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.

Step 2: Write the system prompt

The system prompt is what tells Claude how to behave every time you use this Project. Without it, Claude scores leads by feel, and the answers come back generic. The prompt below is the version I use for Asaura AI. Adapt the criteria to your business and keep the structure.

Click into the Instructions field on the right side of your Project and paste this in:

The conditional point logic (”Award X for Y”) makes the scoring repeatable. Every lead gets evaluated against the same logic, and Claude returns the same score when you re-run the same lead.

The “Never invent” line at the bottom keeps Claude from filling in missing information with plausible-sounding guesses. If a criterion can’t be evaluated from what the lead actually wrote, Claude assigns a zero and says so in the Explanation field.

Click Save.

Subscribe now

Step 3: Test it before connecting anything

Before you connect your inbox and HubSpot, test the Project with sample leads pasted in manually. This makes sure your criteria produce results you trust.

Open a new chat in the Project. Paste in three sample leads, one at a time, and check that each one scores the way you’d expect.

For Asaura, I tested these three:

Lead one: A VP of People Operations at a 250-person SaaS company filled out the contact form. Their message says they are evaluating productivity tools for Q1 to support neurodivergent employees, need to make a purchasing decision by end of month, and currently use Notion and Slack across the org.

Expected tier: Hot. Actual score:

Lead two: A marketing manager at a 30-person consulting firm filled out the contact form. Their message says they’re curious about Asaura and have heard good things, but they didn’t mention a timeline or budget.

Expected tier: Cold. Actual score:

Lead three: A psychology graduate student filled out the contact form. They’re researching tools for executive function support as part of their thesis and want to ask a few questions.

Expected tier: Cold. Actual score:

If the scores match your team’s gut, the criteria are working. If they don’t, edit the point values or the conditional logic in the Project Instructions and re-test. Get the calibration right here, before you connect anything.

You’ve got a working scorer at this point. You can paste any lead in, get a score, get a written explanation, and trust the output.

The next four steps connect the scorer to your inbox and your CRM, so it runs from a single prompt. Connecting your email provider. Connecting HubSpot (or whichever CRM you use). The approval flow that protects your CRM from bad contact notes.

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, Founder of The Data Letter, Between Thinking and Doing, and Asaura AI. In case you’re new here, here are some recent 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

Some people spent last week building with Fable 5, but you’re the person on your team who already runs AI tools locally, so a frontier model going down didn’t affect you.

For those of you who aren’t this person or that team yet, this was hopefully the wake-up call you needed to start owning more of your AI stack.

The good news is that the tools you need to build with are free.

Work through the builds below in order, or pick whichever sounds closest to what you’re working on this week.

Subscribe now

Run a model on your own machine

n8n. local. A private AI agent on your laptop, no API keys.
How To Fine-Tune and Deploy an LLM Without an ML Engineer. A support assistant grounded in your own docs, running locally.

Use it on a recurring job

I Built an AI Agent That Sends Me My Numbers Every Monday Morning.
Build a RAG System with NotebookLM in Under an Hour.
Build Your Own AI Productivity App with Codex.

Give it memory so it stops losing your context

I Built a Second Brain to Help Me Run My Company.
Every Time You Start a New Chat, You Lose Everything. Here’s How I Fix That.
How We Use Agentic AI to Help Us Make Big Product Design Decisions.
How to Use AI to Do the Executive Function Stuff Your Brain Skips Over.

What this means for how work is changing

AI Agents Are Redesigning Workflows. Your New Skill Is Staying in Motion.
Agentic AI Matters More to ADHD Brains Than Getting Faster Answers.

This week on The Data Letter: Wednesday’s live session is free and open to everyone. We’re going deep on local model selection, hardware sizing, and quantization, so you walk out knowing which model fits your machine.

Three pieces of free software install a private AI on your laptop gets published Thursday, with the full build ready to deploy.

