Today’s build turns that definition into a working system you can copy.

A multi-agent system is an AI setup where one agent coordinates the work of two or more other agents to finish a job. The coordinating agent is called the parent. The agents it coordinates are called subagents. The parent decides which subagent handles each part of the job, reads each subagent’s output, and either combines the finished outputs into a final result or sends a subagent back with a narrower request if the output isn’t specific enough.

The reason to use a multi-agent system instead of one large agent is that each subagent gets to focus on a single task with its own instructions. That focus produces better output than asking one agent to keep every task in its memory at once. It also means the parent can send two subagents off to work at the same time, which gets the job done faster than doing every step in sequence.

The build below turns this diagram into a working system on your machine.

What it includes: the three files you can copy directly into your own setup, a step-by-step walkthrough of a live run with every part of the system labeled inside the transcript, the follow-up request that shows the parent agent adjusting its next step based on what came back, and a set of concrete swaps for adapting this pattern to other recurring jobs your team runs every week.

👋🏿 Hey, I’m Hodman. I write The Data Letter for senior managers, operators, and technical builders rolling out AI. Here are some recent popular articles you may have missed:

➡ An n8n agent that reads your live metrics and reports them every Monday morning, grounded in a real spreadsheet so it stops inventing numbers.

➡ A four-artifact workflow for calculating AI ROI in a format your CFO will approve, built in 90 minutes.

➡ The intake form, screening guide, vendor checklist, and documentation workflow every enterprise AI project now runs through under U.S. state AI regulations.

In a few minutes, you’ll have a working multi-agent system running. Let’s build it.

Read more

If your team is evaluating something a vendor is calling an AI agent, this session gives you a working definition and a 5-part check you can run this week to determine if it’s actually an agent.

I walk through the anatomy of an AI agent (a three-part loop plus two supporting systems), then apply it to two Zapier products to show the difference between an automation being marketed as an agent and something that fits the definition. Roughly 14 minutes.

On Sunday, I’m publishing the paid follow-up: How AI Agents Actually Work Under the Hood. It walks through how to build a multi-agent system, with every one of the five parts labeled inside the build. You’ll see how a sub-agent becomes a tool for the parent agent, how memory carries context across every step, and how the parent decides what to dispatch next based on what came back. You can copy the setup and adapt it to anything your team runs regularly.

UPGRADE TO PAID

See ya soon!

That decision fits on one page. I call it an Exit Map. Down one side you list the kinds of data your company works with. Across the top, where each kind is allowed to go, whether that’s a personal AI account, your company’s approved account, or no AI at all. Public marketing can go anywhere. Internal documents go only to the company account. Send confidential client data and credentials to no AI at all.

I went through this live yesterday. You can watch the full episode here.

Deciding is the easy part. The hard part is making your tools obey that decision. The settings that do it are inside each platform’s admin area, and few teams switch them on.

Do this and your team keeps the AI they want, your confidential data stays in-house, and when your annual review comes you can show which kinds of data your team may send to an AI tool, and which never go near one. Below, I walk you through that setup for both Claude and ChatGPT, one row of your Exit Map at a time. Upgrade to get every step. By the end, your team’s AI tools will be locked down so your private data can’t slip out, and you’ll have the records to prove it if you’re audited.

Read more

Your team already uses AI every day, and your data goes out with it. This session shows you how to give them access without your private information leaking through those tools, and without it turning up as a finding in your next security review.

I walk through why the security on your files doesn’t cover AI tools at all, the three kinds of company data and which ones software can and can’t catch, and a one-page way to decide which of your data each AI tool is allowed to see. Built for senior managers, operators, and technical leads who are accountable for how AI gets used at their company.

GET THE SLIDES HERE

FREE FOR ALL SUBSCRIBERS:

Free AI Readiness Checklist, which scores how far along your team is with AI adoption instead of leaving you to guess.

Free Friction Audit, which shows you what’s getting in the way of your work.

TOMORROW ON THE DATA LETTER

This session gives you the decision. Tomorrow’s piece gives you the setup. I’m publishing ‘Stop Company Data Leaking Into AI Tools,’ a step-by-step build of the enterprise controls sitting inside Claude and ChatGPT that few teams ever switch on. Everyone knows single sign-on. These settings go deeper, deciding what your connections can interact with, what data gets kept, and what gets logged so you can show a reviewer what the AI did.

