Services · AI Automation
An AI automation
agency of one.
The output of an agency without the overhead. One senior engineer who scopes, builds, and ships your automations directly - n8n, Make, and custom code with OpenAI or Claude doing the thinking. No account managers, no markup on a junior's work.
What I automate
Sales and lead ops
Capture, enrich, score, and route leads; draft personalized outreach that a human approves before it sends.
Document processing
Invoices, contracts, and forms turned into clean structured data with validation and a human review queue.
Support and back office
Ticket triage, tagging, draft replies, and routine internal requests handled with human-in-the-loop control.
Data sync and reporting
Keep your CRM, sheets, and databases in step, and turn raw activity into reports that land in inboxes on schedule.
Why solo beats an agency here
You talk to the builder
No game of telephone through an account manager. The person scoping the work is the person writing it.
No agency markup
You pay for engineering, not for a sales team and a layer of management on top of a junior.
Senior judgment
I will tell you what not to automate. Half the value is killing the ideas that are not worth the maintenance.
Built to last
Error handling, monitoring, and docs so the automation does not quietly break the week after handoff.
What this looks like in practice
Worked examples of builds like this: the problem, the workflow, what the AI does and where people stay in the loop.
A Monday KPI brief that explains last week's numbers instead of just charting them
Computes last week's KPIs in SQL, checks the data is complete, finds what moved and why, and posts a short written brief to Slack at 07:00 every Monday.
Shopify / BigQuery or Google Sheets / GA4 and the ad platform APIs / HubSpot / Accounting and payments
An agent for the shared inbox: every email sorted, answered or filed into the right system
Reads every email in your shared mailboxes, sends orders and invoices into the right system, drafts replies for approval, and flags fake bank-detail changes.
Microsoft 365 shared mailboxes / Gmail and Google Workspace / The ERP (Business Central in this example) / Teams or Slack / The AP flow and accounting system
Commercial insurance submissions assembled from proposal forms, loss runs and property schedules
Reads a client's proposal forms, loss runs and property schedules, reconciles them, and drafts one submission per insurer for the account handler to check and send.
Broker management system (Acturis, Applied Epic, Vertafore) / Outlook / Excel schedules of values / Insurer portals and e-trading / BiPRO interfaces (Germany)
Customer orders from email, PDF and WhatsApp, entered into the ERP without retyping
Turns emailed PDFs, Excel forms and WhatsApp photos into sales orders in SAP Business One or NetSuite, and sends only the doubtful lines to a rep.
Outlook and Microsoft 365 / WhatsApp Business Platform / SAP Business One / NetSuite / Excel order forms
Every inbound lead researched, scored and routed before a rep opens it
Researches and scores every inbound lead against your rubric, catches existing customers, routes by territory and capacity, and replies with a booking link.
HubSpot / Salesforce / Enrichment provider (Clay or Apollo) / Cal.com or Calendly / Slack
Fixing n8n, Zapier and Make automations that report success and did nothing
Audits inherited n8n, Zapier and Make automations, then adds a run ledger, idempotency keys and a daily reconciliation so a green run means the work was done.
n8n / Zapier / Make / Postgres / Slack
Law firm intake that runs the conflict check before anyone calls the prospect back
Captures every inquiry, after hours too, searches conflicts across parties and their groups, flags deadlines, and prepares the engagement letter for a lawyer.
Practice management system (RA-MICRO, Clio, LEAP or Actionstep) / Outlook and Microsoft 365 / Website form and chat / Calendar / iManage
PDFs into rows: document data entry that sends only the doubtful fields to a person
Reads delivery notes, proofs of delivery and forms from an inbox or folder, checks each field against your TMS or ERP, and asks a person only about doubtful values.
Gmail and Google Drive / Excel and Google Sheets / TMS or ERP / OCR or vision model / Review screen
Frequently asked questions
Are you actually an agency?
No, and that is the point. I am one senior engineer who does the work end to end. When you hire a typical AI automation agency you pay for account managers, sales staff, and a margin on top of the junior who actually builds your flow. With me you talk to and get the person writing the code. For most SMB and startup automation work, that is faster and cheaper, not slower.
What do you automate?
Repetitive, rules-plus-judgment work: lead capture and enrichment, outreach personalization, document processing, invoice and contract extraction, support ticket triage, candidate screening, reporting, onboarding, and data sync between systems. If a person spends hours a week moving information between tools and making routine decisions, it is a candidate.
What tools do you build on?
n8n (self-hosted or cloud), Make, and custom code, with OpenAI or Anthropic Claude doing the reasoning steps. I pick the lightest tool that fits - sometimes that is a no-code platform, sometimes a small custom service. I am not tied to one vendor, so the recommendation is honest.
How is this different from buying an off-the-shelf SaaS tool?
Off-the-shelf tools handle the common 80%. Custom automation handles the 20% that is specific to your business - your data, your rules, your edge cases - which is usually where the real time savings hide. I often combine both: a SaaS tool for the generic parts and custom glue for what makes you you.
How fast can you ship, and what does it cost?
A focused automation ships in 1-3 weeks. A larger multi-workflow system is 3-8 weeks. Pricing runs $3.5K-$60K depending on scope, with hourly retainers for ongoing work. Every project starts with a free 30-minute call where I tell you honestly what is worth automating first.
Related: AI workflow automation · n8n developer · AI agent development