Case study · AI automation
A visual bot builder and automation platform
We engineered a bot builder and workflow automation platform. Users drop triggers, actions and AI steps onto a canvas, connect them to the tools they already use, and the flow runs by itself.
- Client
- Automation SaaS
- Year
- 2024
- Our role
- Lead engineering
- Stack
- Workflow engine, Laravel, Queues
The problem
What needed fixing
Small teams want automation but can't write code, and the well-known tools are built and priced for developers. They needed something a business owner could set up in an afternoon.
The approach
How we built it
- 01
A flow is just data
Each workflow is stored as a graph of typed steps. The runner works through it one step at a time and logs, retries and times every step on its own.
- 02
Integrations are blocks
Adding a service means adding a block with inputs and outputs. The canvas and the runner don't change.
- 03
Bots on the same engine
A chatbot is a flow that starts with a message. Same builder, same logs, same retries.
The outcome
Where it landed
Live, with teams building their own bots and automations without a developer.
- Canvas builder
- No-code
- Canvas builder
- Built into every flow
- AI steps
- Built into every flow
- Running today
- Live
- Running today
Workflow engine · Laravel · Queues · Webhooks · OpenAI
Services used
We can do the same for you
- AI workflow automationHours of copy, paste and chase turned into flows that run on their own, with AI steps where judgement is needed.
- Chatbots & voice agentsChat and voice agents on WhatsApp, web and phone that answer, book and hand over to a person at the right moment.
- Laravel & PHPSecure, maintainable Laravel applications, upgrades and rescues, from a team that has written PHP since 2008.
Start here
Got a workflow that eats your team's week?
Tell us about it. Hussain reads every message himself and replies within a working day, usually with a question or two.