Subscribe to The Data Letter to get it the moment it goes up.

Subscribe now

WHO I AM

I’m Hodman Murad, Data Scientist and Founder of Asaura AI, where we build productivity tools for people with ADHD. I publish two newsletters on Substack. The Data Letter, where I teach senior managers, operators, and technical staff how to build with AI. And Between Thinking and Doing, where I design structured AI systems for high performers facing execution friction.

Yesterday’s live session opened with a diagram from a 2015 Google paper called ‘Hidden Technical Debt in Machine Learning Systems’. That paper made an argument that changed how teams build with AI: writing the model is the fast, cheap part. Running it inside a company, and keeping it working over time, is where the cost and the risk sit. By the authors’ own estimates, a mature AI system is around 5% model and 95% that surrounding infrastructure.

That 95% is where AI projects fail, and it’s what you get asked to approve as a leader, even though it’s the hardest piece for a non-technical person to assess. So on the live, I gave you a way to break any AI project into five layers, and for each layer, the one question that tells you whether it’s a good investment or a risk. Together, the five answers show you where a project is strong and where it will cause trouble, before you commit budget or scale it. Those five layers are model, compute, data, orchestration, and governance. Work through them in order, and you can sit in a leadership meeting and say, with evidence, which layer is ready and which one needs work before the company invests further.

If you missed it, watch the recording here. It includes a link to the deck and the Google paper. This article picks up where that session ended.

What you’re building today

On the live, you learned how to read an AI project across the five layers. Today you turn that into something you own. You’ll build a Claude Project that takes about 30 minutes of notes from a working session with your team and returns a leadership-ready assessment that shows where the project is solid, where it’s exposed, and what to resolve before you scale. Build it once, and you reuse it on every AI project after this, without relearning the framework or writing the assessment yourself.

Below this line is the full build. You get the questions to work through for each layer, the scoring system that shows where the project is solid and where it’s exposed, the instructions you paste into Claude to set the tool up in 10 minutes, and a worked example that turns one messy set of notes into an assessment you could put in front of your CEO that same afternoon.

Read more

In 2015, a group of Google engineers published a paper called Hidden Technical Debt in Machine Learning Systems. Their conclusion was that a mature AI system is at most 5% model and at least 95% the infrastructure around it.

That small box is the part we all discuss. Which model, how capable it is, what it scored on the benchmark. The 95% around it is what determines whether an AI project works once it’s inside your company.

This week’s live session gives non-technical leaders a way to see that 95%.

You take any AI project, break it into five layers, and ask your technical teams one question about each.

You can watch the recording above and follow along with this deck here.

Tomorrow I’m publishing the build that turns all of this into a tool you keep, called ‘The Complete AI Infrastructure Briefing Tool: Build and Deploy It This Week’. Today you got the five layers. Tomorrow we build the tool together, so you drop in the answers you gather from your team, and it produces a finished briefing, each layer flagged and formatted, ready to put in front of leadership this week.

If you’ve ever sat in a meeting nodding along to an AI project you couldn’t quite see inside, this is the one that changes that for good.

See you tomorrow, Hodman

It’s more difficult than it seems because no one documented the costs of running a workflow before the tools were introduced, leaving you without earlier figures to compare today’s performance against. Usage goes up, people report saving time, but none of it converts into dollars anyone can put in a budget.

This article gets you that figure for one workflow, and gets it accurate enough to put in front of your finance team.

The method is a Friction Ledger, which is three columns you fill in for a single workflow before you spend anything. Column one is frequency, which is how many times a week the task happens. Column two is proximity to cash, which is how many steps sit between that task and cash entering or leaving your company. Column three is handoff cost, which is how many minutes a person spends on the output after your AI produces it. Column three decides whether the workflow returns dollars or costs them, because every minute your reviewer spends is a minute subtracted from what the AI saved.

Thursday’s live session ran that through a worked example. You can open the slides I used for that here.

Getting from the method to your own figure takes about 90 minutes, spread across a week.

