Skip to main content
This guide takes you from signup to a useful answer in about five minutes. By the end you will have an Agent, your first piece of research, and the beginnings of a Profile the Agent remembers.

​
1. Sign in

Open Driven and sign in with Google. New users get one month of Pro free — just follow the signup flow shown in the app.

​
2. Create or open an Agent

An Agent is your dedicated investment workspace. It keeps its own chat history, Profile, portfolios, files, and scheduled tasks. Creating one is a single click now, no setup commands required. Think of an Agent as a desk dedicated to one job. You might eventually have a US research desk, a Hong Kong desk, and a portfolio-monitoring desk, each with its own context. For now, one is enough.

​
3. Ask a concrete question

The quality of your answer tracks the specificity of your question. Start with something concrete: 
Analyze AAPL after the latest earnings report. Focus on revenue growth, margin trend, valuation, and risks.
For broader research, point the Agent at a theme: 
Do a deep dive on the AI semiconductor supply chain and identify the strongest public companies.
Driven will automatically select the right Skill for the job, pull the data it needs, and structure the answer. You do not have to tell it which workflow to run, though you can if you want to.

​
4. Review the answer

For investment work, the answer is only as good as its evidence. Check:
  • Sources — are the financial figures pulled from data, not guessed?
  • Assumptions — does the answer separate facts from interpretation?
  • Risks — are the downside cases concrete and specific?
  • What would change the view — does it say what evidence would flip the conclusion?
If anything is thin, push back in the same conversation: ask for the bear case, ask it to date its claims, or ask it to cite the specific statement fields it used.

​
5. Tell the Agent how you invest

When you want the Agent to remember how you invest, save it to the Agent’s Profile. The Profile is the Agent’s standing identity and preferences, and it shapes every future conversation. For example:
  • Target market: US equities
  • Risk preference: avoid highly leveraged businesses
  • Style: concise answers, evidence first, always flag the bear case
From now on, every analysis this Agent runs will respect those preferences without you repeating them. You can set the Profile up properly when you create an Agent.

​
What just happened

In five minutes you used four of Driven’s core pieces: an Agent (the workspace), a Skill (the analysis workflow Driven auto-selected), live data (the figures behind the answer), and the Agent’s Profile (the preferences it now remembers). The rest of the docs go deeper on each — including the Playbook, the strategy behind each portfolio.

​
Next steps