Introducing dotDash

Most teams adopting generative AI end up with the same architecture by accident: a chatbot in one place, a retrieval index in another, a scheduler somewhere else, and a growing pile of glue holding them together. Each part works. The seams are where the effort goes — and where the audit questions land.

dotDash exists because those parts belong in one system.

What it is

dotDash is a generative AI orchestration platform. Four capabilities share the same identity model, the same data and the same audit trail:

• Workflows. Compose agents, tools and approvals on a canvas. Branch, loop, pause for a human, and watch each step execute with its logs attached.
• Conversations. One assistant across web chat, WhatsApp Business and Slack, with session history, voice transcription and escalation to a person who can see the whole thread.
• Retrieval. Semantic, keyword and hybrid search over your documents and databases, with reranking, so an answer can cite the passage it came from.
• Tools. Through the Model Context Protocol, agents query databases, search documents, call your integrations and start other workflows.

Because they are one system, a conversation can trigger a workflow, a workflow can search your documents, and an agent can act on the result — without a webhook in the middle translating between three products.

Humans stay in the loop

Automation that cannot be stopped is not automation anyone will approve. A workflow can pause on a human approval step: the run halts, a named approver accepts or rejects in-product, and execution resumes from exactly where it stopped. Nothing is re-run and nothing is lost.

The same applies to answers. Every agent step, tool call and model response is recorded, so when someone asks why the system said what it said, the trace is there.

Built for more than one team

dotDash is multi-tenant to the database. Rows are scoped to your organisation by Postgres row-level security rather than by an application filter that someone could forget to write. On top of that sit workspaces, role-based access, MFA and an append-only audit trail — so several teams can work in one organisation without sharing anything they should not.

Usage you can see

Processing units, search queries, storage and seats are metered and visible in-product as they accrue. Exceeding an allotment adds to the invoice at a published rate; it never blocks a workflow mid-run. We think a bill should be predictable before it arrives, not explicable afterwards.

Every plan includes the full REST API and its published OpenAPI spec. API access is not a tier here.

Getting started

Start a 14-day trial and build one workflow against your own data. If you would rather be walked through it, talk to us — describing what you are trying to automate is usually enough for us to show you the shape of the answer.