Every workflow has a review time above which it costs your company more than it returns. Cross that line and your AI spending is a loss, however good the tool is. Almost nobody knows their own figure, and one formula produces it in under a minute.

The rest of this article gives you four things:

1. A spreadsheet with the break-even formula already in it, where you enter your own workflow’s numbers and read the annual return off the bottom.

2. Nine questions to ask the person who usually manually runs the workflow, so your timings come from watching rather than remembering.

3. A prompt that turns those numbers into a one-page summary you can send to your finance team.

4. Six slides you can copy for the meeting where leadership decides whether to keep paying for your AI tools.

Read more

AI tool usage inside 400 companies climbed 65%. Completed tasks climbed 8%.

Today’s live session is on why those two numbers sit so far apart, and on the single measurement that decides whether your AI spending comes back to you.

Here’s what’s we covered:

▸ Why your AI tool only works on about 14% of your team’s day, and what that means for your return

▸ The Friction Ledger, a three-column method you fill in before you spend anything

▸ A full worked calculation on one workflow, from 6 minutes saved to $58,000 a year

▸ The same workflow at a company with conflicting supplier records, where the return is (-$18,000)

▸ How to run this yourself

The deck is yours as well. Every figure from the session is on a slide, so you can drop your own numbers straight into the calculation.

Get the deck

Every minute someone spends checking your AI’s output is a minute subtracted from what it saved. Nobody writes that number into a business case, which is why so many AI projects look profitable on paper and return nothing.

On Sunday, I’m publishing ‘Calculate AI ROI Your CFO Will Approve’ for paid subscribers. Today gives you the method. Sunday gives you the files.

You get:

▸ The ledger as a working spreadsheet with the formulas already built

▸ The questions to ask when you walk through a workflow with the person who runs it

▸ The prompt that turns your recorded times into a one-page summary for finance

▸ And the slide structure for presenting the figures to your leadership team

See you Sunday!

Hodman

📌 Quick Reminder: The Data Letter paid subscription price is going up at the end of the day on July 31st (Tomorrow) from $5/month or $50/year to $10/month or $100/year. If you upgrade before then, or if you’re already a paid subscriber, you’ll stay at the current price for as long as your subscription remains active.

UPGRADE HERE

During beta testing for Asaura AI, I killed a feature 51 users told me made their lives harder. The feature was a breathing exercise overlay that showed up before every task. I’d built it because I’d read a study out of India on meditation as an ADHD intervention for kids, and because meditation had worked for me personally.

The study was on kids in a supervised meditation program. Asaura users are adult professionals who open the app to start a task in the next few minutes, and the overlay added a step in front of that exact goal.

I pulled the feature and lost a month of build time. So I built a Claude system to make sure I’d never repeat the pattern.

I ran the same decision back through the system live. The output caught what I was doing before I could pretend it was a new idea, using only the evidence sitting in my knowledge files.

The full walkthrough is in the recording above, and the accompanying files are linked below. This only worked because I gave Claude my own evidence to work with.

📌 A quick note before we started. The Data Letter paid subscription price is going up at the end of the day on July 31st from $5/month or $50/year to $10/month or $100/year. If you upgrade before then, or if you’re already a paid subscriber, you’ll stay at the current price for as long as your subscription remains active.

UPGRADE HERE

What’s inside Decision Studio

Decision Studio is a Claude Project you set up once and reuse for every product decision from then on. It has four moving parts.

1. Custom instructions. A decision partner persona that stops Claude from cheerleading.

2. Four knowledge markdown files. Job-to-be-Done, user feedback log, past decision memos, and product anti-patterns. All linked below.

3. A decision input template. Five fields you fill in before every prompt.

4. A master prompt. Runs a pre-mortem, a red team, and a decision memo in one call.

The prompt alone gives you a generic pre-mortem. The four knowledge files give the studio the context it needs to evaluate any decision using how your product works in practice, whether it’s brand new or a variation on one you’ve made before.

Subscribe now

What Claude said when I re-ran the killed decision

For the segment, I pasted the priming overlay decision back into the studio as if I were making it fresh today, using only what I knew six months ago.

Before Claude even started answering the three parts of my prompt, it opened with this:

Before I hand this to you, a flag you’ll notice as soon as you read it: your own docs already record this exact decision, killed after 51 beta testers rejected it. I answered the three parts anyway, but they all point the same direction.

