Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Look up the three modes, the five loop steps, the five Forge phases, and the copy and paste prompts you need to get started with Bright.
| Mode | Use when… |
|---|---|
| Ask | You want answers before anything is created |
| Plan | You want a reviewable path and shared scope |
| Agent | You’re ready for Bright to create, edit, or run |
There’s a dropdown menu at the bottom left that says: Agent, Plan and Ask. What’s the difference between the three?
What agents / subagents are available in Brightstack? And explain what each agent does.
Help me research whether my Node.js API needs a dedicated error-tracking service, and which option fits a small project. Cost matters.
Create a plan I can review before we take next steps. Include issues, key decisions, and what’s out of scope.
No adjustments needed. Turn this into a project with issues, then start the engineering work we’re ready for.
I run a small Node.js API in production. When something breaks, I find out
from users, not from my logs.
Help me to research, plan, create a project and execute the following:
1) Is a dedicated error-tracking service worth it for a small team, or is
structured logging enough? What exactly do I gain?
2) Compare the realistic options (Sentry, Rollbar, GlitchTip, Axiom) for a
small project where cost matters. Free tier first.
Happy with the project. Let’s start implementing what you can.