Skip to content
AdithyaNarayannPublic

About

No description, website, or topics provided.

Resources

Stars

2 stars

Watchers

0 watching

Forks

Latest commit

 

History

22 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Prompta

Pipeline: Prompt Diagnostics License: Custom FastAPI React PyTorch

Stop guessing. Start debugging prompts.

Most prompt workflows are still trial → error → hope.

A prompt breaks.
You tweak it.
You rerun it.
But you never see what actually failed.

Prompta changes that.

It treats prompts like systems — and failures like signals.

By analyzing the gap between prompt and output, it pinpoints where control broke, classifies the failure, and generates a targeted rewrite with traceable reasoning.

Not prompt tweaking.
Prompt debugging.

Quick Navigation

Quick Example

Input Prompt

Return strict JSON summary

Model Output

Free-form text

Analysis

  • Detected: format_pressure
  • Fix: enforce schema and explicit output constraints

Demo

Watch Video

Analysis View

Analysis Example

Rewrite Output

Rewrite Example

Detailed Example

Before
"Summarize this architecture and return strict JSON. Keep it short but include all details."

Failure
- format_pressure: strict format + conflicting completeness constraints
- scope_ambiguity: unclear boundary for "all details"

Fix
"Return valid JSON with keys: summary, risks, mitigations.
Limit summary to 5 bullets. Include only production-impact risks.
If information is missing, add an explicit unknowns array."

How It Works

flowchart TD
    A[Prompt + Output] --> B[Intent Extraction]
    B --> C[Multi-label Failure Classification]
    C --> D[Threshold Filter]
    D --> E[Focused LLM Diagnostics]
    E --> F[Severity Scoring]
    F --> G[Prompt Rewrite]
Loading

Pipeline design goal: narrow expensive reasoning to only the failure modes that matter.

Why It Matters

  • Eliminates blind prompt iteration
  • Converts vague failures into structured signals
  • Produces traceable, explainable rewrites
  • Supports consistent prompt quality workflows

Tech Stack

  • Backend: FastAPI, HTTPX, Pydantic
  • ML/NLP: DeBERTa (Transformers, PyTorch), Sentence-Transformers, scikit-learn
  • Frontend: React, Vite, React Router
  • LLM Gateway: OpenRouter

Author

Adithya Narayan V S

License

This project is under a custom license.
See the full terms here: LICENSE

About

No description, website, or topics provided.

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages