SaaS inbound lead relay
Demo requests are captured, scored, routed and pushed into CRM with owner alerts.
Case note
The implementation was treated as a small operating system: visibility first, ownership next, automation only after the workflow was clear.
The starting point
The sales team was receiving demo requests from the website, paid campaigns and referral pages. The leads were visible, but not operationally clean: someone had to check inboxes, copy data into CRM, decide priority and message the owner. Response quality depended on who saw the lead first.
The important signal was not that the team was working badly. The issue was that work depended on memory, copied data, parallel system checks and priority decisions without a shared source of truth. The first value was turning invisible work into a visible workflow.
The implementation
Ductio connected the form intake to a structured lead record, added fit and urgency scoring, created or updated the CRM entry and posted a concise owner alert with the next action. The first version stayed deterministic, with AI used only to classify free-text context and summarize the lead.
The scope stayed deliberately small. Rules cover repeatable work, AI summarizes or classifies where free text adds context, and sensitive decisions remain in human review. AI as support inside the process, not as autopilot.
What was used
Tooling was chosen from the process outward, not from a pre-decided technical preference. Each piece needed a clear owner, a stable integration path and a simple way to inspect errors.
In practice, the build combined Next.js, Supabase, CRM API, AI classifier, Slack, n8n. The tools visible to the team stayed close to their daily work, while integration logic was documented and kept separate from sensitive commercial decisions.
The improvement showed up in daily work.
Rather than treating the result as a dashboard, the team felt it in three specific moments: less manual preparation, less context hunting, and fewer doubts about who needed to act.
Lead prep: Average prep per qualified lead moved from 35 min to 5 min.
Admin load: Manual routing and copying moved from 9 h/wk to 2 h/wk.
Visibility: Pipeline visibility score moved from Daily to Live.
What changed after launch
The team moved from batch review to near real-time triage. Reps started from a clean CRM record and a short context note instead of assembling the information themselves.
The most valuable change was operational calm. The team stopped chasing fragments and started working from a shared sequence: intake, context, decision, action and evidence. 7h/week saved
The workflow in one line
How it was built
The workflow uses a web form/API trigger, Supabase for the lead source of truth, an AI classification step for message context, CRM create/update logic, Slack notification and a weekly lead digest.
The stack was pragmatic: Next.js, Supabase, CRM API, AI classifier, Slack, n8n. Tools were chosen for ownership, integration and maintainability, not for theater. The result is a system the team can understand and operate.
What was delivered
- Form intake
- Lead database
- CRM sync
- Fit scoring
- Owner alert
- Lead prep moved from 30-45 minutes to under 5 minutes.
- New opportunities became visible near real time.
- Manual lead admin dropped by roughly one working day per month.