Claude found the priming overlay memo in decisions.md, matched it to the decision I pasted in, and opened the response by flagging the repeat.

Then Claude pulled direct quotes from feedback.md that contradicted my decision. It caught the founder-brain anti-pattern I’d written for myself after the last failure. And it ended with a No-Go verdict and kill criteria I would have measured on day one instead of hoping the numbers came in strong.

Subscribe now

The files

Everything you need to build your own Decision Studio is below. Free-tier Claude works fine, and no coding is required.

• Setup guide — Project instructions, decision input template, master prompt, 30-day check-in template.

• jtbd.md — placeholder Job-to-be-Done doc.

• feedback.md — placeholder user feedback log.

• decisions.md — placeholder past decision memos.

• anti-patterns.md — placeholder product anti-patterns list.

  Subscribe now

What to do this weekend

Set up Decision Studio in your Claude account, fill in your own knowledge files, and run it on the next product decision you were about to make from gut. Even one memo is worth the ten minutes.

Thanks to Wyndo and Dheeraj for having me on!

If you’re new to The Data Letter, this is what I do here. I share how I build AI systems for operators, managers, and technical builders who need to make better calls faster. Subscribing gets you the AI Readiness Checklist so you can score how far along your team really is with AI adoption instead of guessing.

Subscribe now

First, the four regulations reshaping enterprise AI in 2026:

• The June 2nd federal executive order on frontier model pre-release review.

• State-level frontier AI laws, led by California TFAIA and New York RAISE.

• State-level automated decision-making laws, led by California ADMT, Colorado SB 26-189, and Texas TRAIGA.

• Federal procurement guidance from the White House Office of Management and Budget.

Second, why enterprise AI adoption is no longer a software-access problem. The review functions your company already runs still apply, but each one now has to evaluate categories of exposure that traditional enterprise procurement was never designed to handle.

Third, the four Adoption Gates every AI project now clears before deployment: vendor selection, use-case screening, monitoring, and documentation.

Fourth, three practical steps to prepare: build a use-case intake before you build any pilot, ask vendors for evidence instead of assurances, and reduce your company’s dependency on any single AI vendor’s release schedule.

📌 A quick note before we start. My paid subscription price is going up at the end of day July 31st from $5/month or $50/year to $10/month or $100/year. If you upgrade before then, or if you’re already a paid subscriber, you’ll stay at the current price for as long as your subscription remains active.

What this piece gives you

The live gave you the framework. This piece gives you the workflow.

By the end, you’ll have six artifacts your team can install this week:

• A one-page use-case intake form.

• A screening guide that maps every AI project to the specific state laws that apply to it, across the seven U.S. states with active or upcoming AI regulations.

• A vendor evidence checklist covering eleven categories of documentation your legal team should require before any AI vendor evaluation begins.

• A monitoring log schema your data engineer can implement without additional infrastructure.

• A documentation template designed to survive a regulatory audit.

• A build order that shows your team how to put all five into place, in the sequence that saves the most rework.

Read more

In this session, I walked through the federal and state regulations that will affect enterprise adoption in 2026, as well as three practical steps your company can take this quarter to prepare.

A few things you'll walk out with:

→ A clear understanding of which regulations apply to your company and which apply to your vendors
→ The four review points that every AI project must pass before deployment
→ Three steps you can put in place next week to reduce the operational cost of every future regulation your company absorbs

If you’re a senior leader, a technical builder, or an operator responsible for how AI shows up inside your company, this session gives you the framework.

Later this week, I will be publishing a piece on Substack called The Enterprise AI Compliance Workflow for U.S. State AI Regulations in 2026 that walks you through how to build those workflows on The Data Letter. It hands you the workflow that puts all of this into practice. Everything downstream of today’s framework, in one workflow, ready to implement inside your company.

You can get it now here ⤵

Every free subscriber to The Data Letter gets the AI Readiness Checklist, a scored assessment of how far along your team is with AI adoption so you can stop guessing.

SUBSCRIBE

Today, you’re going to be that someone. You’re going to build the thing Microsoft and AWS charge millions for, at your own desk.

