The Macroline Blog
Notes from a tracker built differently.
AI-native macro tracking, GLP-1 and nutrition science, what makes food data actually trustworthy.
Start here
GLP-1 and macro tracking — why precision matters more, not less
GLP-1 medications change appetite, satiety, and food choices. Here's how macro tracking should adapt — and why "good enough" calorie estimates aren't.
Maya Chen AI-native vs. AI-bolted-on — a developer's take
The difference isn't a chatbot button. It's whether the product was designed assuming an AI agent would be a primary user. Most "AI features" still aren't. Here's how to tell, and why it matters.
Alex Rivera What 'verified' nutrition data actually means
Most macro trackers display numbers without telling you where they came from. Here's why that's a problem, and how Macroline shows its work on every food row.
Marcus Hayes Writers
You don't eat a thousand foods, you eat the same twenty
People quit tracking because they think it means endlessly searching a database. It doesn't. Here's the retention trick: set up your staples once, then re-log them in seconds.
Marcus Hayes I asked Claude what to order, then told it to log it
Macroline runs as an MCP server, so an AI assistant can read your diary and write to it. Here's a real workflow: ask Claude for the best thing to order, then have it log the meal, without the AI ever inventing a number.
Alex Rivera How to track restaurant food you didn't cook
The hardest meal to track is the one someone else made. No label, no scale, no barcode. Here's how to log it honestly instead of giving up on the whole day.
Maya Chen How two untracked days erase five good ones
A client swore he tracked perfectly all week and wasn't losing. He did track perfectly, Monday through Friday. Here's the weekend math that was undoing the whole thing.
Marcus Hayes Protein and muscle on a GLP-1: what the scale won't show you
On a GLP-1 the scale moves on its own. What it won't tell you is how much of the loss is muscle. Here's why protein matters more when you're eating less, and how to actually hit it.
Maya Chen What we built — Macroline 1.0 ships today
Today Macroline 1.0 lands on the App Store. Here's what's in the box, what we deliberately left out, who 1.0 is for, and the design principles behind the cuts. Substance, no hype — that's the brand.
Alex Rivera No tracking, no theater — the macroline.app stack, in full
Most consent-banner sites set thirty or more third-party cookies on first load. macroline.app sets zero non-strictly-necessary cookies. Here's what we actually use, what we deliberately don't, and why the popular "Accept all / Reject" pattern is theater more often than it's a defensible privacy practice.
Alex Rivera Bad food data wrecks a cut faster than bad programming
I've audited the food logs of more than thirty clients whose cuts stalled. The training plan wasn't the problem in roughly twenty-four of them. The numbers in their tracker were off, sometimes by a lot, and the compounding made the stall inevitable.
Marcus Hayes Calorie targets after bariatric surgery — why your app should never refuse the number
A bariatric beta tester told us the iOS app wouldn't let her set 880 cal/day, even though her surgeon prescribed it. The bug is on us. But it's also a pattern in nearly every tracker on the App Store, and it tells you something about how the industry thinks about you.
Maya Chen What "evidence-based" actually has to mean now
Every nutrition app, supplement brand, and Instagram account in 2026 calls itself evidence-based. The term has lost most of its meaning. Here's what I actually evaluate when I use the phrase, and what I think you should ask of anyone using it about your food.
Maya Chen What "losing strength on a cut" actually looks like in numbers
Lifters dread a strength drop on a cut, but the actual losses you should expect are small and recoverable. Here's the data on what to anticipate, when to worry, and when the drop is just water + glycogen.
Marcus Hayes GLP-1 and macro tracking — why precision matters more, not less
GLP-1 medications change appetite, satiety, and food choices. Here's how macro tracking should adapt — and why "good enough" calorie estimates aren't.
Maya Chen What 'verified' nutrition data actually means
Most macro trackers display numbers without telling you where they came from. Here's why that's a problem, and how Macroline shows its work on every food row.
