Kevin Leneway kleneway

It is critical that you do not skip any steps. After you complete each task, update the file to check off any task. Run builds and commits after each task. Continue with each task until you have checked off each one. After each story, do not take a screenshot. If you need more detail about a task, you can gather relevant files and pass the FULL file to the research agent.

Design Enhancement Tasks

Typography & Brand

1. Update font hierarchy in tailwind.config.ts to use Geist for headings and Inter for body text, with precise font weights (300, 400, 500, 700)
2. Define a consistent type scale in globals.css with proper line heights and letter spacing for all text elements
3. Create text styles utility classes in globals.css for common text patterns (headings, body, captions)

Story: Extend the Prisma Schema with PIA Models

Add the Pia model to prisma/schema.prisma with the following fields (in addition to the existing models):

model Pia {
  id                    String   @id @default(cuid())
  userId                String
  projectName           String?
  systemDescription     String?

	__________________START o1______________________

	Plan to Address GitHub Issue: Add Research Component to Dashboard Workspace

	---

	### 1. Understand the Problem

	- Objective: Add a new "Research" component to the dashboard application to display research items associated with a specific task or issue.
	- Key Requirements:

	/**
	* This is a version of a tool-calling behavior that implements a "phased scenario" style prompt
	* for restaurant selection and reservation. The conversational agent guides the user through
	* selecting a restaurant and making a reservation based on their preferences in phases.
	*/
	import { defineTool } from "@pioneersquarelabs/language-barrier";
	import { defineBehaviorModule } from "@pioneersquarelabs/vdot";
	import { z } from "zod";

	/**

	#!/usr/bin/env bash

	set -e

	APP_NAME="newco"

	echo "🚀 Starting setup..."

	# Remove any existing app directory
	rm -rf $APP_NAME

	# .cursorrules

	Components & Naming

	- Use functional components with `"use client"` if needed.
	- Name in PascalCase under `src/components/`.
	- Keep them small, typed with interfaces.
	- Use Tailwind for common UI components like textarea, button, etc. Never use radix or shadcn.

	Prisma


	<TEMPLATE>
	<INSTRUCTIONS>
	Use the <CODEBASE> code as reference, and convert the high-level <TASK> into a set of very detailed step-by-step instructions that an AI coding agent can complete.
	Only includes steps an AI coding agent can take. Do not include testing or any other work a human would do to confirm the task has been completed.
	ALWAYS have the agent run a build when it is complete. Be specific and decisive about what the agent should do.
	Do not include any additional meta instructions to the user. Use markdown formatting.
	</INSTRUCTIONS>
	<TASK>

	#!/bin/bash

	# Path to the .cursor-updates file (update this with your own .cursor-updates file)
	CURSOR_FILE="/full/path/to/your/.cursor-updates"

	# Get today's date in YYYY-MM-DD format
	TODAY=$(date +%Y-%m-%d)

	# Create a temporary file
	TMP_FILE=$(mktemp)

	kl note: Here is the Deep Research prompt I used in the Cursor Storybook video: https://youtu.be/gXmakVsIbF0
	For background, this is a real-world tech feasibility task I am working on where I am trying to build out a realistic-looking fake website for an AI browsing agent to use to complete tasks. I found this random site that was close enough to what I wanted so I used it as a shortcut instead of taking the time to write out a full PRD or anything.

	...above this was just the transcript and the initial guidance...


	Act as a technical fellow and create a detailed, step-by-step guide to recreating this software using a modern stack. Here is the cursorrules for this repository:
	# .cursorrules

	Components & Naming

	For generating stories and tasks from a video, use the following instructions:
	<INSTRUCTIONS>
	Act as a world-class technical product manager. Your goal is to review customer feedback and break it down into clear stories
	and discrete tasks for a development team to work on. Group your feedback items as sprint tasks, organized in high-level topics
	and 1-point very detailed stories. Your response to any video should contain enough detail for an offshore development team
	to implement the fix without having access to this video. Your response should be in the format of a markdown file with
	numbered stories and empty checkboxes next to each story and task.
	</INSTRUCTIONS>

	For refining the stories in the cursor-tasks file, use the following instructions: