Mastering ChatGPT: Advanced techniques for workplace communication and productivity | Hiten Shah

Mastering ChatGPT: Advanced techniques for workplace communication and productivity | Hiten Shah

How I AIJul 7, 202542m

Claire Vo (host), Hiten Shah (guest)

ChatGPT memory hygiene: temporary chats, archiving, pruningProjects as persistent context containers“Show it what great looks like” via exemplarsCodifying outputs into reusable instructionsReplicating your boss for manage-up and pitch prepPersonal OS: personality tests + voice/tone artifactsFramework-driven sales enablement using PDF knowledge bases

In this episode of How I AI, featuring Claire Vo and Hiten Shah, Mastering ChatGPT: Advanced techniques for workplace communication and productivity | Hiten Shah explores hiten Shah’s ChatGPT Projects for context-rich workplace communication workflows today Hiten Shah explains why high-quality results from ChatGPT come from better inputs—especially persistent context via Projects, curated files, and deliberate memory management.

Hiten Shah’s ChatGPT Projects for context-rich workplace communication workflows today

Hiten Shah explains why high-quality results from ChatGPT come from better inputs—especially persistent context via Projects, curated files, and deliberate memory management.

He demonstrates building “replicas” of key people (your boss, yourself, teammates) by uploading artifacts like operating manuals, writing samples, and personality frameworks, then prompting ChatGPT to generate tailored advice and conversation prep.

He also shows a repeatable pattern for turning great outputs into reusable instructions (“codify the output”), including having a “project for projects” to generate future project setups and prompt templates.

A second major workflow applies an external sales framework (Winning by Design) by loading PDFs into a Project, generating discovery scripts (e.g., SPICED questions), and iterating manually before attempting automation.

Key Takeaways

Treat context as the primary lever for quality.

Shah repeatedly emphasizes front-loading context (files, examples, explicit goals) or building it over time in a Project rather than expecting one-shot prompts to work reliably.

Get the full analysis with uListen AI

Use temporary chats for anything you don’t want remembered.

He separates “random” or disposable work into temporary sessions to avoid polluting long-term memory, and uses pruning when ChatGPT indicates it stored something.

Get the full analysis with uListen AI

Exemplars beat abstract instructions—“show it what great looks like.”

Instead of describing desired output, he feeds strong examples (e. ...

Get the full analysis with uListen AI

Build a ‘boss simulator’ to prep high-stakes conversations.

By uploading a manager’s operating manual plus related articles and adding simulation instructions, he gets tailored advice on how to pitch ideas, frame updates, and anticipate objections in that manager’s voice.

Get the full analysis with uListen AI

Add relationship frameworks to personalize communication guidance.

Layering Enneagram/Human Design/DISC/Myers-Briggs context helps the model suggest interaction tactics (e. ...

Get the full analysis with uListen AI

Codify good outputs into reusable systems.

When an output is strong, he asks ChatGPT to turn it into paste-ready Project instructions or even a meta-workflow (“project for projects”), reducing repeated setup cost across use cases.

Get the full analysis with uListen AI

Don’t rush to automation—manual iteration is how you get reliability.

He argues many teams jump to Zapier/agentic automation before they understand the prompts and evaluation criteria; iterating on ‘bare metal’ chat first helps you identify instruction gaps and stabilize outputs.

Get the full analysis with uListen AI

Notable Quotes

Context is everything.

Hiten Shah

Just show it what great looks like. It’s like a human.

Hiten Shah

This is a tip for all the ICs out there: Go and replicate your boss, and prep for conversations with them.

Claire Vo

I think people are racing to automation, and that’s a mistake.

Hiten Shah

If you’re gonna treat it like a human, think about incentives.

Hiten Shah

Questions Answered in This Episode

What exact ‘Project instructions’ template do you use most often to make a boss-simulator reliably quote and prioritize from the uploaded operating manual?

Hiten Shah explains why high-quality results from ChatGPT come from better inputs—especially persistent context via Projects, curated files, and deliberate memory management.

Get the full analysis with uListen AI

When you say you ‘prune memories,’ what kinds of items do you delete vs keep, and how do you decide what belongs in a Project file instead of memory?

He demonstrates building “replicas” of key people (your boss, yourself, teammates) by uploading artifacts like operating manuals, writing samples, and personality frameworks, then prompting ChatGPT to generate tailored advice and conversation prep.