What you’re building

By the end of this build, you’ll have a working, autonomous agent that watches your team’s support intake queue in Notion, reads a written playbook for how your team already answers common questions, drafts a response in your team’s voice, and hands that draft to a person for approval before anything goes out.

It checks the queue every 30 minutes on a set schedule; no one has to open a chat window and trigger it. I set mine to check only during work hours, since a person still needs to be around to review what it drafts, but you can widen that window to whatever hours your team covers.

I ran this against my own company’s queue, and every screenshot in this piece comes from that run. My team gets a handful of the same questions from new users, over and over. That’s the type of request this build is for.

You’ll use Claude Code to run the agent, and Notion to store incoming requests and the playbook that agent follows. If your team tracks requests somewhere else, the same setup works with whatever you’re already using.

Read more

We covered what Microsoft, AWS, and the NFL are all telling us about how enterprise AI needs to change to produce returns, plus a five-question diagnostic you can run to score any live AI projects your team currently has, and three failure modes to watch for as you start embedding AI into your workflows.

Sunday’s follow-up walks through the full build of an internal embedded AI agent that handles the repetitive knowledge work requests coming into your team.

See you Sunday!

Free Friction Audit

Free AI Readiness Checklist

That decision happens dozens of times a day. Every ticket follows the same steps and uses the same types of information, even though the tickets themselves are different. High volume and a repeatable process are what make a decision a good candidate for AI to handle.

Every team has decisions like this. Support triage. Sales escalation. Refund reviews. Vendor evaluations. Once you can name these decisions, you can build AI tools that handle the parts that don’t need human judgment.

The way you identify these decisions on your own team is a 4-step audit. Recognizing these opportunities shows your team’s proactive approach and builds confidence in your ability to leverage AI effectively.

Step one names the decision that recurs.

Step two names who does each step today.

Step three names the information each step needs.

Step four circles the steps an AI model could handle.

Those four steps together give you a clear specification you can hand to your Revenue Operations team, or use to build the tool yourself in Claude Projects, empowering your team to innovate and improve efficiency.

Subscribe now

What’s below

The full audit walkthrough applied to customer support triage. A worksheet template you fill in for any decision on your team. The four outputs of a completed audit, and what each one tells you about the tool to build.

Then the Claude Project: the system prompt with six triage criteria, three sample tickets to calibrate the criteria before you connect anything, the connector setup for your support inbox and CRM, the approval flow that keeps a person in the loop until your team trusts the scoring, and four other decisions you can adapt this same setup to inside your team.

Setup takes about an hour once you’ve picked the decision you want to automate. If a support team of five is spending 45 minutes per day each on manually triaging, this build gives them back about 18 hours a week combined. That’s roughly half a full-time work-week of hours, returned to the work your team does best.

Read more

She didn’t have to search for the trend herself.

That advertiser’s workflow is one example of what Pinterest changed in June. The same pattern is rolling out across its advertiser tools, and operators outside ad-tech should look closely at how Pinterest is using its data to take repetitive analysis off the human side of the workflow.

What Pinterest Shipped a Week Before Cannes

On June 17, Pinterest announced four AI products ahead of Cannes Lions: Business Assistant, Pinterest MCP, a new Performance+ creative model, and Ask Pinterest. The announcement reads like an ad-tech story. Underneath the ad-tech framing, Pinterest is using a decade of taste and intent data to automate the analysis and selection work advertisers used to do themselves.

In the announcement, Pinterest’s Chief Business Officer Lee Brown said, ‘The future of discovery won’t be driven by keywords alone. It will be shaped by context, taste, and trusted recommendations.’

Users don’t want to type queries anymore. They want the platform to already know what they’re looking for, and Pinterest is rebuilding its advertiser tools around the same idea.

Subscribe now

Which Advertiser Decisions Pinterest’s AI Now Handles

Each of the four products replaces a task someone on the advertiser side used to do manually.

• Business Assistant automates the trend monitoring a campaign manager used to do by scanning dashboards.

• The Performance+ creative model automates the asset selection that a creative lead used to do through A/B testing.

• Pinterest MCP gives an agency analyst direct access to Pinterest campaign data and analytics from inside the analyst’s own working tools, instead of having to log into Pinterest separately to pull the same numbers by hand.

