Vincent Eliot
Building autonomous AI workflows, AI chatbot with n8n.
New to Contra
Vincent is ready for their next project!
Lead Research & Qualification workflow
Sales teams spend hours every week checking a lead's website, tracking down their LinkedIn page, guessing headcount, and figuring out if they're even a fit before a rep sends a follow-up.
By the time that's done, the lead has gone cold, and weak ones (tiny local shops, solo founders, wrong region) are already sitting in the CRM.
I built an automated system that handles this.
A prospect submits their website and email through a form, and n8n passes the website to a custom AI Agent I built in Relevance AI.
The agent runs 3 steps:
1. Google searches for the company's LinkedIn page and has an LLM pull out the single most likely URL.
2. Scrapes that profile, uses an LLM to extract business type, headcount, and location.
3. Runs a final LLM step against the client's own qualification rules (no local-only businesses, no sub-5-employee companies, US/Europe only) and returns a plain "qualified" or "unqualified."
N8n takes that answer and routes the lead automatically.
Qualified leads get created as HubSpot contacts, ready for outreach.
Unqualified ones get logged to a Google Sheet for nurture instead of getting lost.
What used to take 10-15 minutes of manual digging per lead now happens in seconds, applying the same criteria every time.
0
31
API Integration: Connecting the Modern Business Stack
Most businesses don't run on one system.
They run on a patchwork: a CRM here, a payment processor there, analytics in one place, communication tools in another, none of it talking to the rest.
Data ends up siloed inside each tool, so someone re-enters the same customer details three or four times a week, and nobody can point to a single source of truth when a number gets questioned.
A central orchestration layer connects the entire tech stack through APIs and webhooks, handling authentication, transforming data into the format each system expects, and catching errors before they turn into bigger problems.
Every tool stays in sync automatically, without anyone manually pushing data from one place to another.
The business ends up with one connected ecosystem. Duplicate data entry and manual syncing both go away, and there's room to add whatever platform comes next without rebuilding the whole thing.
It also changes how a business sees the person who built it: someone who can architect the whole stack, not just patch one tool at a time.
Remaining patterns to watch: the closing sentence still leans on a mild contrast to land its point, but it's carrying a real claim (the person's perceived role) rather than just adding weight, so I left it.
0
40
n8n Workflow Automation: Visual Workflow Engineering
Most off-the-shelf AI tools work fine until a process gets complicated.
A business rarely runs one clean step from trigger to outcome. It runs across a CRM, a database, email, Slack, and a spreadsheet someone still updates by hand, all at once, with different rules depending on the situation.
A generic chatbot plugin isn't built for that. The business needs custom logic, branching that adapts to different conditions, and orchestration that doesn't fall over the first time something unexpected happens.
This workflow is a production-ready automation architecture, engineered visually so every connection between APIs, databases, AI agents, and business tools is mapped out on purpose.
Conditional logic decides what happens next.
Scheduled triggers keep things running without anyone remembering to press a button.
Multi-branch workflows handle the cases that don't follow the simple path, and the whole thing holds up in production.
The result is a system shaped around how the business actually works, not forced into a generic template. It's maintainable, so a client can hand it off to a technical partner who understands the complexity underneath it, not just the surface.
The workflows stay transparent enough to debug when something changes and solid enough to scale as the business grows.
Remaining patterns to watch: none strong enough to act on alone; the passage reads clean on a second pass.
0
45
CRM Automation — Lead Enrichment & Qualification
Sales teams lose deals in ways that rarely show up on a scoreboard.
A rep spends an hour chasing a lead that was never going to convert.
Prospects get researched by hand, one browser tab at a time.
Follow-up lands a day late because nobody was sure who to call first.
Leads sit in the CRM with no context, so prioritization turns into a guessing game:
- Which leads are actually worth calling today?
- Which ones need more research before outreach?
- Which ones are already cooling off from the wait?
This workflow removes the guessing.
The moment a lead comes in, AI enriches it with company and contact data, scores it against your qualification criteria, segments it, and triggers the right follow-up action on its own.
No manual research, no waiting for someone to get to it.
Reps end up spending their time only on leads worth chasing.
Response time drops from hours to minutes, and because every lead gets the right action as soon as it arrives, conversion rates move in the right direction too.
Less guesswork for the team, more closed deals at the end of the month.
0
49