Meeting Prep Automation A one-page brief before every external meeting, in slack an hour before
An hour before every external meeting, the rep has a one-page brief: the company, the people, the history, the open items.
- Installed for you · one-time$249
- Run for you$197/month
- Custom build · this process$2,000–3,500 one-time
- Starts whenCalendar scan (hourly) + meeting event
Per team of up to ten reps and 400 external meetings a month; enrichment credits billed by the provider. Custom research sources or CRM objects are a custom build. Custom builds start at $2,000 site-wide; this band is for this process and its integrations.
Meeting Prep Automation is an automation Agentmelt installs in your own tools. The free template is a file you import yourself; the kit ($49) adds the setup guide and prompts. Installed for you costs $249 one-time and is live within two working days of access, with a recorded walkthrough and 30 days of fixes. Run for you costs $197/month, with setup and maintenance included. A custom build of this process is $2,000–3,500 one-time; custom builds start at $2,000 site-wide. No call is needed for any option. Written by Max Zeshut; last revised 2026-09-21.
Reference stack: Claude + n8n. Node names are on each step; the file is under the template.
Founder at Agentmelt
Reviews every build before it goes live; the workflow escalates to a person, never past one.
What is meeting prep?
Meeting prep automation watches the calendar and, for every external meeting, assembles the one-page brief a rep never has twenty minutes to write: the account and the deal from the CRM, the company’s site and recent news, the attendees’ roles and public profiles, past interactions and product usage, and — the AI agent’s part — the three angles worth raising in this meeting. The brief lands in Slack or the calendar event an hour before, and after the meeting a two-question prompt captures the outcome into the CRM. Reps walk in prepared; customer success and executives use the same workflow for renewals and board meetings.
- Reps walk into calls under-prepared because research takes twenty minutes and the calendar is full.
- Meetings start with ‘remind me who these people are’.
- The company announced a funding round last week and nobody on the call knew.
- The outcome of the meeting never makes it into the CRM.
- Each rep researches the same account separately.
If two of these are yours, this is the process to look at first. Free audit — or read on.
What it looks like once it runs.
Reps walk into calls under-prepared because research takes twenty minutes and the calendar is full. The workflow watches the calendar, and for every external meeting assembles a one-page brief from the CRM, the company's site and news, LinkedIn-level role data, past interactions and product usage — then has the AI agent write the three angles worth raising. It lands in Slack an hour before the call.
- Every hour Meetings in the next 24 hours with outside attendees are found.
- Attendees and their company are matched in the CRM; deal stage, open tickets and last interactions are pulled.
- Their site, recent news and hiring signals are researched; each attendee's role and public profile are noted.
- T−60 min The brief is sent to the rep and attached to the calendar event. After the meeting, one question logs the outcome.
Research is skipped or shallow. Reps miss that the prospect just raised a round, that a colleague spoke to them last quarter, or that the account is at 90% of its plan limit. Calls open with questions the CRM already answered.
Every external call has a brief: who is attending and what they do, what the company does and what changed recently, the relationship history, live account signals, and three suggested talking points. Reps spend the twenty minutes on the call, not before it.
Trigger, then 7 steps.
All seven steps run without anyone; a person sees only what the guardrails escalate.
Calendar scan (hourly) + meeting event
Find upcoming external meetings
Meetings in the next 24 hours with attendees outside the company domain; internal-only meetings are ignored.
Identify attendees and account
Contacts and company matched in the CRM; deal stage, owner, open tickets and last interactions pulled.
Research the company
Company site (about, product, pricing pages), recent news, funding and hiring signals from enrichment and news APIs; product usage or billing signals for existing customers.
Research the people
Role, tenure and public professional profile per attendee from enrichment providers; recent public posts where available.
Write the brief
One page: company in two lines, what changed recently, attendees and roles, relationship history and open items, live account signals, and three suggested angles tied to the evidence. Nothing without a source.
Deliver
Posted as a DM to the rep an hour before, and attached to the calendar event and the CRM deal.
Capture the outcome
After the meeting a one-question prompt ('how did it go, next step?'); the answer is logged to the CRM so the next brief includes it.
No step waits for a person.
What the workflow hands to someone, by rule:
- Only public and first-party data; no scraping behind logins, no personal data beyond professional role.
Every external call has a brief: who is attending and what they do, what the company does and what changed recently, the relationship history, live account signals, and three suggested talking points
Every external call has a brief: who is attending and what they do, what the company does and what changed recently, the relationship history, live account signals, and three suggested talking points.
No decisions needed. Anything the guardrails flag is handed to a person; the rest ran alone.
