Marketing Operations & AI Automation

AI and CRM systems for real sales work.

I built AI phone agents, CRM workflows, call-auditing reports, and scheduled publishing for a U.S. marketing agency. My background in B2B sales helps me connect those systems to qualification, booking, and follow-up.

I started on the phones. Seven years in B2B sales and revenue operations taught me what teams need when a lead comes in, a prospect asks for a callback, or a deal gets stuck.

Christian PeralesBased in Mexico | English and Spanish
Open to remote roles, projects, and ongoing work

AI systems resume | Sales operations resume

What I actually do

Phone systems and AI voice agents

Inbound and outbound agents that answer, qualify, handle objections and book straight into the calendar. Transfer rules, call scripts, the lot.

CRM and automation

GoHighLevel workflows, pipelines, lead routing, and data hygiene. Make.com, webhooks, and API integrations connect the CRM to the rest of the operation.

Call auditing and reporting

Call transcription and scoring workflows that turn recordings into coaching reports for team review.

Content, ads and creative

Scheduled publishing, short-form video ads, and landing pages. Experience with paid social and search, SEO, and Local Services Ads.

Web and mobile app development

Websites and applications, from a dating app for Spanish speakers to a driving academy's booking platform. Selected projects and concept work are shown below.

Phone systems

CRM & automation

Report format (illustrative)

Ads & creative

Apps & sites

Explore the systems, reports, creative work, and websites below.

Let's start with the work you need owned and a clear scope for getting it done.

How the systems connect

Lead capture, follow-up, call review, and reporting work better when the systems share the right information.

01 · Capture

AI voice agent answers, qualifies, books straight into the calendar.

02 · Route

CRM workflows organize contacts and route follow-up.

03 · Score

Call transcription and scoring support coaching reports.

04 · Feed

Approved content is queued for scheduled publishing.

05 · Watch

Monitoring flags failures for investigation.

Built with GoHighLevel, VAPI, Make.com, and custom integrations.

Talk to an AI phone agent I built

Try the voice demo in your browser. Ask about my work, describe what you need, or try its qualification and booking flow. This demo introduces my work. The case studies below describe the systems I built for agency operations.

Runs in your browser, needs a microphone. Ends on its own after five minutes.

Worth trying

Ask what he actually does
Ask if he could run your phones
Ask what he charges
Say you're not hiring right now
Book a time

Call ends in 5:00

Transcribing what it hears you say

Your side of the call appears here, live, as you speak.

7+years in B2B sales and operations

20+partner accounts audited

3core platforms: GHL, VAPI, Make

7selected sites and projects

$200Kmonthly revenue in a sales operation I helped scale

Selected systems and responsibilities

Examples from my previous agency and sales-operations work.

Inbound rep & after-hours answeringAI phone agents on live customer calls

The follow-up nobody has time forCallback scheduling and retry logic

A QA analystCall auditing across 20+ partner accounts

A social media managerScheduled content publishing

A video editorAround thirty short-form ads, made in house

Workflow monitoringMonitoring, so automations fail loudly

AI phone agents on live customer calls

Problem

The team needed a consistent way to handle incoming calls and outbound follow-up.

Built

I built inbound and outbound voice agents with qualification logic, human-transfer rules, and calendar booking connected to GoHighLevel. Call transcripts informed prompt and script revisions.

Outcome

Connected call outcomes, contact records, and appointment booking in one workflow.

Diagram of the post-call automation: the call ends, the system reads what happened, creates or updates the contact, saves the call notes, then sorts into ten outcomes including booked, not a fit, voicemail and stopped at reception. — The post-call workflow reads the outcome, updates the contact, saves notes, and routes the next action. Booking, callback, voicemail, and do-not-call outcomes follow different paths.

Diagram of the outbound dialer's opening sequence: the run kicks off, pulls today's appointments, goes through them one by one, notes who is already booked, marks who still needs a call, checks for promised callbacks, then decides whether to call or skip. — The dialer's opening steps check appointments and promised callbacks before deciding which records should move into follow-up.

These diagrams document the systems from my prior agency work, with module names shown beneath each step.

The whole outbound dialer: about forty-five modules ending in a router that fans out to separate AI call agents. — The outbound dialer on the Make canvas, with branches for different call types.

Post-call automation: a router fanning out to a separate branch for each call disposition, each one writing back to the CRM. — Post-call routing writes the disposition back to the CRM and determines the next action.

Click either to open it full size.

