Getting started, one role at a time

People get value from Babbily in different ways. A writer, a researcher and a team owner each start from a different place, and that’s fine. Choose the path below that sounds closest to your work, try it for a while, then adjust it as your workflow grows.

If you write, summarize or plan

Start with a normal chat. Ask Babbily to draft, rewrite, summarize, compare or plan, and include who the work is for and the format you want back. If Auto is in your model picker, it chooses a model for each message, so you don’t have to.

Next, save the preferences that don’t change. Memory is the place for your tone, preferred format, role, units and recurring audience details, so you don’t repeat them in every chat.

For work you repeat, such as weekly updates, customer emails or review checklists, use a consistent prompt structure. Memory supplies the stable details, and the prompt can focus on the task in front of you.

Try: “Draft a concise customer update for non-technical admins. Include what changed, what they need to do, and who to contact.”

If you research decisions

Match the tool to the question. For a focused question that needs current public sources, use Manual > Web search. For a broad topic, such as a comparison, a landscape or a multi-source brief, use Manual > Deep research.

Deep research follows a plan and writes its report into Canvas. Review its citations and completion status when it finishes. It can read from Plugins you select, but it doesn’t change anything in your connected apps.

Before you rely on anything about pricing, policy, legal, medical or financial topics, or anything that changes quickly, open the sources yourself.

Try: “Do deep research on this market and return a sourced brief with key players, risks, and open questions.”

If you work with files

You don’t need to switch models to work with a file. Every chat model accepts documents, text and code, images, audio, video and ZIP archives.

Attach only what matters. Start with one or a few relevant files, because long files can fill the context window quickly. Then name the result you want: a summary, a list of risks, a table, a rewrite, an action list, a comparison or a decision memo.

Try: “Analyze this document for executive readers. Return a summary, open decisions, risks, and next steps.”

If you manage ongoing or recurring work

Create a Project to keep related chats, instructions, knowledge files and project memory together, in the workspace where the work belongs.

On a paid plan, Scheduled tasks can run briefings, reviews or monitoring without you there. Know the boundaries before you rely on them: a scheduled task can read from the Plugins you select, but because nobody is present, it can’t stop for approvals or perform write actions.

If you use connected apps

1. Connect the app. Open Settings > Plugins and authorize the app you want Babbily to use.

2. Ask for specific context. Name the app, person, folder, project, channel, repository or time window when it matters.

3. Review anything that needs approval. Check recipients, destinations, content and side effects first. Nothing runs until you choose Allow on the approval card, or Send on an email draft.

Try: “Use Gmail to find the latest thread with this customer and summarize open questions, blockers, and next steps.”

If you manage a team

Team plans use seat-based billing with a three-person minimum, and include team workspace, billing, member and usage controls where available.

• Explain when members should work in Personal and when they should use the team workspace.

• Decide whether the owner should turn on Shared team memory.

• Invite teammates from Settings > Team and keep an eye on pending invitations.

• Review access regularly: accepted members, pending invitations, team shares, Shared team memory, public shared chats, plugin access, billing and API usage budget.

Where to go next

Once you’ve found your path, the task recipes and prompting patterns guides help you get more from each chat, and the docs for Projects and Scheduled tasks cover ongoing work in more depth.

Read the full docs ↗