Marcus Hayes Why we built an MCP server for nutrition data
Macroline runs as a Model Context Protocol server. Here's what that means, why it matters, and how AI-native tools change what a tracker can be.
Alex Rivera The 3 macro tracking mistakes I see lifters make
After coaching enough cuts, the same patterns show up. Most lifters' tracking isn't wrong because it's hard — it's wrong because of three specific habits that compound into 200–400 calorie daily errors.
Marcus Hayes Eating out on a cut — ordering strategies that don't blow your day
Restaurants are where most cuts go off the rails, but they don't have to. Here are the tactics that work without making you the difficult one at the table.
Maya Chen AI-native vs. AI-bolted-on — a developer's take
The difference isn't a chatbot button. It's whether the product was designed assuming an AI agent would be a primary user. Most "AI features" still aren't. Here's how to tell, and why it matters.
Alex Rivera Refeeds vs. diet breaks — which one actually helps
A weekly carb-up day and a 14-day return to maintenance look like the same idea, but the research is clearer than the bro-science. Here's what each does, when each works, and when you don't need either.
Marcus Hayes Postpartum macro tracking — the lactation modifier nobody mentions
Most tracking apps treat lactation as a footnote. The metabolic reality is anything but. Lactating bodies need 400-500 additional kcal/day plus an extra 15-25g of protein, and the timing across a feeding schedule matters more than the daily total.
Maya Chen GLP-1 plateaus — when the scale stalls and what it means
Most people on Wegovy, Ozempic, or Zepbound hit a plateau at some point. Some are signal. Most are noise. Here's how to tell which is which without panicking.
Maya Chen Building an MCP server — lessons from the trenches
Notes from implementing a production-ready MCP server with OAuth 2.1, dynamic client registration, and a real consumer app on the other end. The places we got it wrong, and how the spec helps and hurts.
Alex Rivera Bulking with precision — why "see food diet" is wrong
The old advice was eat everything, gain everything, cut later. The newer research says you can build muscle on a much smaller surplus than that — and the fat tax of dirty bulks isn't worth the marginal muscle.
Marcus Hayes The maintenance phase nobody talks about
Most people who lose weight regain it. Not because they fail at the cut — because they treat the period after the cut as "back to normal." Here's how to think about maintenance instead.
Marcus Hayes How to read a nutrition label like a dietitian
The label gives away more than most people realize — once you know what to look for. A practical walk-through of the lines that matter and the ones that don't.
Maya Chen Designing for AI clients vs. human clients — same data, different shape
A REST API for humans and an MCP server for AI agents look superficially similar. They aren't. The contracts, error semantics, and data shapes that work for one are quietly bad for the other. Here's what the second-class consumer of your API actually needs.
Alex Rivera How MCP changes the API economy
The Model Context Protocol isn't just another integration spec — it's a shift in who the primary user of an API actually is. Here's what that means for product builders.
Alex Rivera How to cut without losing strength — a 12-week template
A practical fat-loss framework for lifters who care more about strength than the scale. Caloric structure, protein floor, lift selection, and when to break.
Marcus Hayes Why protein targets matter more after 40 — especially for women
Sarcopenia starts earlier than most people realize, and the standard 0.8g/kg recommendation is set up to fail you. Here's what the research actually says about protein, age, and lean mass.
Maya Chen When AI is wrong about food (and how to spot it)
AI is good enough at parsing meals into macros that the failure modes are no longer obvious. The wrong number doesn't look wrong. Here's a taxonomy of the specific ways AI gets food data wrong, and what to look for in your own logs.
Alex Rivera Deloads aren't optional — even for naturals
The "I don't need a deload, I'm not advanced enough" argument is exactly backwards. Deloads aren't a reward for being strong; they're the mechanism that lets you get strong. Here's why mid-cut deloads are non-negotiable.
Marcus Hayes Why I don't connect my food log to my AI assistant
I work on AI tooling. I build MCP servers. And I deliberately do not connect my personal nutrition data to a cloud AI assistant. Here's the threat model, what 'connected' actually exposes, and the version of this I do use.