Read it here:

Every build I’ve published over the past few weeks has given you one piece of this. The local agent build put a private model on your laptop with n8n, Ollama, and Docker. No API keys necessary. The Monday metrics build taught the agent to answer from wherever you’re storing your data instead of inventing numbers, and to say ‘I don’t have that’ when the answer wasn’t there. The RAG build in NotebookLM showed how retrieval lets a model answer from your documents. The prompt engineering piece made the case for treating your system prompt as an asset, versioned and tested, not a throwaway string.

Today, those pieces become one thing you own: a support assistant that runs entirely on your own machine, answers from your team’s documents, speaks in your team’s voice, and refuses to make things up. This is the same system I built for Asaura AI. You’ll build your version of it in the next half hour, for free, and when you’re done, the model is yours. No vendor update can take it out from under you, because no vendor is in the loop.

First, the word ‘fine-tune’

Real fine-tuning means retraining a model’s weights on your own examples. It changes the model itself, and it needs either a GPU or a paid training service plus a labeled dataset. For most teams, it’s the wrong tool for what they actually want.

What teams want is a model that answers from their own knowledge, in their own voice, and admits when it doesn’t know. You get that by adapting an open model at the moment you run it: you give it a system prompt that sets its role and rules, you put your own documents in front of it, and you show it a few examples of the answers you expect. The proper name for this is in-context learning, and it gets you the outcome people mean when they say fine-tune, without training anything, without a GPU, and without a bill.

That’s what we’re building today. The model stays a general open model. What makes it yours is everything you wrap around it.

Below the paywall is the complete build, every step from empty workflow to a working assistant you’ve tested and trust, plus the downloadable files ready to paste in.

Read more

• Anthropic Claude: https://claude.com/pricing

• OpenAI: https://openai.com/api/pricing/

• Google Gemini: https://ai.google.dev/gemini-api/docs/pricing

• Anthropic Fable 5 / Mythos 5: https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5

  Subscribe now

Then the vendor shipped a new version.

And the thing that worked last quarter started returning garbage.

Last month, my friend, an operations leader named Priya, messaged me. Her team had settled on an AI model, built it into their support workflow, and shipped it. A few weeks later, she wrote again: ‘It started giving us garbage, but nobody touched the code. What do you think is going on here?’

She’d asked the questions everyone asks up front: Which model is best? ChatGPT or Claude? Which one’s cheaper? She hadn’t asked the question that decides whether a model keeps working: what happens when OpenAI or Anthropic releases a new version.

She started worrying three weeks in. You should start on day one.

Hey there! 👋🏿👋🏿👋🏿 I’m Hodman Murad, Founder of The Data Letter, Between Thinking and Doing, and Asaura AI. In case you’re new here, here are some past TDL articles you may have missed:

• I Built an AI Agent That Sends Me My Numbers Every Monday Morning → A step-by-step n8n build that takes an agent from inventing your metrics to reading them from a live Google Sheet, remembering context, recovering from failed steps, and reporting on its own every Monday, all running free on a local model.

• Prompt Engineering.: Treating LLM Prompts as Software Assets → Why ad-hoc prompting breaks once three engineers touch the same string and a model update degrades your outputs; and, how versioning, structured evaluation, cost tracking, and drift monitoring turn prompt management into a boring, solved problem.

• n8n. local. → A 30-minute build that gets a private AI agent running free on your own laptop with n8n, Ollama, and Docker, no API keys and no model weights leaving your machine, ready to take on a recurring job your team already does.

Version churn is the breakage nobody prices in

When a vendor ships an update, the model starts behaving differently.

When the company that makes your model releases a new version, the same prompt and settings you tested can start returning answers in a different format, or skipping details it caught before. Operations leads and analysts have watched a support classifier that sorted tickets cleanly on one version start mislabelling them on the next. A model that read a 40-page contract end-to-end last quarter now skips the middle pages and summarises only what it saw at the beginning and the end.

You changed nothing in your code. The vendor changed the model, and your results changed with it.

So the question worth asking is how the model behaves when OpenAI or Anthropic updates it on their schedule.