• Ask Pinterest automates the multi-step planning a shopper used to do across several searches.

The people doing the work stay in place. What changes is the part of the job they spend time on.

A campaign manager defines what a winning campaign looks like and reviews the recommendations Business Assistant surfaces. A creative lead sets the brand voice and approves which AI-selected variant runs. An agency analyst advises the client using insights MCP delivers automatically. The strategy and judgment stay with the human. The retrieval, comparison, and selection now sit with the model.

Advertisers spend less time on retrieval and comparison and more time on strategy, judgment, and client relationships.

Subscribe now

Why This Matters for the Team You Run

Pinterest spent two years building infrastructure to automate the repetitive analysis its advertisers used to do themselves. The Performance+ model improved click volume by 7.5% in Pinterest’s own testing. Pinterest MCP is letting agencies like PMG, Pacvue, and Omnicom’s Jump450 plug Pinterest insights directly into their AI workflows.

The pattern is borrowable. The technology is open. Pinterest MCP runs on the same protocol your team can run.

Technology is the easy part. The harder part is auditing your team’s decision flows in enough detail to see which steps an AI tool could handle on its own. Without that audit, applying AI to your team stays abstract.

Many operators can name three or four obvious time sinks. Status meetings. Slack triage. Pulling numbers for the weekly review. Those are the symptoms a team sees.

The deeper layer is the work nobody tracks. Context switching. Re-reading yesterday’s threads to remember what was decided. The seven-minute Slack derail that costs forty minutes of regained focus. The constant low-grade pattern-matching across dashboards that no one would call work but everyone does anyway.

Until a team can name those untracked tasks specifically, no AI tool can handle them. The audit has to come first.

In case you missed last week’s Data Letter sprint, it covered the same problem from a different angle. Samsung is rolling out ChatGPT, Gemini, and Claude to all 260,000 of its employees and measuring the rollout by full-time-equivalent.

• Samsung Gave 260,000 Employees AI. Few Will Use It Well. explains why access to AI doesn’t change how the work gets done.

• Build the AI Scoring System Samsung’s 260,000 Employees Aren’t Getting is Wednesday’s live recording, where I built a working scoring system from scratch.

• I Built an AI Lead Scoring System That Reads My Inbox and Writes to HubSpot. Here’s How. is the full implementation guide: the Claude Project setup, the system prompt, and the HubSpot connector flow.

One Thing to Try This Week

Pick one decision your team makes every week. Something like ‘which support tickets get escalated this morning’, ‘which leads sales should prioritize, or ‘which marketing campaign deserves more budget this week’. The decision should recur often, have a clear input, and produce a clear output.

For each step in that decision, write down two things: the person who currently does the step, and the data or context they pull to do it. For a ‘pipeline coverage review’, for example, the person is the sales manager and the data is the current week’s deal stages from the CRM.

Many teams find that around 60% of the cognitive effort involves retrieval, comparison, or pattern matching. Work an AI tool can do faster than a tired manager at the end of the week.

If an AI tool handled the 60% that’s retrieval and comparison, the hours your team spends on that work would free up for the 40% that requires judgment, strategy, and client time.

Pinterest finished that audit for its advertisers two years ago. The same exercise is overdue on many teams.

Next Step

This Thursday, July 2nd, I’m going LIVE to walk through how AI is redistributing cognitive labor across organizations. What the pattern looks like, where it’s working, and the framework operators can use to map their own teams.

On Thursday, I’ll release the full build: Map Where Your Team’s Mental Energy Goes, and Build an AI to Redistribute It. The Pinterest story above explains why this redistribution matters. Thursday’s build walks through a full example: a team’s weekly decision flow, the audit that identifies the 60%, and the AI tool built to handle it. You can run the same approach on your own team’s workflow.

Subscribe now

The system runs continuously. Every time a new lead lands in the inbox, Claude reads it, scores it against the same criteria, and writes the score, tier, and reasoning back to the matching contact record in HubSpot. By the time my sales team checks the queue, every lead is already sorted by tier with an explanation attached.

This article is the full build. Setup takes about 45 minutes. You’ll need a paid Claude subscription, a HubSpot account, and a business email account that supports the Microsoft 365 or Gmail connector.

