diff --git a/migrations/README b/migrations/README
new file mode 100644
index 0000000..0e04844
--- /dev/null
+++ b/migrations/README
@@ -0,0 +1 @@
+Single-database configuration for Flask.
diff --git a/migrations/alembic.ini b/migrations/alembic.ini
new file mode 100644
index 0000000..ec9d45c
--- /dev/null
+++ b/migrations/alembic.ini
@@ -0,0 +1,50 @@
+# A generic, single database configuration.
+
+[alembic]
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic,flask_migrate
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[logger_flask_migrate]
+level = INFO
+handlers =
+qualname = flask_migrate
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S
diff --git a/migrations/env.py b/migrations/env.py
new file mode 100644
index 0000000..4c97092
--- /dev/null
+++ b/migrations/env.py
@@ -0,0 +1,113 @@
+import logging
+from logging.config import fileConfig
+
+from flask import current_app
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+logger = logging.getLogger('alembic.env')
+
+
+def get_engine():
+    try:
+        # this works with Flask-SQLAlchemy<3 and Alchemical
+        return current_app.extensions['migrate'].db.get_engine()
+    except (TypeError, AttributeError):
+        # this works with Flask-SQLAlchemy>=3
+        return current_app.extensions['migrate'].db.engine
+
+
+def get_engine_url():
+    try:
+        return get_engine().url.render_as_string(hide_password=False).replace(
+            '%', '%%')
+    except AttributeError:
+        return str(get_engine().url).replace('%', '%%')
+
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+config.set_main_option('sqlalchemy.url', get_engine_url())
+target_db = current_app.extensions['migrate'].db
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def get_metadata():
+    if hasattr(target_db, 'metadatas'):
+        return target_db.metadatas[None]
+    return target_db.metadata
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url, target_metadata=get_metadata(), literal_binds=True
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    # this callback is used to prevent an auto-migration from being generated
+    # when there are no changes to the schema
+    # reference: http://alembic.zzzcomputing.com/en/latest/cookbook.html
+    def process_revision_directives(context, revision, directives):
+        if getattr(config.cmd_opts, 'autogenerate', False):
+            script = directives[0]
+            if script.upgrade_ops.is_empty():
+                directives[:] = []
+                logger.info('No changes in schema detected.')
+
+    conf_args = current_app.extensions['migrate'].configure_args
+    if conf_args.get("process_revision_directives") is None:
+        conf_args["process_revision_directives"] = process_revision_directives
+
+    connectable = get_engine()
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=get_metadata(),
+            **conf_args
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()
diff --git a/migrations/script.py.mako b/migrations/script.py.mako
new file mode 100644
index 0000000..2c01563
--- /dev/null
+++ b/migrations/script.py.mako
@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}
diff --git a/migrations/versions/565419907b71_add_event_model.py b/migrations/versions/565419907b71_add_event_model.py
new file mode 100644
index 0000000..a9439dc
--- /dev/null
+++ b/migrations/versions/565419907b71_add_event_model.py
@@ -0,0 +1,32 @@
+"""Add Event model
+
+Revision ID: 565419907b71
+Revises: 
+Create Date: 2025-07-28 14:29:12.567526
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '565419907b71'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('note')
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('note',
+    sa.Column('id', sa.INTEGER(), nullable=False),
+    sa.Column('content', sa.TEXT(), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    # ### end Alembic commands ###
diff --git a/run.py b/run.py
new file mode 100644
index 0000000..2964eca
--- /dev/null
+++ b/run.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+"""
+EchoNote Application Entry Point
+
+This script runs the EchoNote Flask application.