That question rarely comes up before a team commits.

Subscribe now

Cost is the same trap wearing a different coat

Breakage has a financial twin: the bill.

Token billing means your spend scales with use, and use scales the moment the workflow works, and the team starts to depend on it. Operators report the bill arriving like a surprise, because the thing that made the tool valuable, everyone using it, is the same thing that made it costly.

Both fears come from one root:

You committed to a model without a way to judge what you were committing to.

How Experienced Operators Pick a Model They Can Trust for a Year.

Experienced operators care less about which model is cleverest and more about which one they can rely on month after month. They’ve learned that the model that scores highest on a benchmark today isn’t always the one that still sorts your support tickets correctly after the vendor updates it.

They choose durability over dazzle.

The model that tops the benchmark this week and the model still working in your stack a year from now are often two different models. You learn which one you’ve got by running it on your own work, watching what it costs as your team uses it more, and seeing how it behaves when the vendor updates it next.

Subscribe now

Your instinct is right. The framework is what’s missing.

So your hesitation looks like timidity. It’s good judgment, you just don’t have a way to act on it yet.

The teams that commit fastest are often the ones who get stranded, because they chose on capability alone and never asked what happens when the vendor updates the model. The teams that hesitate are right to fear getting locked into a model that breaks; they just have no structured way to test for it.

What you need is a way to test a model before you commit, one that weighs how it handles vendor updates, what it costs as your team uses it more, and how narrow the job is, rather than how impressive its answers look in the first demo.

So this week I’m walking through the choice live, in two parts.

Wednesday, June 10th, 8:30 AM EST, live: Pick an LLM You Won’t Regret. I’ll walk through a clear set of checks for choosing a model. How to read a version string so you know what you’re committing to, what a model costs as your team uses it more, and whether your task is narrow enough to catch a bad answer fast. You’ll leave with a way to choose instead of a guess.

On Thursday, we’ll go one level deeper, into the answer that takes the update schedules of OpenAI, Anthropic, and Google out of your hands for good: Fine-Tune and Deploy an LLM Without an ML Engineer. You decide when to update, instead of waking up to a vendor’s change you didn’t choose. Your weights, your control, start to finish.

Wednesday tells you which model to trust. Thursday hands you the build where you stop living by a vendor’s release calendar.

Choose the version after this one, not the demo in front of you.

Subscribe now

I showed this on my weekly live session yesterday morning (Every Wednesday at 8:30 AM EST). I built a small AI agent in n8n whose only job was to answer questions about my startup’s weekly metrics. I asked for last week’s churn rate. It gave me a number, a cancellation count, even a quarterly comparison. All of it was invented. It never once looked at Asaura’s user data.

An agent like that doesn’t crash or flag a problem. It hands you a wrong answer that looks just like a right one, and you don’t catch it until someone manually checks. The fix is a set of techniques that make an agent read from a live source, remember what it’s doing, recover on its own when a step breaks, and run on its own.

Hey there! 👋🏿👋🏿👋🏿 I’m Hodman Murad, Founder of The Data Letter, Between Thinking and Doing, and Asaura AI. In case you’re new here, are some recent articles you may have missed:

Code w/ Claude: 5 Data Science Trends I’m Watching → Five shifts coming for the data scientist role by 2027, from treating model upgrades like dependency bumps to curating memory the way we curate feature stores.

Build Your Own AI Agent Before Google Ships You Theirs → Why Google’s five overlapping consumer agents don’t fit a small ops team, and how to put one working agent on one recurring job this week instead.

Build a RAG System with NotebookLM in Under an Hour → A hands-on build that gets you a private RAG running on your own documents, plus the ten engineering terms you’ll need to lead any AI conversation at work.

Build Your First AI Data Pipeline in Python: From Raw CSV to Predictions → A step-by-step scikit-learn tutorial that turns vehicle data into CO2 predictions and teaches you to read your model’s metrics honestly, even when the answer is that your model is useless.

Today’s build is the next one in this series.

