You buildAn ingest and rough-cut pipeline
Applied AI for GTM teams
Build a multimodal agent workflow on your own pipeline data, launch it in the revenue stack your team already works in, and measure what it changed.
Free
8 modules
6 weeks
Intermediate
What you will learn
- Map your go-to-market workflow end to end and record a baseline you can defend.
- Build an agent workflow on your own pipeline data with current multimodal models.
- Connect approved prompts and automations to your CRM and marketing stack.
- Score opportunities, forecast, and read churn and expansion signals.
- Measure time saved and cost per output against the baseline you started from.
- Finish with a completion record: the brief, the build, the launch and the result.
Course content
Method step 1, Profile
Map the whole revenue process once, then choose the one part of it you will rebuild.
- Map your customer journey end to end
- Find the high-value use cases
- Record your baseline on time, cost or quality
- Decide where a human stays in the loop
Method step 2, Build
The multimodal agent loop, applied to research a rep would otherwise do by hand.
- Build the ICP from your own closed-won data
- Persona and account research
- Competitive and intent signals
- Verify a source before it reaches a rep
- The account brief
Method step 2, Build
One source message, adapted by the workflow to every channel you run.
- Positioning and the offer
- Channel adaptations from one source message
- Build the content calendar
- Email sequence and landing page
- Ad variants and the review step
Method step 2, Build
Prospecting, call preparation and follow-up, on the briefs from module 2.
- Prospecting and personalization at account level
- Call preparation from the account brief
- Call summaries and next steps
- Qualification and objection handling
- Follow-up a rep will actually send
Method step 3, Deploy
The workflow goes live in your stack. Launching it completes the course.
- Connect the approved prompts to your CRM
- Marketing automation and meeting tools
- Handoff rules and who owns each step
- The launch checklist
- Run the first week live
Method step 4, Measure
What the workflow tells you about the pipeline once it has been running.
- Opportunity scoring on your own pipeline
- Pipeline hygiene rules
- Forecasting with the agent in the loop
- Churn risk and expansion signals
- The executive report
Method step 4, Measure
Measure the same thing you measured in module 1, and state the difference.
- Design the test
- Measure time saved and cost per output
- Quality review against a rubric
- The outcome sheet
Method step 5, Document
The controls that let it run without you, and the record that proves it ran.
- Approved-data rules and brand controls
- Disclosure and human accountability
- Document the workflow for a successor
- Maintenance, and how to judge a replacement tool
- Assemble the completion record
- Publish it and book the review
Requirements
- One go-to-market workflow you own, and permission to change it.
- Access to your CRM and the marketing tools your team already uses.
- About four hours a week for six weeks.
- Comfort reading a spreadsheet. The labs supply every prompt and template.
About this course
This course is for the technical layer of go-to-market: marketing ops, RevOps, growth analysts and GTM engineers. It treats marketing, sales and revenue operations as one operating system rather than three separate subjects, which is the gap across every comparable course on the market today.
The method is the one every course here runs on. You profile one workflow you own and record what it costs today. You build the agent workflow on your own pipeline data through eight guided labs. You launch it into the revenue stack your team already works in. Then you measure the same thing again and document what changed.
The capstone is a traceable workflow rather than a set of prompts. It carries an ICP brief, campaign assets, a sales sequence, an automation diagram, a measurement plan and the controls that let it run without somebody watching it.
Roan Weigert records the core lessons. The agent loop at the centre of module 2 is the subject of his AGI Summit SF 2026 keynote, The Multimodal Agent Loop: Orchestrating AI for GTM.
Common questions
It is free. The first module of every course opens instantly, and one free account unlocks the rest of that course. Everything on this site is free to use.
A course completes when your workflow runs live and you have measured it. You record a baseline in module 1, launch the workflow into a working environment, then measure the same thing again. That pairing is what makes the completion record worth sharing.
Yes. The first module of every course plays for everyone, with a free account needed only from module 2.
Name, role, organization, and a few questions about the workflow you want to improve. It takes about a minute, and it is what lets the guided labs use your own workflow as the project.
One workflow you own, permission to change it, and the tools your team already uses. Applied AI infrastructure also assumes access to a GPU cloud account, and AI starter for small business runs on everyday business tools.
A one-page record inside the course. Before you launch, you note a baseline on time, cost, or quality. After you launch, you measure again. The sheet holds both numbers and the difference between them.
Instructor
Roan Weigert
Records all five courses
Hackathon judge and AI content creator, and host of the AI Insights San Francisco podcast. Writes this curriculum and records every core lesson.
Other courses
The other four courses
Each one takes a different kind of work through the same five steps. Pick the one closest to your job.
You buildAn AI use policy your team runs onAI literacy, ethics and data compliance
A working AI policy for your team, covering what the tools may touch and who checks it.
You buildModel serving on GPU cloud
You buildOne assistant for your busiest taskAI starter for small business
A short course to one measurable first win, built for owners and operators.
Start with module 1
The GTM AI operating model
Open to everyone, with no account. You finish it holding a baseline and use-case map.