Each pattern page explains it in plain words and lists every automation that uses it.
The template is built on n8n (how the n8n AI Agent node works); the same steps run on Make, Zapier or plain code. The tool is chosen to fit your accounts, you own the result, and the template comes in all three formats.
Data it touches
- Calendar (Google Workspace, Microsoft 365)
- CRM (HubSpot, Salesforce, Pipedrive)
- Enrichment and news (Clay, Apollo, Clearbit, news APIs)
- Product usage / billing for existing accounts
Guardrails
- Only public and first-party data; no scraping behind logins, no personal data beyond professional role.
- Every statement in the brief carries a source; the agent is instructed to omit rather than guess.
- Briefs go only to the rep and the CRM; they are not forwarded externally.
- Enrichment credits are spent only for meetings that survive the external-attendee filter.
What a good brief contains
Not a dossier — one page a rep reads in three minutes. Company: what they do, size, what changed in the last quarter. People: role, tenure, anything public and relevant. History: every touch your company has had, open tickets, open deals. Signals: usage, plan limits, renewal date for customers; intent signals for prospects. Angles: three specific things worth raising, each tied to one of the above. The agent's discipline is to write only what has a source.
The outcome loop
The post-meeting prompt is the part reps like least and the part that makes the next brief better. One question, one line, logged to the CRM — and the next person to meet that account starts with it. Teams that keep this loop running end up with a CRM that reflects reality, which no amount of nagging achieves.
What it connects to.
| Tool | Role in this workflow |
|---|---|
| n8n | Calendar scan, data assembly, delivery, outcome capture |
| Claude | Brief writing with sourced angles |
| HubSpot / Salesforce | Relationship history |
| Clay / Apollo | Company and people data |
Want this running without building it?
$197/month
We set it up in your tools, run it on our servershost it on our n8n cloud (or deploy it to your own n8n, Make or Zapier), watch it, and fix it when something changes. Setup included, cancel monthly; the automation stays yours if you leave.
$2,000–3,500 one-time
Your systems, your rules, your edge cases. A one-off build delivered into your accounts to keepon Claude and n8n, delivered into your accounts to keep, with documentation and a recorded walkthrough.
Per team of up to ten reps and 400 external meetings a month; enrichment credits billed by the provider. Custom research sources or CRM objects are a custom build.
Also sold one-time, installed in your own accounts, as part of the executive assistants package and the project managers package and the sales teams package — do it yourself $49 · installed for you $249 · done for you $490.
When this becomes a custom build.
The subscription covers the standard version — $197/month, setup and maintenance included. Three things move it to a custom build ($2,000–3,500 one-time), delivered into your accounts to keep. If one of them is you, say so on the audit and the plan prices both.
Custom research sources — your own data warehouse, product usage, support history.
CRM objects beyond contacts and companies, such as opportunities with custom fields the brief has to read.
Teams above ten reps or 400 external meetings a month.
Running the standard version first is the usual path: the exceptions it logs in the first month are the scope of the custom build, with your own numbers. How custom builds work.
Frequently asked questions.
Does it work for customer success and executives too?
Yes — the same brief with account-health and usage signals for CSMs, and a lighter version for executives' external meetings.
Which calendars and CRMs?
Google Workspace and Microsoft 365 calendars; HubSpot, Salesforce, Pipedrive and Attio CRMs.
Is it compliant with privacy rules?
The brief uses public professional information and your own first-party data. No personal data beyond role is collected or stored, and enrichment providers are used within their terms.
Does meeting prep automation work for customer success and executives?
Yes — the brief pulls the same sources with a different emphasis: usage, tickets and renewal dates for a customer success manager; the relationship history, the numbers and the news for an executive. The three angles are written for the role reading them.
Which calendars and CRMs does it connect to?
Google and Microsoft calendars; HubSpot, Salesforce and Pipedrive; Slack for delivery; news through a search source; roles through an enrichment provider. Custom research sources — your own warehouse, product usage, support history — and CRM objects beyond contacts and companies are custom builds.
Is researching meeting attendees compliant with privacy rules?
The brief uses public professional information — the company’s site, public profiles, news — and your own CRM records, the same sources a rep would open by hand; it does not scrape personal data or store profiles beyond the brief. Enrichment providers are used under their terms, and the brief is deleted with the meeting on request.
What this blueprint is built on.
Vendor documentation the steps rely on, and the rules the guardrails are written against.
- HubSpot — API overview developers.hubspot.com/docs/api-reference/latest/overview
- Apollo.io — API documentation docs.apollo.io/
- n8n docs — AI Agent node docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/