Orchestrate AI agents across your business

dotDash puts agentic workflows, conversational AI and search over your own data on one platform — so an idea becomes something running in production, not another integration project.

A dotDash workflow: an AI agent node wired to a human approval step, with the agent's prompt and output schema alongside

Connects to what you already run

Bring your own cloud, warehouse, messaging channels and models. Anything marked soon is on the roadmap, not in the product.

Google Cloud

Vertex AI

Google Workspace

BigQuery

WhatsApp Business

Resend

PostgreSQL + pgvector

MCP

Slack

Soon

GitHub

Soon

Microsoft 365

Soon

Salesforce

Soon

HubSpot

Soon

One platform, four moving parts

Workflows, conversations, retrieval and tools. They share the same identity, the same data and the same audit trail, so they compose instead of needing glue.

Build workflows you can see

Compose agents, tools and approvals on a canvas. Branch, loop, pause for a human, and watch each step execute in real time.

AI Agent

Summarise the request

inputoutput
Human Approval

Is this a good idea?

inputoutput
workflow console — ready to execute

Meet people where they are

One assistant across web chat, WhatsApp and Slack — with voice transcription, session history and escalation to a human.

Hi — what's the notice period for cancelling our contract?
Thirty days in writing, under clause 9.2 of your master agreement. Want me to pull the exact wording?
Yes please. And who signed it?
Signed 4 March by your operations lead. Here's the clause and a link to the document.
Can you get someone to call me about it?
Handing this to the accounts team now — they can see the whole thread.

Answers grounded in your data

Semantic, keyword and hybrid search with reranking over your own documents and databases, so answers cite something real.

Indexed sources

Add

Policies & handbook

1,204 documents

Support tickets

18,730 threads

Contracts

342 documents

Product docs

pgvector index

Warehouse — BigQuery

via MCP

Agents that can act

Through MCP, agents query databases, search documents, call your integrations and start other workflows.

search_documentsquery_databaseexecute_workflowlist_integrationscall_integration_apimonitor_workflowsend_emailcalendar_events
list_integrationscall_integration_apimonitor_workflowsend_emailcalendar_eventssearch_documentsquery_databaseexecute_workflow
monitor_workflowsend_emailcalendar_eventssearch_documentsquery_databaseexecute_workflowlist_integrationscall_integration_api
Tenant isolation in the database

Every row is scoped to your organisation by Postgres row-level security, not by an application filter someone can forget to write.

Roles and permissions

Granular role-based access across workspaces, with an append-only audit trail of who changed what.

Multi-factor authentication

TOTP enrolment and challenge, enforceable organisation-wide, alongside Google sign-in.

Workspaces

Separate teams, data and workflows inside one organisation, with their own members and integrations.

Usage you can see

Processing units, searches, storage and seats are metered and shown in-product, so a bill is never a surprise.

Scheduled runs

Put any workflow on a cron schedule and let it run unattended, with execution history kept per run.

Traced end to end

Every agent step, tool call and model response is logged and traceable, so you can explain any answer.

Full API on every plan

A complete REST API with a published OpenAPI spec. Not an upsell — API access is not a plan tier here.

What teams build with dotDash

Every one of these is assembled from the same parts: a workflow, an agent, your data and a channel to reach people on.

Put your first agent to work this week

Start a 14-day trial and build a workflow against your own data. Talk to us if you would rather be walked through it.

Copyright © 2026 dotDash
All rights reserved

DOTDASH