This guide builds that agent from scratch in n8n, step by step. You’ll start with a simple agent running on a local model. Then you’ll connect it to your live metrics, give it memory, make it handle failures, and schedule it to report on its own every Monday (or whichever days you pull your numbers). It runs entirely free.

Read more

Whose model scores highest? Whose benchmark beat whose? Who topped the leaderboard this week?

Model. Model. Model.

But inside your company, model IQ isn’t the thing hurting you.

Your agents pile up. Forget what they were doing. Snap the second one step downstream fails.

I keep seeing the same fear surface, even in seasoned teams: ‘We shipped the agent, so why does it keep breaking??’ Because building one and running one are two different jobs.

To be clear, I’m not anti-agent. I build them. I run them.

The trouble starts when everyone treats the model as the finish line and forgets the pipes underneath.

Hey, everyone! 👋🏿👋🏿👋🏿 In case you’re new here, I’m Hodman Murad, Founder of The Data Letter, Between Thinking and Doing, and Asaura AI. Here are some recent TDL articles on AI agents and orchestration you may have missed:

• On the orchestration layer, and why it decides who gets leverage from cheap models: 'NVIDIA and AI Inference Economics in 2026.'

• On building your own agent instead of waiting for a vendor: 'Build Your Own AI Agent Before Google Ships You Theirs.'

• On the step-by-step build: 'n8n. local.' A private AI agent running on your own laptop in about 30 minutes, using n8n, Ollama, and Docker.

• On grounding, the thing that keeps an agent from making things up: 'Build a RAG System with NotebookLM in Under an Hour.'

• On reading a model honestly before you trust it: 'Build Your First AI Data Pipeline in Python.'

  ---

Why Reliability Beats Model IQ

So the contest is about reliability now.

When every vendor ships a frontier-class model, the model stops being worth fighting over. So the fight climbs one floor up. To the layer that decides which agent touches which system, gives each one an identity, logs what it did, and shuts it down when it misbehaves.

This is the control plane. The plumbing for a building full of agents.

Subscribe now

Microsoft and Google Build the Agent Control Plane

Watch the giants. They’ve stopped pretending it’s about the model.

Last November, Microsoft shipped Agent 365 and named it ‘the control plane for AI agents.’ Registry, identity, security, the works. A place to govern every agent, whoever built it.

Then, in April 2026, Google launched the Gemini Enterprise Agent Platform. Build, scale, govern, optimize. Agent Identity. Agent Registry. An Agent Gateway they call ‘air traffic control for your agent ecosystem.’

Read the two feature lists side by side.

Registry. Identity. Governance. Gateway.

Two rivals, working apart, are using the same vocabulary to describe their products.

When competitors employ identical marketing language, they’re telling you where they think the market is headed.

And the prize they’re naming is the plumbing.

Accenture argued that Agentic AI is becoming the interface across your platforms, orchestrating work in real time. The agent sits on top of finance, the CRM, and the supply chain, and runs across them.

Whoever owns that orchestration layer owns the customer.

Subscribe now

Reliability Problem Behind AI Agents

The first wave of agents is breaking in the field.

VentureBeat reported last month that teams are entering what one engineering leader calls a rebuild era. They rushed agents out, skipped the underlying plumbing, watched them crash, and went back to rebuild on a solid base.

Her words: ‘They had to move really fast, but they didn’t take care of the plumbing. Things crash and burn.’

Crash and burn.

Independent benchmarks back her up. Researchers found that for long-running tasks, the same agent can produce different results on each run. It finishes the job cleanly one day and falls apart the next.

In one benchmark, agents ran a small vending-machine business over many days. Some lost track of the job entirely and began sending angry, irrational emails to suppliers over a one-dollar fee.

So buyers care less about which model is smartest. They want to know one thing: Can I trust this to run, recover when it fails, and tell me what it did?

Subscribe now

What Agent Platform Wars Mean for Your Team

Maybe you govern ten thousand agents. Maybe you run three workflows that your team relies on every morning.