+Usage: python run.py
+"""
+
+import sys
+import os
+
+# Add the src directory to Python path so we can import our package
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src'))
+
+from echonote.app import app
+from echonote.database import init_db
+
+if __name__ == '__main__':
+    # Initialize the database
+    init_db()
+    
+    # Run the Flask app
+    app.run(debug=True, host='0.0.0.0', port=5000)
diff --git a/src/echonote/__init__.py b/src/echonote/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/echonote/app.py b/src/echonote/app.py
new file mode 100644
index 0000000..81d9f15
--- /dev/null
+++ b/src/echonote/app.py
@@ -0,0 +1,121 @@
+import os
+from google.cloud import speech
+from google.auth.exceptions import DefaultCredentialsError
+from werkzeug.utils import secure_filename
+from flask import Flask, render_template, request, redirect, url_for, jsonify
+from flask_sqlalchemy import SQLAlchemy
+from database import create_task, init_db, get_all_tasks, update_task, delete_task
+from genai_parser import TaskParser
+task_parser = TaskParser()
+
+app = Flask(__name__)
+app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = False
+app.config['UPLOAD_FOLDER'] = os.path.join(os.getcwd(), 'uploads')
+
+
+# Dummy speech client class for testing
+class DummySpeechClient:
+    """adding so tests can import app.py without crashing"""
+
+    def recognize(self, config, audio):
+        # stub - tests will override this
+        raise NotImplementedError("This should be monkey patched in tests")
+
+
+# Initializing google speech client
+try:
+    speech_client = speech.SpeechClient()
+except DefaultCredentialsError:
+    # fallback to a stub so that tests can monkey patch
+    speech_client = DummySpeechClient()
+
+# Define nav links to be used across routes
+def get_nav_links():
+    return [
+        {'href': '/', 'text': 'Home', 'endpoint': 'index'},
+        {'href': '/draw', 'text': 'Draw', 'endpoint': 'draw'}
+    ]
+
+#updated to use Task model not Note model
+@app.route('/', methods=['GET'])
+def index():
+    tasks = get_all_tasks()
+    return render_template('index.html', tasks=tasks, nav_links=get_nav_links())
+
+@app.route('/draw', methods=['GET'])
+def draw():
+    return render_template('draw.html', nav_links=get_nav_links())
+
+# Audio upload route
+@app.route('/api/upload', methods=['POST'])
+def upload_audio():
+    f = request.files.get('audio')
+    if not f:
+        return {"error": "no file"}, 40
+    # sanitizing filename (used werkzeug helper)
+    filename = secure_filename(f.filename)
+    upload_folder = app.config['UPLOAD_FOLDER']
+    # make sure the folder exists
+    os.makedirs(upload_folder, exist_ok=True)
+    # do we want to save audio to disk? if not we dont need next two lines
+    save_path = os.path.join(upload_folder, filename)
+    f.save(save_path)
+    return {"filename": filename}, 200
+
+# Audio transcribe route
+@app.route('/api/transcribe', methods=['POST'])
+def transcribe_audio():
+    if 'audio' not in request.files:
+        return jsonify(error='no file'), 400
+    audio_bytes = request.files['audio'].read()
+    audio = speech.RecognitionAudio(content=audio_bytes)
+    config = speech.RecognitionConfig(
+        language_code="en-US",
+    )
+    resp = speech_client.recognize(config=config, audio=audio)
+    transcript = " ".join(r.alternatives[0].transcript for r in resp.results)
+
+    return jsonify(transcript=transcript), 200
+
+# List tasks route
+@app.route('/api/tasks', methods=['GET'])
+def list_tasks():
+    tasks = get_all_tasks()
+    return jsonify([{
+        "id": t.id,
+        "name": t.name,
+        "completed": t.completed
+    } for t in tasks])
+
+# process tasks route
+@app.route('/api/save_task', methods=['POST'])
+def save_task():
+    data = request.get_json()
+    print("Received JSON:", data)
+
+    if not data or "transcript" not in data:
+        print("No transcript provided")
+        return jsonify(error='Transcript is required'), 400
+
+    transcript = data["transcript"]
+    parsed_tasks = task_parser.parse_transcript(transcript)
+
+    if not isinstance(parsed_tasks, list):
+        return jsonify(error="Failed to parse tasks"), 500
+    
+    count = 0
+    for task_data in parsed_tasks:
+        task_text = task_data.get("text")
+        due_date = task_data.get("due")
+        print(f"Trying to save task: {task_text} (Due: {due_date})")
+        if task_text:
+            create_task(task_text, due_date)
+            count += 1
+            
+    print(f"Saved {count} tasks to database")
+    return jsonify(message=f'{count} tasks saved'), 200
+
+if __name__ == '__main__':
+    with app.app_context():
+        init_db()#initialize the tasks database
+    app.run(debug=True)
\ No newline at end of file
diff --git a/src/echonote/database.py b/src/echonote/database.py
new file mode 100644
index 0000000..4233e38
--- /dev/null
+++ b/src/echonote/database.py
@@ -0,0 +1,77 @@
+from sqlalchemy import create_engine, Column, Integer, String, Boolean, DateTime, Text
+from sqlalchemy.orm import declarative_base
+from sqlalchemy.orm import sessionmaker
+from datetime import datetime, timezone
+
+
+# create a SQLite database
+DATABASE_URL = "sqlite:///./echo_note.db"
+engine = create_engine(DATABASE_URL, connect_args={"check_same_thread": False})
+SessionLocal = sessionmaker(bind=engine)
+Base = declarative_base()
+
+
+# define the Task model
+class Task(Base):
+    __tablename__ = 'tasks'
+    id = Column(Integer, primary_key=True)
+    name = Column(String(255), nullable=False)
+    completed = Column(Boolean, default=False)
+    created_at = Column(DateTime, default=lambda: datetime.now(timezone.utc))
+    due_date = Column(String(100), nullable=True)
+
+    def __repr__(self):