If your team uses a different CRM or inbox, the build is the same. The connector names change. Most major CRM and inbox platforms have Claude connectors now, or are adding them quickly.

What you’ll have at the end

A working Claude Project that:

• Reads inbound leads from your inbox automatically

• Scores each lead against five criteria you can edit in 30 seconds

• Returns a structured response with a score, a tier, an explanation, and the specific signals it picked up

• Writes the score, tier, and explanation back to the corresponding HubSpot contact record

• Stays consistent across hundreds of leads a week

  Subscribe now

Step 1: Create the Claude Project

Open Claude on the web or desktop app. In the sidebar, click “Projects.” Click “Create new Project.”

Name the Project something specific to the decision type. For lead scoring: “Lead Qualification Scoring System.” If your team plans to share this Project later, the name should make the use case clear at a glance.

Leave the description blank for now. You’ll fill in the Project Instructions in the next step.

Read more

It’s the system Samsung’s 260,000 employees aren’t being taught to build. It’s the system Salesforce hasn’t built after spending $300 million on Anthropic this year.

Tomorrow on The Data Letter, I’m publishing the full implementation guide with the HubSpot and Gmail setup that lets Claude pull leads and score them automatically.

Subscribe now

The way Samsung plans to measure whether the rollout works is the part of the story every operator and manager needs to understand, because every other large enterprise AI rollout has hit the same wall: access without a system for using that access well.

What Samsung Just Did for 260,000 Employees

Samsung Electronics has around 260,000 employees globally. By the end of 2026, every one of them will have access to ChatGPT, Gemini, and Claude. The DX Division, which builds phones, TVs, and home appliances, gets access first. Every other Samsung subsidiary, from Samsung Display to Samsung SDI to Samsung Biologics, follows after.

To get there, Samsung is running a top-down training program. About 50 senior leaders are training first. 2,300 executives follow through August. Then everyone else, in waves, through the rest of the year.

The metric Samsung is using to measure whether the rollout worked is full-time equivalent, or FTE. One FTE equals one person working a 40-hour week. Samsung will measure AI success by how many people’s worth of work a single employee can do with AI. If a marketing manager using ChatGPT produces what used to take three people, that’s a 3.0 FTE.

Samsung is the first of Korea’s four largest business groups, called chaebols, to fully adopt external AI tools across all its companies. The other three are SK, Hyundai, and LG. Together, these four groups account for a large share of Korea’s industrial economy. Whatever Samsung does, the other three watch. Whatever Samsung measures, the other three are likely to measure too.

The FTE metric is worrying some Samsung employees, who said AI adoption ‘could be perceived as a measure for ultimately determining how many jobs can be cut rather than being used as a means of improving work efficiency.’

Hey there! 👋🏿👋🏿👋🏿 I’m Hodman Murad. I write The Data Letter for senior managers, operators, and technical builders rolling out AI. Here are some recent popular articles you may have missed:

I Built an AI Agent That Sends Me My Numbers Every Monday Morning → A step-by-step n8n build for an AI agent that reads your live metrics, remembers context, recovers from failures, and runs on its own every Monday.

Build Your Own Local AI Stack: A Session on Models, Hardware, and Quantization → How to choose an open-weight model that fits your local machine, runs without a cloud subscription, and can’t be shut down by a vendor.

3 Pieces of Free Software That Install a Private AI → The full step-by-step build for a private AI on your laptop in under an hour. Free, offline, yours.

I sat down with for her Career Pivot Playbooks series to talk about how I got from data science to building AI for productivity. Read the interview here.

Why Giving Employees AI Doesn’t Change How Work Gets Done

Samsung’s rollout is the largest one announced this year. It isn’t the first to hit the same problem.

In May, Marc Benioff said on the All-In podcast that Salesforce will spend $300 million on Anthropic tokens this year, primarily for coding. He described the efficiency gains across service, support, and marketing as ‘unprecedented.’ Salesforce’s support team went from 9,000 people to 5,000 over the past year as AI agents took over more of the work.

Later in the same interview, Benioff said Salesforce still needs a smarter routing system to connect its employees with the models they use. Right now, every request from an employee goes to the same top-tier model.