Same problem at either size. No orchestration. Context that drops halfway through. No way to recover when one step fails. Same lesson, your scale.

The takeaway: reliability comes from how you build, not how much you spend. The giants pay billions for it. You can build the same habits into one workflow on your own. Do that, and it keeps running when a step fails instead of crashing.

Ok, in closing.

The giants are spending billions to own their plumbing.

You can fix yours this week.

This Wednesday, June 3rd, 8:30 AM EST, I’m going live on Substack again: ‘Why AI Workflows Break (and How to Fix Yours Before It Costs You).‘ We’ll pull apart why these systems fail and what a steady one looks like.

You can read the follow-up to I Built an AI Agent That Sends Me My Numbers Every Monday Morning,’ is the system that fixes it, and it is walked through so you leave with one running.

A smarter model won’t save a workflow that keeps breaking. Build the system that keeps it running.

Subscribe now

Operations teams want one working agent on one recurring job this week that they own end-to-end. Google has options on both ends of the spectrum (consumer apps like Gemini Spark and enterprise platforms like Gemini Enterprise). Neither is built for a small ops team looking to operate a recurring task.

Today, we build that agent.

In the next 30 minutes, you’ll have a private AI agent running on your own laptop. It costs zero dollars. No model weights leave your machine. Once the basic loop runs, plugging in a tool turns the agent into something that handles jobs for your team, such as drafting replies in your support inbox, pulling a number from a spreadsheet on a schedule, and triaging incoming customer support requests.

Subscribe now

What you’ll find inside this post

• The full step-by-step setup

• A downloadable n8n workflow file.

• The setup errors you’re likely to hit and how to fix each one.

• Three ways to put the agent on a job your team already does.

• A video walkthrough of the finished agent

Read more

AI Mode in Search just crossed one billion monthly users, with queries more than doubling every quarter. Liz Reid, who runs Search, described what’s happening as ‘the era of Search agents,’ and said Google’s new information agents run in the background, performing repetitive work and notifying users when something changes.

What an AI agent does

An agent has four moving parts:

• It perceives an input.

• It reasons through what to do.

• It acts in your tools.

• It remembers what happened, so the next run starts smarter.

Chat does the first two. Agents do all four.

Chat changed how quickly you can think and draft. Agents now manage what gets done while you’re working on something else.

Subscribe now

Why Google’s version isn’t the one your team needs

Google packaged these capabilities for consumers, but the packaging is messy. Google now has Gemini as the model, Gemini Spark as a personal assistant, Android Halo as a notification system for Spark, Information Agents inside Search, and Daily Brief as a morning digest. Five products under one company, each with its own brand, each doing a slightly different version of the same job. A consumer trying to figure out which one to use for which task is doing work Google should have done before the keynote.

The combination of a $100-a-month entry price and five overlapping product names means a team lead trying to put an AI agent into a workflow this month has to first decode which Google product to buy, then justify the spend, then hope the consumer-facing version maps onto a work task. None of that is how teams adopt new tools.

Agents are a genuine new capability. The consumer-facing version Google led with at I/O is built for personal life. Google’s enterprise agent products, such as the Gemini Enterprise Agent Platform and Agentic Data Cloud, operate on the Cloud side and target large organizations with platform teams and procurement cycles. Neither one helps a small operations team that wants an agent to triage their inbound support emails or pull their weekly numbers from three tools into one report.

Subscribe now

Your team’s first AI agent is closer than a Google subscription

You can put one agent on one recurring job your team already does, this week, without waiting for Google.

A data scientist can put one into a pipeline. A team lead can put one into a recurring workflow. A head of ops can put one into a standard process. The underlying parts (perception, reasoning, action, memory) are the same even when the job changes.

The skill that’s becoming valuable for every team isn’t knowing how to pay for a subscription.

This Wednesday, May 27th, at 8:30 AM ET, I’m running a live build: How to Build an AI Agent for Your Team. We’ll put a working agent together in real time using n8n.

🚀 Thursday’s post is the full write-up with the build and deploy steps. Get it here now.

