AI agents with real tool access

Write your workflow.
AI runs it.

Describe what you want to automate in plain English. Dugong hands your instructions to an AI agent — it reads them, reasons through each step, and calls your apps directly. No builder. No blocks. No code.

Start for free → ▶ See how it works
Trusted by teams at
VercelNotionLinearRampResend
How it works

No builder.
Just language.

Traditional automation tools make you draw a diagram. Dugong just reads what you write and does the work.

01

Describe it in plain English

Write your trigger and steps the way you'd explain it to a colleague. Say "if the deal is over $10k, notify the CSM." Name any app. No special syntax — just plain language.

02

An AI agent reads and reasons through it

Your description is passed to an AI agent. It understands the intent, decides what to do at each step, handles conditions, and figures out what to pass between apps — live, at runtime.

03

It calls your apps and gets it done

The agent executes each step by making direct tool calls to Slack, Gmail, Salesforce, Notion, and more — in the right order, with the right data — no human involved.

Live example

You write this.
The agent does this.

A real workflow — written in plain English on the left, executed by the AI agent on the right.

Your workflow description
Trigger
When this happens
A deal is marked "Closed Won" in Salesforce
Steps — in your own words
1
Look up the contact in Clearbit — get their company size, industry, and LinkedIn
2
Create an onboarding project in Notion using our "New Client" template, fill in their details
3
If the deal is over $10k, post to Slack #csm-team and assign a dedicated CSM. Otherwise skip.
4
Send a personalised welcome email from the account exec's Gmail
5
Log the win in our Google Sheets revenue tracker with deal value and close date
Agent executing now
Acme Corp · $24,000
Done ✓
09:41:02
Trigger received → Salesforce webhook
opportunity.stage = "Closed Won" contact.email = "sarah@acmecorp.com"
09:41:03
Step 1 → tool call: clearbit.enrich()
clearbit.enrich({ email: "sarah@acmecorp.com" }) ← company_size: 340, industry: "FinTech" linkedin: linkedin.com/in/sarah-k
09:41:04
Step 2 → tool call: notion.pages.create()
notion.pages.create({ template: "New Client", client: "Acme Corp", industry: "FinTech" }) ← page_id: abc-123 · created ✓
09:41:05
Step 3 → agent reasoning: is $24k > $10k?
Yes → taking the CSM path slack.postMessage({ channel: "#csm-team", text: "New enterprise win: Acme Corp ($24k)" }) salesforce.update({ csm: "Jordan Lee" })
09:41:07
Step 4 → tool call: gmail.send()
gmail.send({ from: "mike@company.com", to: "sarah@acmecorp.com", subject: "Welcome to [Co], Sarah!" }) ← delivered ✓
09:41:08
Step 5 → tool call: sheets.append()
sheets.append({ sheet: "Revenue 2026", row: ["2026-05-29","Acme Corp","$24,000"] }) ← row added ✓
Use cases

Real workflows,
described in seconds.

Every team has repetitive processes that eat hours every week. Just write them down.

Sales ops

Qualify and route every inbound lead automatically

The moment a form lands, the agent enriches the contact, scores the lead, routes it to the right rep, and creates the Salesforce deal — all before your rep has opened their laptop.

Try this workflow →
Form submitted
Typeform, HubSpot, or any webhook
Enrich with Clearbit
Company size, industry, tech stack
Tool call
Agent scores and routes
Reasons: AE for high-fit, nurture for low
AI reasons
Create Salesforce deal
Owner assigned, stage set, notes added
Tool call
Notify rep in Slack
Card with lead score and key context
Tool call
Under the hood

What makes it
actually different.

Dugong isn't a visual builder with an "AI" button bolted on. The AI is the engine — it reads, reasons, and acts.

Language is the interface

Your description is the workflow. No canvas, no blocks, no config panels. The agent reads what you wrote and figures out the rest.

Conditional logic for free

Write "if the deal is over $10k" or "unless they've already been contacted" — the agent understands the condition and branches accordingly, every run.

Failures handled intelligently

If a tool call fails, the agent doesn't just crash — it retries, tries an alternative approach, or flags the issue with full context. No silent breakages.

200+ tools, called directly

Mention Gmail, Slack, Salesforce, or Notion — the agent knows how to call them. No manual API setup. No OAuth headaches. Just name it.

Context carried across steps

Each step isn't isolated. The agent carries context from what it learned in previous steps — so it can personalise, adapt, and make sensible decisions throughout.

Full visibility into every run

Every tool call, every decision, every piece of data — logged in plain language so you always know exactly what the agent did and why.

Why Dugong

Other tools automate.
Dugong understands.

The difference isn't features — it's whether you're configuring a tool or just telling it what to do.

Capability Traditional automation tools Dugong
Creating a workflow Drag blocks, wire connections, configure each one Write it in plain English — the agent handles the rest
Conditional logic Add filter nodes, set field rules manually Write "if" — the agent reasons and branches live
Connecting apps OAuth per app, manual field mapping per step Mention the app name — already wired
When something breaks Silent fail — you find out from a user complaint Agent retries, adapts, and explains what happened
Handling edge cases You have to anticipate and build every path upfront Agent reasons through unexpected situations on the fly
Time to first workflow 30–90 minutes of setup and testing Under 5 minutes — just write it and run it
94%
Steps executed correctly first run
12×
Faster than building manually
3.2M
Agent-powered runs per month
67%
Fewer failures vs rule-based tools
200+ integrations

If you can name it,
the agent can call it.

Just write the app name in your steps. The agent handles auth, API calls, and data mapping automatically.

Gmail
Slack
Salesforce
Stripe
Notion
GitHub
HubSpot
Shopify
Airtable
SendGrid
Google Sheets
AWS
Linear
Google Calendar
Clearbit
185 more
Pricing

Simple pricing.
Free to start.

No credit card required. Upgrade when your workflows grow.

Starter
$0 /mo
For individuals automating personal workflows and side projects.

  • 5 active workflows
  • 500 agent runs per month
  • Plain English workflow builder
  • 20 core integrations
  • Full run logs and history
  • Community support
Get started free
Enterprise
Custom
For organisations needing custom models, security controls, and a dedicated partner.

  • Unlimited everything
  • Custom AI model tuning
  • SSO and SAML
  • Audit logs and permissions
  • On-prem deployment option
  • Dedicated success manager
Talk to sales

Stop configuring.
Start describing.

Join 4,000+ teams who shipped their first automation in under five minutes — just by writing it down.

Get started free — no credit card →