
Build Daily
Tinley Park · July 1, 2026Posts
What I worked through enough to put on paper. The read, the take, what changed.
All entries
- § 01field notesessay
Loop engineering without the cloud bill
The best writing on agent loops assumes you'll run them on a vendor's cloud, metered per token. I run the same loop architecture on a laptop that refuses to sleep — and the only surface that actually needed the cloud was the one I don't use.
Filed · Jun 30, 2026Read on ↗ - § 02field notesessay
Anatomy of an AI product
An AI product isn't one clever model call — it's a stack of layers, split across two planes: a live request path and an offline batch plane that feeds it. Here's the anatomy, where DSPy fits, and why Airflow is not where most people put it.
Filed · Jun 27, 2026Read on ↗ - § 03field notesessay
Base wants to be the chain for AI agents
Base shipped an agent infrastructure layer — wallets with spending limits, an MCP server that talks to DeFi protocols via natural language, an HTTP payment standard called x402, and an identity primitive for onchain agents. Most of the metrics page reads zero. Here's what matters anyway.
Filed · Jun 27, 2026Read on ↗ - § 04field notesessay
Build an AI Product
A build-along series that reconstructs the chat agent on this site, one layer at a time — the brain, the evals, the grounding, the serving, the guardrails. You're talking to the project. Here's the map before we start.
Filed · Jun 27, 2026Read on ↗ - § 05field notesessay
DSPy vs LangChain for typed LLM programming
Both help you build with LLMs, but they sit at different altitudes. LangChain gives you components to wire together and prompts to write. DSPy gives you typed signatures and a compiler that writes the prompts for you. Here's how I choose.
Filed · Jun 27, 2026Read on ↗ - § 06field notesessay
Prompt engineering was never the bottleneck
Everyone optimizes the prompt. But when an agent runs in production, the wording is rarely what makes or breaks it — the harness around the model is. Here's what harness engineering means, and why it's the half of the work that actually matters.
Filed · Jun 27, 2026Read on ↗ - § 07field notesessay
The voice gate that grades me, too
I built a structural rubric to grade the agent that drafts my posts. The real payoff came when it started gating every post on the site — including the ones I write by hand — holding me to the same bar I set for the machine.
Filed · Jun 27, 2026Read on ↗ - § 08field notesessay
What is DSPy?
DSPy gets called a prompt framework, which undersells it. The point is that you stop writing prompts by hand and start declaring what you want as typed code a compiler can optimize. Here's the plain-English version — and when it's the right tool versus the wrong one.
Filed · Jun 27, 2026Read on ↗ - § 09field notesessay
Running agents on the go
Building a field-service app meant I was out testing it instead of at my desk shipping it — and my dev velocity tanked. The fix was four tools and one skill: drive my coding agent from my phone, against the machine at home.
Filed · Jun 20, 2026Read on ↗ - § 10field notesessay
You can't optimize what you can't measure
When the product is a model's output, 'does it work' gets slippery — there's no line of code to inspect. The fix has a boring name and it's the most important idea in building AI products: the eval.
Filed · Jun 16, 2026Read on ↗ - § 11field notesessay
Building with AI is not the same as building an AI product
Two different disciplines wear the same buzzword. One is AI helping me write software; the other is AI that *is* the software. Conflating them quietly muddies every decision — here's the line I draw, and why it makes hard calls obvious.
Filed · Jun 13, 2026Read on ↗ - § 12field notesessay
The best startup idea might be a Boomer's retirement
Most founders build a product and hope someone wants it. There's a generation of proven, profitable businesses about to go dark for want of a successor, and that gap is the most validated demand you'll ever find.
Filed · Jun 3, 2026Read on ↗ - § 13field notesessay
Do you need a multi-agent system?
Claude Code is already one agent with tools. So when does carving it into a roster of named specialists actually earn its keep? Four reasons it does, and a few where it doesn't.
Filed · May 28, 2026Read on ↗ - § 14field notesessay
Smith: the coding agent learning to own my SDLC
The goal isn't an AI that helps me code. It's an agent that owns the development lifecycle — design, test, implement, review, ship — driven from a Kanban board, with as little of me in the loop as I can responsibly remove. Here's where Smith is today, and where he's going.
