Tably Team
Guides to building apps with an AI team
What each AI does well, how to pick one for each role, what building an app costs and how Tably Team works inside. Written by the team that builds it.
AI models
One guide per model: what sets it apart, where not to use it, which role to give it and what it costs. Plus the role-by-role comparison.
Which AI to choose for each role on your team (CEO, CTO, engineering, product, design and QA)
A practical comparison of Claude, GPT, Gemini, DeepSeek, Grok, Llama, Kimi and Mistral by role. Which model performs best in leadership, technology, engineering, product, design and quality, with three ready-to-copy teams.
OpenRouter: a single API key for more than 300 models
What OpenRouter is, how it works, which models it unlocks (Qwen, Llama, DeepSeek, Claude, GPT and hundreds more), what it costs and how to make the most of it on an AI team without entering ten different keys.
Ollama: run AI models on your own computer, free and in private
What Ollama is, which models you can run locally (Llama, Mistral, Qwen, DeepSeek, Gemma), what hardware you need, what quality to expect and how to use it on an AI team without any data leaving your machine.
Mistral: the European model, what it is good for and what role to give it on your team
A guide to the models from Mistral AI. Its European focus on privacy, its Small, Medium and Large variants, its performance on code and the roles on an AI team where it contributes most.
Llama on Groq: Meta's open model at lightning speed
A guide to Llama, Meta's open models, served by Groq. Why it responds so fast, what quality to expect, what it costs and which roles on an AI team it is best suited for.
Kimi (Moonshot AI): what it is good for and what role to give it on your team
A guide to Kimi, the models from Moonshot AI. Its strength in long contexts and agent tasks, its price and the roles on an AI team where it performs best.
Grok (xAI): what it is for, what makes it different and which role to give it on your team
A guide to xAI's Grok models. Their direct style, their access to recent information, their reasoning performance and the roles on an AI team where they contribute most.
GPT (OpenAI): what it is for, which models exist and which role to give it on your team
A complete guide to OpenAI's GPT models. What sets them apart, when to use the full version and when the mini, what Codex is as a builder, and which roles on an AI team they fill best.
Gemini (Google): what it is for, Pro vs Flash and which role to give it on your team
A guide to Google's Gemini models. The differences between Pro and Flash, their strength in vision and long contexts, what they cost and which roles on an AI team they are best suited for.
DeepSeek: what it is for, why it is so cheap and which role to give it on your team
A guide to the DeepSeek models. Their quality-to-price ratio, their direct style in debate, their performance in code and math, and the roles on an AI team where they are the right choice.
Claude (Anthropic): what it is for, which models exist (Fable, Opus, Sonnet, Haiku) and which role it fills best
A complete guide to Claude, Anthropic's family of models. Fable, Opus, Sonnet and Haiku, their reasoning style, where they shine at writing code and designing products, and which roles on your team you should give them.
Prompt engineering and references
How to write the request so it comes out right, and how Tably studies the apps you like before building.
How to write an app request so the AI builds it well (applied prompt engineering)
What to include and what to leave out of your app request, how Tably Team's automatic prompt engineering works, examples of good and bad requests, and a template you can copy.
Reference apps and reverse engineering: how Tably studies the apps you like before building yours
How reference research works in Tably Team: a real browser visit, screenshots, descriptions from a vision model and, with deep analysis, reverse engineering of bundles, routes and APIs to replicate an app faithfully.
How Tably works
The team, the two ways to build and who writes the code.
What Tably Team is and how it builds an app with a team of AI models
Tably Team assembles an AI team with real roles (CEO, CTO, engineering, product, design and QA), has it debate your idea, design it and build it. Here is how it works under the hood, step by step.
Direct builder or builder with a team: which one is right for your app
The two ways to build in Tably Team, compared honestly. What each one does, how long it takes, how much it costs, what quality to expect and a simple rule for choosing.
Claude Code vs Codex vs API: who writes your app's code and what it costs
The three types of builder in Tably Team compared: Claude Code and Codex on a subscription, or a model via API with your key. Differences in quality, cost and speed, and how to use your subscription from your phone with your computer turned off.
Publishing and mobile
Going live with a database and users, and building for iOS and Android.
Publishing your app with Tably Cloud: your own git, one click to go live, database and authentication
How Tably Team publishes what it builds: a git repository per project, one-click publishing (on Tably, Cloudflare or Fly), database and authentication with Neon or Supabase, migrations, and how to take everything to your own infrastructure.
Mobile apps for iOS and Android with AI: how Tably builds with Expo and runs them in the simulator
How Tably Team builds mobile apps with React Native and Expo, how to choose between web, mobile or both from a single codebase, what you need installed to run them in the iOS simulator and the Android emulator, and how they get published to the stores.
Costs and security
What you pay, to whom, how to lower it, and what happens to your keys, your code and your data.
Security and privacy in Tably Team: what happens with your API keys, your code and your data
Where your keys are stored, what each AI provider sees, where your code lives, what data leaves your machine, how the subscription token works, and what options you have if nothing can leave your infrastructure.
How much it costs to build an app with AI: tokens, subscriptions and what actually drives the bill
An honest breakdown of the cost of building an app with an AI team: what providers charge, what a council debate costs, how to build without spending tokens using a subscription, and how Tably shows the real cost.
Try Tably Team with your idea
Describe what you want to build and watch the team debate it, design it and build it.