Benioff said simpler requests should be sent to smaller, cheaper models, and only the complex ones should reach a frontier model like Claude. Salesforce is spending $300 million a year on Anthropic, and the routing system Benioff wants doesn’t yet exist at his company.

Two weeks before this appearance on the All-In podcast, Microsoft started canceling Claude Code licenses for the engineers who build Windows, Microsoft 365, Outlook, Teams, and Surface. The cancellations will finish by the end of June. The official reason was that Microsoft wanted to consolidate its own GitHub Copilot CLI. The reason underneath was cost. Claude Code usage at Microsoft grew faster than the team’s budget could absorb.

Subscribe now

Each of these companies invested heavily in access to AI. None of them built the system that sits between the employee and the model and decides what the model should be asked to do, with what inputs, and scored against what criteria. That system is what’s missing. Without it, $300 million in token spend produces uneven output. Without it, access to frontier models becomes a budget problem. Without it, 260,000 employees with three AI tools each will fall back to the few uses they already know.

What a Scoring System Is

The operators I work with don’t ask the model to make the decision. They write down the criteria a good decision would meet, hand the model those criteria, and ask the model to score the option against them.

Let’s take a simple example: qualifying inbound sales leads. A new lead arrives through a contact form on your website. The sales manager writes down what makes a lead worth a call: job title fit (30 points), industry match (25), company size (20), intent signals in the message (15), tech stack overlap (10).

Each lead gets scored out of 100. The model reads the lead, scores it against the criteria, and returns the number, a tier (hot, warm, cold), and a written explanation of how it arrived at the score.

The sales team trusts the output because they can see exactly how the model arrived at the number, and they can change any single point value within 30 seconds if they disagree. The model applies the same scoring across hundreds of leads a week, faster than any one person could.

The same scoring approach works for almost any decision your team makes regularly:

• Evaluating vendor proposals

• Triaging customer escalations

• Reviewing inbound resumes

• Flagging unusual expenses

• Prioritizing bug reports

A scoring system is what your team would write down if they had unlimited time to document how they make these calls. It’s the criteria, the point values, and the explanation requirement, written down once and applied consistently thereafter. AI handles the volume. Your team keeps control over the criteria.

Samsung’s training program covers how to use ChatGPT, Gemini, and Claude. From everything Samsung has announced publicly, it doesn’t cover how to build the system that turns those tools from a chat window into a decision engine the team can trust.

Subscribe now

Your Next Step

Two days is how long it’ll take you to build the system that Samsung’s 260,000 employees aren’t getting.

This Wednesday at 8:30 AM EST, I’m going live on Substack to build a working scoring system from scratch. Here’s what I’ll be covering:

• How to take the way your team already makes a decision and turn it into a written scoring system

• The structure of a scoring prompt that returns a usable number every time

• How to write the explanation field so your team trusts the output

• What to do when a domain expert on your team disagrees with the model’s score

• Why a short, plain scoring system outperforms a complicated AI agent

Thursday’s article is the full implementation guide of what we built on the live. Every line of the scoring prompt, the workflow setup, the structured output format, and the integration into your existing tools.

By the end of this week, you’ll have a working scoring system running on your team’s own decisions, in your own tools, with your own criteria. You’ll be the person on your team who built it.

Subscribe now

The second is the one a smaller group has already started: what does our team own, and what runs regardless of whether others are having an outage today?

This article is for people moving into the second conversation. The full step-by-step build for a private AI on your laptop in under an hour. Free, offline, yours.

Read more

1. Where the model came from.

2. What your hardware allows.

3. And a concept called quantization that decides whether the model runs smoothly on your machine or slows everything down.

Watch the recording above.

Every step-by-step build I’ve published over the last two months lives in one place, from your first local AI agent on a laptop to wiring one into your team’s data. The n8n local tutorial alone gets you a private AI on your machine in about thirty minutes, no cloud, no API keys.

Get them here: https://www.thedataletter.com/p/build-ai-tools-you-control

Tomorrow’s article on The Data Letter is a build that takes the three questions from this morning’s live, applies them to your machine, and walks you through setting up a local model you can connect to the work you already do every day.

Read it here:

After the Fable 5 fiasco, it’s time to take ownership of your own stack seriously.

Subscribe now