RAG stands for retrieval-augmented generation. It’s a way to build AI systems that can answer questions using your own documents rather than guessing from general training data. When you ask a RAG system a question, it searches your documents, finds relevant pieces, and writes an answer based on what it finds. Every internal AI assistant your company is piloting right now uses some version of this.

Today, you’re going to build a RAG system on your own documents in under an hour. You’ll do it in Google’s NotebookLM, a polished interface built on top of the same retrieval-and-generation architecture your company is paying engineers to build. By the time you finish, you’ll have a working private RAG running on your laptop, and you’ll know roughly ten engineering terms well enough to use them in a conversation.

What You’ll Have at the End

A working RAG system reading from a folder of your own documents, returning answers with citations to the source files, running in your browser, free.

You’ll also have the vocabulary to walk into your next engineering meeting and say things like ‘what’s our chunking strategy?’ or ‘how are we handling grounding at the retrieval layer?’ and sound like someone who’s done the work.

Subscribe now

What You Need Before You Start

A Google account. NotebookLM is free with any Google account, and it doesn’t require Workspace.

A folder of documents you’re allowed to upload. PDFs, Word docs, Google Docs, plain text, web URLs, and YouTube transcripts all work. For this build, I’d suggest using your own writing or a project’s documentation. Don’t use your company’s confidential materials in a personal Google account. That’s a violation of every company AI policy I’ve ever read, and the point of this build is learning, not getting yourself in trouble.

For this build, I used three articles from TDL and one from my other publication, Between Thinking and Doing (BTD).

The TDL pieces:

• Choosing Between Fine-Tuning, RAG, and Prompt Engineering: A $10K Decision Guide

• Vector Database Guide

• My AI gave me fake data. Here’s how to catch it if it happens to you.

From BTD:

• AI Keeps Losing Your Train of Thought

It’s important for three of these articles to operate within the same domain so that synthesis questions have relevant material to work with. The BTD piece is unique, allowing retrieval to select from multiple sources rather than choosing any one. You can do the same with any documents you own or have permission to upload.

It takes about twenty minutes, but you can finish faster if you move through the steps quickly.

Step 1: Open NotebookLM and Create Your First Notebook

Go to notebooklm.google.com. Sign in with your Google account.

Click ‘Create new notebook.’

Subscribe now

What just happened, in operator terms. What you just did was initialize an empty RAG. There’s a structure waiting for documents, but no documents are in it yet. In engineering terms, you’ve created an empty vector store. A vector store is an indexed library where your documents are stored in a format that the AI can search. NotebookLM uses Google’s own vector store behind the scenes, so you don’t pick one or configure it. At your company, engineering will pick one (you’ll hear names like Pinecone, Weaviate, or Chroma), and that choice affects cost, speed, and the country where your data is stored.

That's the vocabulary from Step 1. Below the paywall, I'll walk you through seven more steps that get you to a working RAG running on your own documents. You'll learn how to ingest sources, watch chunking and embedding happen, run the three stress tests that show what your RAG can and can't do, and walk away with the ten engineering terms you'll need to lead any AI conversation at your company.

Read more

I walked through RAG, the technology behind every enterprise AI tool worth running, and the four areas senior managers and operators need to own when their company is rolling one out. About 20 minutes.

Tomorrow morning, I’m publishing a hands-on build: how to set up a RAG system on your company’s internal docs in under an hour. Same concepts from the Live, this time as something you can follow along with and have running by the end.

If you’ve been thinking about upgrading, this is a good week to do it.

UPGRADE

See you in the morning,

Hodman

Last week, I wrote about the infrastructure providers behind Frontier AI and the over $100 billion deals that Anthropic signed with AWS, Google, and Broadcom, which are shaping the future of frontier AI technology. That piece was the macro view: who controls the compute, the chips, and the power contracts that frontier AI runs on. What cheaper inference does, and doesn’t do, for the people doing the work is the micro level of this issue.

