Prepare bounded domain evidence for AI agents

Python example: AI Agents

Requires Python 3.9 or later. Uses the standard library only, processes local files, and makes no network requests. Save the script beside your downloaded inputs, or provide full paths.

Download ai-agents.py

Run the example

python3 ai-agents.py new.txt.gz --keyword cloud --observation-date 2026-09-01 --limit 20

Results are printed to the terminal. Redirect standard output to a file if you want to save the report. For the SQLite example, the database is saved at the path you specify.

Complete script

import argparse
import csv
import gzip
import sys


def domains(path):
    with gzip.open(path, "rt", encoding="utf-8") as source:
        for line in source:
            domain = line.strip().lower().rstrip(".")
            if domain:
                yield domain

import datetime
import json

parser = argparse.ArgumentParser(description="Build bounded domain evidence for an AI agent")
parser.add_argument("file")
parser.add_argument("--keyword", required=True)
parser.add_argument("--observation-date", required=True)
parser.add_argument("--limit", type=int, default=20)
args = parser.parse_args()
if not 1 <= args.limit <= 100:
    parser.error("limit must be between 1 and 100")
try:
    date = datetime.date.fromisoformat(args.observation_date).isoformat()
except ValueError:
    parser.error("observation-date must be YYYY-MM-DD")
matches = []
for domain in domains(args.file):
    if args.keyword.lower() in domain:
        matches.append(domain)
        if len(matches) == args.limit:
            break
print(json.dumps({"source_file": args.file, "observation_date": date,
                  "meaning": "newly observed names, not verified registrations",
                  "selection": "first matching names in file order",
                  "limit": args.limit, "domains": matches}, indent=2))

To automate input downloads, follow the API documentation for tokens, supported endpoints, and historical dates. Keep API tokens out of shared scripts.