate "Tokenization Hallucination," the engine enforces a strict 3-syllable word ceiling. By prioritizing staccato words over complex multi-syllabic tokens, the system forces the AI to process the verse in smaller, more mathematically predictable units.

• Rhyme-Scheme Synthesis: The system performs a real-time audit of terminal phonemes. It is designed to maintain integrity across AAAA (traditional monorhyme) and AABB (modern) schemes, ensuring that the phonetic "echo" remains consistent with the chosen structure.

• Talinghaga Integration: Following the pre-colonial tradition, the engine prioritizes the "Talinghaga" (metaphor). The system is prompted to treat the physical subject not as a literal description, but as a vehicle for emotional truth, ensuring the "soul" of the poem is preserved even when the AI faces structural challenges.

Technical Note on Resources

Tagalog prosody and the global evolution of the Tanaga are often underrepresented in Western literary databases. Verifying the historical shift from 7-syllable to 8-syllable structures requires access to specialized linguistic and cultural archives.

The Solution: This agent implements User Search Sovereignty via a Search-Path Protocol. Every poem concludes with a "Relevant Resources & Cultural Context" button. The system intercepts synthesized keywords and allows the user to dynamically redirect them into specialized archives, such as The National Library of the Philippines or the Komisyon sa Wikang Filipino (KWF). This ensures that users can verify the ancient roots and modern adaptations of the form against primary sources.

Prompt Guide for High-Value Results

To generate the most evocative and structurally sound poetry, use prompts that specify your desired linguistic and structural constraints:

• The "English Adaptation" Prompt: "Compose an English Tanaga using the 8-8-8-8 structure about 'Shadows' (Anino), focusing on a traditional AAAA rhyme scheme."

• The "Traditional Tagalog" Prompt: "Write a traditional 7-7-7-7 Tagalog Tanaga about a 'Bangka' (Canoe) as a metaphor for navigating life's uncertainties."

• The "Structural Audit" Prompt: "Write a Tanaga about 'Fireflies' (Alitaptap) and provide a breakdown of the syllable count for each line to verify the structural constraint."

Explainer

Technical Insight: This Jupyter Notebook demonstrates the raw algorithmic logic used for phonemic counting and syllable auditing during the initial research phase. The Live Agent (above) represents the transition to a production-ready application that incorporates a responsive interface and standardized API lifecycle management.

Click here to view the complete GitHub Repository

Legal & Intellectual Property

AI Authorship & Global Jurisprudence: Users of the Tanaga Poetic Agent should be mindful of the evolving legal landscape regarding synthetic content. Under current U.S. Copyright Office guidance, unedited AI-generated content generally lacks the "human authorship" required for copyright protection. However, this is not a global standard; jurisdictions such as the United Kingdom and China have begun recognizing copyright for AI-assisted works under specific criteria.

The Architect's Stance: Within the GAIL (Governed Artificial Intelligence Logic) framework, this agent is defined as a Collaborative Partner. While the engine provides the structural "scaffolding" and metaphorical "sparks," the most resonant works result from human intervention. I encourage users to perform significant human edits—not only to infuse the verse with personal soul but to establish a robust claim to intellectual property through transformative authorship.