So why do operators, managers, and students still feel buried? Because cheaper inference doesn’t automatically translate into less friction in your day.

📡 Going live this week. RAG is the engine behind every enterprise AI tool you’ve already used and trusted. Glean. Copilot. Notion AI. The internal assistants your company is piloting right now. It’s also the thing nobody outside the data team is talking about. That’s a problem, because if you’re a manager or operator and you don’t understand RAG, you can’t tell the difference between an AI rollout that earns adoption and one that will be sundowned in six months. I’m going live on Substack this Wednesday, May 20th, at 8:30 AM EST to break it down: what RAG is, why it’s the foundation of every useful enterprise AI deployment, and why operators (not just engineers) need to understand it.

Join Me Here

Back to inference economics.

Cheap Tokens, Same Overwhelm

Gartner expects agentic AI workloads to burn 5x to 30x more tokens per task than standard chatbots, which means the falling per-token price is already being offset by rising consumption. The companies serving you AI will keep a healthy share of those savings, and the ones they pass along will get poured into longer context windows, more tool calls, and more autonomous loops. None of that, on its own, fixes the underlying human problem: the work itself keeps outrunning the worker’s ability to stay in context. Cheaper inference makes it economically viable to throw more AI at a worker without making the work itself any easier to do well. If you’ve felt that the tools got smarter but your workload didn’t get lighter, you’re reading the curve correctly. Cheaper inference is a supply-side phenomenon. It doesn’t reach the worker until something on top of the model reduces friction.

Who Pays for Cheaper Inference

The cost of running AI doesn’t disappear when per-token prices fall. It gets redistributed:

• Frontier Labs absorbs some of it itself to keep its models competitive.

• Hyperscalers recover it by bundling inference into platform contracts, the same playbook AWS ran with storage and bandwidth a decade ago.

• Enterprises pass it through to end users as seat prices, usage caps, and tiered features.

The worker sits at the bottom of that chain. A 10x cost reduction at the chip level rarely translates into a 10x improvement in a worker’s day. By the time it filters through cloud contracts, vendor pricing, and product packaging, your team will end up with a marginally better tool and a slightly larger software budget. The savings are reinvested in additional capabilities for vendors to sell, rather than in capacity that the worker keeps.

What This Means for the Future of Work

The shape of work over the next few years will be decided by who can afford to deploy frontier inference broadly, and by how that inference is packaged before it reaches a worker’s desk. AI capability is becoming an organizational asset rather than an individual one. The worker at a company with a rich inference budget will get more out of frontier AI than one without, and that difference will widen as agentic workloads burn 5x to 30x more tokens per task than today’s chatbots.

Once every team has a frontier model, the orchestration layer will be what separates teams. Whether your context, decisions, and in-flight work are held together by a system or scattered across tabs determines how much of that frontier capability you can actually use.

And the human cost of bad orchestration grows with model capability. More powerful tools used badly create more interruptions, more half-finished threads, more cognitive debt. Cheap inference, poorly wrapped, is a faster way to feel overwhelmed.

Subscribe now

The infrastructure layer is solving its own problem. What still needs building is the layer between cheap compute and a working day, the one that decides whether all that capability turns into leverage for a person, or just more input to sort through. Asaura AI is one bet on that layer, built for people who already feel the difference between having access to a powerful model and having a successful day at work. The broader point applies regardless of which tool you use. In a world where the model is cheap and the work keeps expanding, the system that organizes your context, your priorities, and your decisions is the part that compounds.

Per-token prices will keep falling. Token consumption will keep rising. Both can be true, and both already are. What decides whether that ends up as leverage for you, or as a faster firehose pointed at your inbox, is the orchestration layer sitting between the chip and the chair. I’ll keep following this trend, both on the economics side and on what the layer between the model and the worker has to look like.

Subscribe to The Data Letter for more on the economics of AI and the future of work.

SUBSCRIBE

If you want a system that keeps your context, your goals, and your work organized on the days your brain pushes back, try Asaura AI.

GET ASAURA