+        return f"<Task(id={self.id}, name='{self.name}', completed={self.completed}, due_date='{self.due_date}')>"
+
+
+# initialize the database
+
+
+def init_db():
+    Base.metadata.create_all(bind=engine)
+
+# CRUD operations
+
+
+def create_task(name, due_date=None):
+    db = SessionLocal()
+    task = Task(name=name, due_date=due_date)
+    db.add(task)
+    db.commit()
+    db.close()
+
+
+
+def get_all_tasks():
+    db = SessionLocal()
+    tasks = db.query(Task).all()
+    db.close()
+    return tasks
+
+
+def update_task(task_id, name=None, completed=None):
+    db = SessionLocal()
+    task = db.get(Task, task_id)
+    if not task:
+        db.close()
+        return None  # or raise an error
+    if name is not None:
+        task.name = name
+    if completed is not None:
+        task.completed = completed
+    db.commit()
+    db.refresh(task)
+    db.close()
+    return task
+
+
+def delete_task(task_id):
+    db = SessionLocal()
+    task = db.get(Task, task_id)
+    if not task:
+        db.close()
+        return False
+    db.delete(task)
+    db.commit()
+    db.close()
+    return True
diff --git a/src/echonote/genai_parser.py b/src/echonote/genai_parser.py
new file mode 100644
index 0000000..345386a
--- /dev/null
+++ b/src/echonote/genai_parser.py
@@ -0,0 +1,44 @@
+import os
+from urllib import response
+from dotenv import load_dotenv
+import google.generativeai as genai
+import json
+import re
+
+'''re = regular expressions ; cleans up text patterns --> when run w/o, output is messy. example below
+"tasks": "```json\n[\n  {\n    \"text\": \"Finish the report\",\n   
+ \"due\": \"Monday\"\n  },\n  {\n    \"text\": \"Email report to the team\",\n   
+  \"due\": \"Monday\"\n  }\n]\n```"
+'''
+
+class TaskParser:
+    def __init__(self):
+        load_dotenv()
+        genai.configure(api_key=os.getenv("GENAI_KEY")) 
+        self.model = genai.GenerativeModel("gemini-1.5-pro") 
+
+    def parse_transcript(self, transcript: str):
+        with open("prompt_template.txt", "r") as file:
+            base_prompt = file.read()
+
+        full_prompt = f"{base_prompt}\n\n{transcript}"
+
+        try:
+            response = self.model.generate_content(full_prompt)
+            print("RAW GEMINI OUTPUT:")
+            print(response.text)
+            
+            original = response.text.strip()
+            clean_it = re.sub(r"```json|```", "", original).strip()
+            tasks = json.loads(clean_it)
+            print("Parsed tasks:", tasks)
+            return tasks
+        except Exception as e:
+            print("Error parsing transcript:", e)
+            print("Raw Gemini output:", response.text if 'response' in locals() else "None")
+            return []
+
+'''class that reads a transcript and sends it to Gemini using a custom prompt.
+returns a list of tasks based on what the user said. This lets us take 
+unstructured voice input and turn it into structured to-do items for the project.
+'''
\ No newline at end of file
diff --git a/templates/index.html b/templates/index.html
index dc93d9a..08713b4 100644
--- a/templates/index.html
+++ b/templates/index.html
@@ -181,6 +181,66 @@ <h2>Tasks</h2>
     document.getElementById('cancel-btn').addEventListener('click', function() {
         document.getElementById('confirmation-popup').style.display = 'none';
     });
+
+    // ✅ Handle undo button (mark task as incomplete)
+    document.querySelectorAll('.btn-undo').forEach(button => {
+        button.addEventListener('click', async function() {
+            const taskId = this.getAttribute('data-task-id');
+            
+            try {
+                const response = await fetch(`/api/tasks/${taskId}`, {
+                    method: 'PUT',
+                    headers: {
+                        'Content-Type': 'application/json'
+                    },
+                    body: JSON.stringify({
+                        completed: false
+                    })
+                });
+                
+                if (response.ok) {
+                    // Refresh the page to show updated task
+                    window.location.reload();
+                } else {
+                    const errorData = await response.json();
+                    throw new Error(errorData.error || 'Failed to mark task as incomplete');
+                }
+            } catch (error) {
+                console.error('Error marking task as incomplete:', error);
+                alert('Error marking task as incomplete: ' + error.message);
+            }
+        });
+    });
+
+    // ✅ Handle done button (mark task as complete)
+    document.querySelectorAll('.btn-done').forEach(button => {
+        button.addEventListener('click', async function() {
+            const taskId = this.getAttribute('data-task-id');
+            
+            try {
+                const response = await fetch(`/api/tasks/${taskId}`, {
+                    method: 'PUT',
+                    headers: {
+                        'Content-Type': 'application/json'
+                    },
+                    body: JSON.stringify({
+                        completed: true
+                    })
+                });
+                
+                if (response.ok) {
+                    // Refresh the page to show updated task
+                    window.location.reload();
+                } else {
+                    const errorData = await response.json();
+                    throw new Error(errorData.error || 'Failed to mark task as completed');
+                }
+            } catch (error) {
+                console.error('Error marking task as completed:', error);
+                alert('Error marking task as completed: ' + error.message);
+            }
+        });
+    });
 });
 </script>