Get the full analysis with uListen AI

How do you prevent a “replicate your boss” setup from becoming manipulative or creating trust issues on a team (Claire jokes about “psychological warfare”)?

He also shows a repeatable pattern for turning great outputs into reusable instructions (“codify the output”), including having a “project for projects” to generate future project setups and prompt templates.

Get the full analysis with uListen AI

What’s your step-by-step method for ‘codifying an output’—what do you ask ChatGPT to produce so it’s reusable and not just a one-off answer?

A second major workflow applies an external sales framework (Winning by Design) by loading PDFs into a Project, generating discovery scripts (e. ...

Get the full analysis with uListen AI

In the Winning by Design example, what instruction changes would you make so the model uses the pasted research only (and stops inventing personas like RevOps)?

Get the full analysis with uListen AI

Transcript Preview

Claire Vo

I wanna learn how to use ChatGPT the right way. So you gave us one tip, which was, "Be thoughtful about its memories." But what else? What are your tips?

Hiten Shah

I usually won't start anything without a ton of context or with the intention of giving it context over time. Just show it what great looks like. It's like a human. If a human doesn't know what great looks like, they're not gonna know what great looks like.

Claire Vo

You do have an example of something that you think is great, which is your boss's operating manual.

Hiten Shah

My boss's name is Morgan, so it's What Would Morgan Do? So I'm gonna create the project, and then I'm gonna add these files here. I wanna pitch Morgan the craziest product idea I can think of. What is the best way to pitch it to him so we can go after it? [laughing] Now it's like, this is what you want Morgan to say. Yeah, that sounds like him.

Claire Vo

This is a tip for all the ICs out there: Go and replicate your boss, and prep for conversations with them. [upbeat music] Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today, we have a great conversation with Hiten Shah, who's been building B2B SaaS for over 20 years. Not only is he a great founder and product thinker, but he is, by my estimation, a total ChatGPT power user. He's figured out how to load up ChatGPT Projects with information about yourself and about your boss to figure out the best way to communicate with each other and get work done. Let's get to it. This episode is brought to you by Paragon, the integration infrastructure for AI SaaS companies. Are AI features on your 2025 product roadmap? Whether you need to ingest data for RAG from your users' external apps, like Google Drive files, Gong transcripts, or Jira tickets, or build AI agents that automate work across your users' various tools, integrations are key to building useful AI features. However, building every one of these integrations costs months of engineering, time you simply can't afford, given the rapid pace of AI advancement. Paragon is an all-in-one embedded integration platform for AI products. Industry leaders like AI21, you.com, and Copy.ai use Paragon to connect over 100 of their users' SaaS applications to ingest data for RAG and provide their AI agents with thousands of integration actions. They've accelerated their integration development velocity by up to 50X, allowing their engineering teams to focus on core product features. Want to fast-track your integration roadmap this year? Visit useparagon.com/howiai to learn how. That's useparagon, P-A-R-A-G-O-N, .com/howiai. Thanks for being here! I am excited to talk about everybody's favorite friend, ChatGPT. Today is all about ChatGPT, right?

Hiten Shah

Yep.

Claire Vo

How did you get to ChatGPT being your, your favorite?

Hiten Shah

You know, it's, it's really funny. I, I obviously started using ChatGPT first. Uh, it existed first. There's a bunch of experiments I did with the API and all that prior to ChatGPT itself, so with OpenAI's APIs, and then when, when, when it came out, started playing around with it. It really wasn't doing what I wanted in terms of my output that I was looking for. I think it was still helpful in a bunch of areas that we'll talk about today, but it wasn't quite getting there. So then I started using Claude when it came out, and I was... In the initial days of using this stuff, I was actually way more Claude-heavy by, like, more than 50%. Even though ChatGPT came out first, I had access, I upgraded and all that. And I think the turning point for me, which I can't prove because I don't know the dates, was when memories started working, and that made it so that... And, and I'm a very, like, um... I don't try to talk to ChatGPT about everything, and if I'm gonna talk to it about things that are, like, a little random, I'll actually start a temporary session.

Install uListen to search the full transcript and get AI-powered insights

Get Full Transcript

Get more from every podcast

AI summaries, searchable transcripts, and fact-checking. Free forever.

Add to Chrome