Dust is a capable platform for building AI agents over the data you connect — flexible, with open-source components and published pricing. If your goal is to build bespoke assistants, it gives you room to move.
Redijo doesn’t compete on agent flexibility; it competes on proof. The question that defines Redijo is “where did that number come from?”, and the answer arrives with the source file, tab, and range. The agent is the means; auditability is the product.
Auditable by construction
In Redijo, calculation and comparison are deterministic, kept off the AI’s path. The model drafts the prose, but the figure comes from a path you can re-run and check. The proof is born with the answer — you review, you don’t trust.
Permission at synthesis time
Redijo enforces each fragment’s permission the instant the answer is composed. Anything outside your access never enters — not even aggregated inside a total. That’s our moat.
Where Dust has the edge
In fairness: for building and orchestrating customizable AI agents, with open source and configuration freedom, Dust is strong. Redijo is more opinionated: it aims at the auditable management report and the monthly recurrence, with per-number citation at the center. You can also bring your own AI through an MCP server, with permissions and an audit trail.
Both publish pricing openly. The difference is in what each number carries back. Your files are hosted with international-transfer safeguards.