ConciseSpec
.dev
Saved Plans (
0
)
Cloud / Provider API
Copy Markdown
Model Architecture & Tier
Checking Cache...
SmolLM2 135M (Micro - Fast, Low RAM)
SmolLM2 360M (Balanced - Recommended)
Qwen 2.5 0.5B (High Quality Tiny)
Llama 3.2 1B (Requires Modern GPU / 2GB+ VRAM)
CF: Meta Llama 3.1 8B
CF: Mistral 7B
Groq: Llama 3.1 8B (Sub-Second)
OpenAI: GPT-4o Mini
Deterministic Heuristics (Instant Rule-Based)
Initializing...
0%
Project Scope
Project Name
Problem Statement (TL;DR)
Primary Persona
Project Duration
Additive Tech Stack Modifiers
1. Vanilla HTML/CSS/JS
2. React / Svelte
3. FastAPI + WebSockets
Core Goals & Architecture
Primary User Action / High Priority Feature
Explicit Non-Goal
Generate / Recompile Spec
Save Current Plan
Live Document Preview
0 words | 0 chars
Cloud AI Settings
×
Configure API keys for remote cloud inference when not using local WebGPU.
Cloudflare Workers AI
Cloudflare Account ID
Workers AI API Token
Groq / OpenAI (BYOK)
API Key