Alex Rivera Compounded GLP-1s in 2026 — what changed and what to ask
The compounded GLP-1 market shifted hard between mid-2024 and now. The FDA shortage list ended for tirzepatide in early 2025; semaglutide compounding is on tighter footing too. Here's where things stand for patients in early 2026, and what to actually ask your prescriber.
Maya Chen The "cut" that's really a binge cycle
If your week looks like 1400 calories Monday through Thursday and 4000+ on the weekend, you're not on a cut — you're on the binge cycle that pretends to be one. Here's how to tell, and how to break it without restarting.
Marcus Hayes Your TDEE math is wrong (and that's not your fault)
Mifflin–St Jeor + an activity multiplier is the standard, and for most women in their 30s and beyond it's off by 200–400 calories. The equation wasn't built for you. Here's what it gets wrong, what to use instead, and how to find your number with one week of data.
Maya Chen MCP turned one — what shipped, what didn't
Anthropic announced the Model Context Protocol in late 2024. A year and a quarter in, the protocol has stabilized in surprising ways and stalled in others. Here's what's actually in production, what got built and abandoned, and where I think the next year goes.
Alex Rivera When January falls apart — what to do in February
The annual cycle is predictable. Strong start, slip mid-month, full collapse by the end of January, vague guilt through February. Here's how to actually use February to fix what January's structure couldn't.
Marcus Hayes Tools we wish existed in the macro-tracking category
An honest builder's wishlist for what's still missing in nutrition tracking, from substitution preview to cross-tracker import. Open product brief, not a roadmap.
Alex Rivera What a realistic deficit actually looks like
Why "1 lb a week" is too aggressive for most non-obese lifters. The 0.5-0.75% bodyweight rule, the math on a 350 vs 700 calorie deficit, and where the apps get this wrong.
Marcus Hayes GLP-1 starter guide: the first 30 days
A week-by-week clinical guide to your first month on semaglutide or tirzepatide. What to expect, how to hit protein when food is unappealing, and when to call your prescriber.
Maya Chen New year, same approach
Patients who succeed long-term didn't restart their tracking January 1. They kept going through December. Here's what to actually do if you're motivated today.
Maya Chen Christmas Day is not a binge
The case for one designated non-tracking day per year. Weekly averages still hold, cortisol from food guilt costs more than the calories, and your weigh-in can wait until Tuesday.
Maya Chen Why we wrote our own nutrition parser instead of stuffing GPT into it
A vanilla LLM call looks like a free meal parser until you ship it. Here's what breaks (units, portions, brand canonicalization) and why a structured parser with confidence scoring is the right tool.
Alex Rivera Train days vs rest days: should your macros match?
Macro cycling fundamentals. When carb cycling matters (advanced bulks, contest prep), when it doesn't (most lifters). Practical protocol if you want to try it.
Marcus Hayes Hydration is the most under-tracked variable in macros
Water and electrolytes affect scale weight, lift performance, energy, and appetite, yet almost no one tracks them. Here's a clinical framework for getting it right.
Maya Chen Cutting through Thanksgiving week
It's not the dinner that wrecks the cut, it's the leftovers. Here's the Monday-through-Sunday protocol: prep days, alcohol math, what to do if you wake up Friday at +3 lbs.
Marcus Hayes Pre-workout nutrition without the marketing
Cut through the supplement-industry noise on pre-workout. What actually matters: real-food carbs 60-90 minutes out, caffeine timing, hydration, and why most powders are a $40 caffeine pill.
Marcus Hayes The trust problem with crowd-sourced macros
A patient logged the same wrap from 5 different community entries and got 320 to 780 calories. Here's why crowd-sourced nutrition data fails, and what to look for instead.
Maya Chen The Thanksgiving math problem
How to estimate macros on Thanksgiving without driving yourself crazy. Front-load protein, use the 60-30-10 rule, estimate high, and trust the 7-day average.
Marcus Hayes No posts match this filter — try "All" or a different topic.