Scheduled callbacks and follow-up

Problem

A requested callback needs a recorded time and a clear follow-up action. Leaving it to memory makes the process hard to manage.

Built

I built a workflow to capture requested callback times, schedule follow-up, and apply retry rules by outcome. Attempts were written back to the CRM, with checks intended to reduce duplicate follow-up.

Outcome

Callback requests became scheduled workflow steps with an attempt history in the CRM.

The callback loop automation: a scheduling chain feeding a large fan-out of retry branches. — The callback workflow combines scheduling, outcome checks, and retry branches.

Automated call auditing across 20+ partner accounts

Problem

The agency needed a repeatable way to review how partner teams handled inbound leads and turn those findings into coaching.

Built

I built a pipeline to collect recordings, transcribe calls, apply scoring criteria, and produce coaching reports. Transcript checks and human review were part of the process.

Outcome

Built call-auditing and reporting workflows used across 20+ partner accounts.

Illustrative call-handling report; fictional company and example scores. — Illustrative report showing the format and scoring categories. The company, figures, and conversation examples are fictional. Open the PDF.

Scheduled content publishing

Problem

The team needed a reliable process for preparing, approving, and scheduling content.

Built

I built a content calendar and scheduler for social posts and Google Business Profile updates, with room for timely additions.

Outcome

Approved posts could be queued ahead of time, with monitoring to flag failed publishing attempts.

Ad creative produced in house

Problem

The agency needed new ad concepts and landing pages to support campaign testing.

Built

I produced short-form video ads and landing pages, using AI-generated scenes and cast where appropriate.

Outcome

Produced multiple creative concepts and variations for campaign review and testing.

Monitoring, so automations fail loudly

Problem

A failed automation can go unnoticed unless the team has a way to see it.

Built

I built workflow health checks and alerts, including external heartbeat checks to help identify an unavailable server.

Outcome

Added failure alerts and run checks to support troubleshooting.

Before the systems

Scaling a remote B2B sales operation

Role

Helped scale a remote B2B sales operation from roughly $10K to over $200K in monthly revenue. Owned the GoHighLevel build, lead routing, follow-up sequences, and data hygiene, and supported scripts and rep coaching.

Scale

GoHighLevel supported the sales operation's segmentation, routing, follow-up, and rep handoffs. That experience shaped how I approach CRM design.

Authorize.net transaction search showing 9,561 transactions and a net total of USD 2,247,326.98 processed between January 2023 and August 2025. — Archived business transaction summary, January 2023 to August 2025. My responsibilities covered CRM and sales operations.

What I'd do differently

One lesson from that work: review call recordings early. They reveal objections and handoff problems that a pipeline view alone can miss.

Ad creative, produced in house

Selected video work I wrote, produced, and edited. AI-generated scenes and concept work are identified in the descriptions.

The Graveyard · 67s concept film
A man walks a cemetery at night reading headstones. Each one is a dead company, with the cause of death on the stone. Rapid Response Restoration. 1.8 stars, four reviews. Est. 2015, closed 2022. "Nobody could find us online." He writes each one down.

Entirely generated: the location, the character, the fog, the crow. Same man and same graveyard across the whole run, which is the part that usually falls apart. The pitch is never spoken. You work out what's being sold from what killed everybody.

Size Matters · 43s spot, credit repair
Two women at a bar, mid-conversation, and you think you know exactly what they're talking about. Then the card lands: Size matters. Credit matters more. Written for a friend's business.
The whole ad is one bait and one turn. It works because it borrows an assumption the viewer brings with them, spends forty seconds letting them sit in it, and spends the payoff somewhere else entirely.

Same Name, Same Script, Sold Four Times · 33s
Cut from real podcast footage rather than generated. The format does the work: two people at microphones reads as a conversation you're overhearing, not an ad you're being served, and that buys enough patience to land an actual argument.

The argument being that the leads these owners pay for are resold to their competitors. It names the resellers, shows the price difference, and closes on "stop buying competitors' leftovers."

You Become Who You Surround Yourself With
Opens cold on a black card, then hands the rest to real customers.

The Marketing Graveyard
The same idea as the film above, cut as motion graphics. One concept, two executions.

Keyword Theft
Explainer. Turns an invisible problem into something you can watch happen.

Lead Relay
AI-generated cast and scenes, cut as a straight direct-response spot.

How I work

I use AI heavily and build review steps around it. For a new project, I agree on the scope, test the workflow, and make exceptions visible so the team knows what needs attention.