Use case
Research briefs
A question split into three parts and researched in parallel, with one pass to fill the gaps, then one written answer with its sources, saved to your files.
The workflow in the editor, captured from the open-source app.
- Steps
- 10
- Agents
- 2
- Where a person answers
- 0
- Run side by side
- 1
- Models
- Yours to choose, per step: a small one for sorting and checks, a strong one where judgment matters
- Stops at
- Its turn and time limits; on Cloud, also your plan’s limit
The workflow
What it solves, and how it runs.
The problem
Open-ended research is where autonomous agents spend the most money. A fixed shape turns it into something you can run on a schedule and plan for.
Why a fixed path matters here
The shape is configuration, not emergent behavior: one pass to fill the gaps, not as many as the model feels like.
How it runs
- 1The question is split into three sub-questions
- 2Each one is researched in parallel, citing every source
- 3What was found is merged, sources attached
- 4A check looks for a part that is thin or unsourced, and if it finds one, an agent follows the cited sources once to fill it
- 5A writer answers the question from all of it and saves the answer to your vault
Run it
On our cloud, or on your servers.
On SynapseOrch Cloud
Describe it to Build with AI in your own words. It drafts the steps, the model for each and where you answer, and builds nothing until you approve the plan.
On your own servers
deep-research-agent.bundle.json holds the agents and the workflow together. Import it from Settings → Import / Export in a self-hosted install, add your own connections, and run it.
It needs
- A model for the agents, from any provider you set up
- Web access: the built-in page reader, or a full browser when Node.js is installed
More
Other workflows worth a look
Customer support replies
Answers customer questions from your help articles, and has a person check anything it isn’t sure of before it goes out.
Market and competitor reports
A report on your market with the same sections every time: news, competitors and numbers gathered in parallel, scored, and written up with a clear go / no-go.
Researched articles
Articles drafted from real sources and checked until every claim is cited, then held for your approval before they’re saved as a Google Doc.
Two ways to run it
Let us run it, with nothing to install and no API key needed. Or run it on your own servers, free and open source.
Free plan, no card needed.