n8n saves Huel over £100,000 in SaaS costs and 1,000+ hours of manual work through enterprise-wide AI automation
Despite early adoption of tools like ChatGPT, Huel found that standalone AI assistants left value siloed within each individual tool with no way to connect AI to the systems and processes employees relied on daily. Many existing SaaS tools were also expensive, specialized, and too rigid to adapt as business needs evolved.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Employee request in Slack
An employee submits a question or request via an AI assistant embedded in Slack.
In nine months, Huel saved more than 1,000 hours of manual work and cancelled approximately £100,000 worth of annual software licenses by replacing SaaS tools with custom-built n8n workflows. The organization grew to nearly 200 live workflows with over 100 active users.
What failed first
Standalone AI tools like ChatGPT kept value trapped within individual tool boundaries, preventing AI from integrating with operational systems. Existing SaaS tools were too specialized and rigid to consolidate or adapt across departments.