FAQ

Questions, answered.

How a research run works, what Bricolage can produce, how your data is handled, and how to get started.

Getting value

How do I get a good result?

Brief it the way you would brief an analyst: the question, the context, and what good looks like. You do not need to write a prompt spec. The more grounding you give it, especially your own documents, the sharper the output.

Can I use my own documents?

Yes. Upload your data room, prior decks, spreadsheets, contracts, or transcripts. Bricolage works from your material alongside the open web and the literature, so the research is grounded in your context, not just public sources.

What final outputs can it produce?

Ask for a report, a presentation, or a brief. Along the way it builds intermediary documents for each layer of the research, and you can open any of those too.

What to expect

How long does a research run take?

It depends on the depth you choose. A Standard run usually finishes in about 30 to 60 minutes. A Complex run takes a few hours. A Landmark run can take most of a day, and a Research-depth run can take up to a few days for the most exhaustive work, though it can finish in a few hours when the agent already has the data it needs. In every case you hand it the question and come back to a finished deliverable; you do not have to babysit it.

What does the deliverable look like?

Board-ready: a structured report, presentation, or brief, with every claim cited to its source and ready to put in front of a client or a board.

What sources does it research?

The open web, peer-reviewed and industry literature, government and regulatory data, and your own uploaded documents. It triangulates across them and scores its confidence.

What are intermediary documents?

As it researches, Bricolage builds a document for each layer of the work: the gathered evidence, the analysis, the synthesis. Your final report, presentation, or brief is assembled from them, and you can inspect any layer.

Trust and data

Is every claim cited?

Yes. Each claim traces to the source it came from, so you can verify the work rather than take it on faith.

Can I verify the audit trail?

Every run is sealed with a cryptographically signed audit receipt. Change a single entry and the signature no longer verifies, and anyone (a client, an auditor, a regulator) can confirm the record independently against a public key they pin once.

Do you train on my data?

No. Your documents are used to answer your questions and are never used to train models.

Where does my data live?

Data is encrypted in transit and at rest, with data-residency and retention controls available. See the Security and Trust page for details.

Projects and plans

How is the work organized?

You run a project. A project produces deliverables, a report, a presentation, or a brief, along with the intermediary documents Bricolage builds for each layer of the research.

Who is Bricolage for?

Teams whose credibility is the product: boutique consultancies, research firms and analysts, corporate strategy teams, universities and labs, and government and regulated bodies.

How do plans and pricing work?

See the Plans page for current plans and what each one includes.

How do I get started?

Tell us about a real project on the contact page and we will help you get your first deliverable.

Ready to try it on a real problem?

Start with a free Standard research run. Hand it a brief and your documents, and get back a cited, board-ready report.

Start a free trial