London HR Startup
From manual workflows to a fully agentic business
Replaced spreadsheet-driven operations with a network of AI agents and MCP servers, freeing the team to scale without proportional headcount.
The challenge
A fast-growing London HR startup was buckling under manual processes — candidate sourcing, interview scheduling, offer management, and client reporting were all spreadsheet- and inbox-driven. The founders wanted to triple revenue without tripling the team.
What we built
Mapped every customer-facing and back-office workflow over a 2-week discovery; ranked each by automation feasibility and ROI
Stood up internal MCP servers exposing Greenhouse, HiBob, Slack, Notion and the company data warehouse as tools available to AI agents
Built specialised agents for sourcing, scheduling, candidate comms, and weekly client reporting — each with explicit human-in-the-loop checkpoints for sensitive actions
Embedded AI assistants directly inside the team's existing tools (Slack, Notion) so adoption was friction-free
Defined an internal AI development lifecycle: prompts and agent definitions versioned in Git, evaluated against golden datasets, deployed via CI
Outcomes
~70% reduction in time spent on candidate ops admin
3× pipeline throughput within 90 days, no headcount added to ops
Client-reporting cycle: from 6 hours/week → 20 minutes (human reviews AI draft)
Founders refocused on growth and product, not coordination
Ready to Automate with AI?
Schedule a free consultation with our team of ex-AWS specialists. We'll discuss your challenges and outline how AI-powered automation can transform your workflows—no commitment required.
