plain-words: a local AI that decodes official letters for a friend

Description and use

A command-line tool that uses a local LLM to translate official letters into plain language, highlighting the letter type, requested actions, deadlines, urgency, and jargon explanations, without sending data to the cloud.

Problem

Official letters are written to be legally precise, not readable, causing missed deadlines for non-native readers.

Outcome

The tool provides a short, plain-language summary of official letters, including type, requested actions, deadlines, urgency, and definitions of hard words, without sending data to the cloud.

Workflow

• 1. Install Ollama and pull an open-weight model (default llama3.2).
• 2. Run plainwords.py with the letter text via stdin or file.
• 3. Specify language with -l (e.g., Hindi).
• 4. The tool queries the local model and outputs five concise answers.
• 5. The friend reviews the summary and checks deadlines against the original letter.

Evidence

Official letters are written to be legally precise, not readable. A tax notice, a visa request, a clinic bill: for someone reading in their second language, one missed deadline can cost real money.

Source

plain-words is a small command-line tool for a friend in that spot. Give it the text of a letter and it answers five questions in short, simple sentences: What is this? What do they want from me? What are the deadlines? (only dates that appear in the letter) Is it urgent? What do the hard words mean?

Source

Runs on an open-weight model through local Ollama. Letters hold tax, visa, and medical details; none of it is sent to a cloud API. Open weights are what make that possible.

Source

The core is one HTTP call to a local Ollama server running an open-weight model (llama3.2 by default, swappable with -m). The real work is the prompt: fixed headings, a reading-level target, and a hard rule against inventing facts or dates.

Source