Sales

Personal AI assistant with custom memory for daily sales support

Use AI to create a personal sales assistant whose “memory” is intentionally designed and preloaded with structured context—ICP details, qualification criteria, funnel stages, CRM field definitions, messaging angles, proof points, and ongoing deal notes—so every new chat starts grounded in the same sales reality and produces consistent, sales-ready output without re-explaining context each time.

Why the human is still essential here

A human defines and validates the ICP, sales process, and approved messaging; chooses what data to include; ensures sensitive CRM details are handled appropriately; and keeps the context up to date as products/processes change. AI accelerates retrieval, drafting, and reasoning using that curated context, but humans own strategy, accuracy, and customer relationships.

How people use this

RAG-based personal knowledge retrieval

A custom assistant retrieves relevant snippets from the seller’s notes, deal history, and playbooks using embeddings so responses reflect the seller’s real context.

OpenAI API / LangChain / pgvector

Personalized message drafting from stored preferences

AI drafts emails and LinkedIn messages in the seller’s voice by referencing stored preferences (tone, offers, discovery questions) and prior interactions.

ChatGPT / Claude

Daily agenda and deal recap from calendar + notes

AI produces a morning brief that summarizes today’s meetings, recaps the latest deal context, and suggests prep questions using the assistant’s memory.

Microsoft Copilot / Google Gemini

Claude Project “Sales Thinking Partner”

Create a dedicated Claude Project with your ICP, qualification rules, funnel definitions, objection handling, and key proof points so every new prompt starts with the same sales brain.

Claude (Projects)

Convert onboarding docs + sales deck into Markdown context files

Have AI turn your sales onboarding doc and deck into structured Markdown sections (ICP, stages, talk tracks, proof points) optimized for reuse in an AI workspace/project.

Claude / ChatGPT

Generate a CRM field glossary with API slugs

Export your CRM property/field list and use AI to produce a readable data dictionary (definitions, allowed values, API slugs) for consistent prompts, reporting, and automation.

Salesforce / HubSpot + ChatGPT

Community stories (2)

LinkedIn

This is one of the lowest effort, highest impact AI habits I have at work.

This is one of the lowest effort, highest impact AI habits I have at work. Most of my work at nettle has been geared towards sales, marketing, and a bit of ops. I use Claude as my workbench – it'd kill me if, every time I opened a new chat, I had to explain the nuances of our ICP, quirks of the sales funnel, or how our CRM deal board is structured. It has the Memory function, sure, but most of my experience with it (though that was with my now deceased ChatGPT) was me asking Chat to recall something and finding out it had deleted it. The joys!

So, in my first week at nettle, I spent roughly one hour building a "Sales Thinking Partner" as a Claude Project.


Essentially, it pre-loads all the context I need when starting any conversation from that Project – our ICP filtering criteria, messaging angles and tone, customer success numbers I can leverage, etc.


The steps were:

1. Take the context that was already pre-produced for me (sales onboarding doc + main sales deck).

2. Create new context, like why our sales funnel is structured in a certain way, what the attributes in our CRM are + their API slugs. This is what took the longest, despite our MCP connector to the CRM helping a lot to retrieve some of this info.

3. Feed all of that into Claude itself, explaining what I wanted, and having it produce structured Markdown files that were optimal for it to read.

4. Add everything as text content in the Project, and, once again, use Claude itself to write optimal Project instructions based on what I wanted to use it for.


In the seven weeks since joining, I have saved a couple of hours by not having to set the conversation context every time + having consistent output from my Claude. Every time I use that Project, it simply knows what I’m talking about.


In the one week our Thinking Partner was out of date because of a new addition to our product suite, I had to manually provide that context every time I interacted with it. That was so annoying that I spent half an hour last week adjusting all my Projects that needed it. Worth every second.


This is just one Project; I’ve others for creating marketing copy, building branded presentations (though I still find Claude 💩 for this), and more.


And for those using Cowork, you can essentially do the same context pre-loading by saving the Markdown files in the working folder/subfolder you point Cowork at, and then adding a line to your Global Instructions telling Claude to read those context files at the start of every session.


AI works best if it has structured context. Less than one hour of set-up creates huge leverage later.

JCO
Julio C. OthonChief of Staff at nettle
Mar 5, 2026
X

From a non-coder perspective:

From a non-coder perspective:
I am in sales and discovered AI a year ago. I'm only good at sales because I understand people and can read them. This is not a brag, just me recognizing a skill I have developed. So this leads me to this post and what @typecraft_dev was commenting on. This game analogy...Yeah this works because this is exactly how my last year has felt. I have been leveling up all year long. I have built, what I think are pretty impressive apps, for someone that is not a coder.


'Vibe Coding' is not a term I would use for myself. I started that way for first 6 months. But I'm the guy that wants to understand why. AI has allowed me to learn things so much faster and have access to information I would have never had before so easily. I can sit down and within minutes be deep into 'human memory', I can iterate and come up with wild ideas. I then can turn those ideas into working applications.


This journey and AI has allowed me to play the ultimate game. I can turn thoroughly researched and iterated ideas into real things. Things that I can use and do use daily. I have a personal assistant, that if you asked it who Brian is, will nail me. Why? Because it uses my design of memory. Not someone else's, but my idea, my design from scratch. I studied human memory and what makes a memory a memory, I studied Postgres, Drizzle, PGVector, I know how to setup Google Auth without AI, I can deploy to vercel, I have my own VPS that runs most of my personal Apps. I built a territory personal CRM for my sales job that has been immensely useful for me.


This has been my game of all games. You have a tool, it's all in how you use the tool. So yeah this has been some of the most rewarding times of my 56 years on this planet.

R
RidgetopAiSales professional
Mar 4, 2026