Filed · May 28, 2026Read on ↗ - § 15field notesessay
Apache Airflow: What It Is and How to Use It
A practical guide to Apache Airflow — what it is, how the Airflow scheduler and DAGs work, retries and backfills, when to use it instead of cron, and a minimal walkthrough. Plus how we run it in production behind paiddaily.io.
Filed · May 27, 2026Read on ↗ - § 16field notesessay
The Airflow DAGs that run paiddaily.io
paiddaily.io is a trading dashboard backed by Airflow DAGs across three DeFi protocols. This is the full architecture — what each DAG does, how fast it runs, and how data flows from chain to screen.
Filed · May 27, 2026Read on ↗ - § 17field notesessay
The weekly Loom: selection, script, distribution
A repeatable workflow for one Loom a week on builddaily.io. How I pick the topic (from the graph, not from a content calendar), how I script it (a seed and three bullets, not a teleprompter), and where the video goes after recording. The goal is a compounding video backlog that recruiters and prospects find alongside the posts.
Filed · May 26, 2026Read on ↗ - § 18field notesessay
When to reach for n8n vs writing the orchestrator yourself
n8n is the best low-code orchestrator I've used — and I don't use it for any of my agent workflows. The decision isn't about n8n being bad. It's about what you're optimizing for: iteration speed on novel logic, or reliability on settled logic. Both are real. The split is load-bearing.
Filed · May 26, 2026Read on ↗ - § 19field notesessay
Why I picked Neo4j over a vector store for my agent system — and when I'd flip
The agent system that runs my life uses Neo4j as its memory layer — not a vector store. Not because vectors are bad (I use them for retrieval) but because the questions I actually ask are graph questions. How the decision landed, where it holds, and the three cases where I'd flip back.
Filed · May 26, 2026Read on ↗ - § 20field notesessay
YearlyPhotos — what I'm building instead of a deal-flow studio
Walking back the deal-flow studio commitment. Same Adobe primitives, different shape — YearlyPhotos turns a phone camera roll into a print-ready family photo calendar. Q4 2026 launch at yearlyphotos.com.
Filed · May 24, 2026Read on ↗ - § 21field notesessay
SEO with a feedback loop
Three things SEO has to do on a personal site: drive cold traffic, measure what lands, and learn from what works. Thirteen stories shipped this week (the schema work that makes the site findable, plus GA4 and GSC for measurement); the five-layer measurement stack is the plan and the pre-commit gate that closes the loop ships next. The one thing the rulebook gets wrong about EEAT, and the rule that broke against my own site.
Filed · May 24, 2026Read on ↗ - § 22field notesessay
Slice 1 of the voice learning loop is live
First end-to-end run of the voice-fidelity drafter — DSPy post_writer + LlamaIndex retrieval over web/content/ + a 10-check structural rubric. The first draft scored 0.886; the rubric flagged the exact LLM tic the editorial rules were written to ban. The eval is doing what evals do. Agent-drafted, edited lightly, published to beta as-is for transparency.
Filed · May 24, 2026Read on ↗ - § 23field notesessay
Teaching an agent to draft in my voice
I'm the only writer on this site. The point of building an agent to draft posts for me isn't scale — it's voice fidelity. Three layered tools and a flywheel that drafts in my voice, gets sharper from my edits, and pays no API bill. The order it ships in, what's already running today, and what's missing.
Filed · May 24, 2026Read on ↗ - § 24field notesessay
When to fine-tune an LLM — and when to skip it
Fine-tuning is the first lever most teams reach for. It's the right one less often than people think. A decision matrix, the steps if you decide yes, what it costs, and one project to put it to work — a small drafter trained on this site's archive that writes the next post in my voice and gets sharper every time I edit it.
Filed · May 23, 2026Read on ↗ - § 25field notesessay
Adobe's Developer API — what can we build with it?
Adobe's developer platform crossed my desk this week. Here's what's reachable from outside an enterprise license, and the one project I'd build to put all of it to work — a freelancer's deal-flow studio from creative brief to signed contract.
Filed · May 21, 2026Read on ↗ - § 26field notesessay
Inside consumer-lending engineering: money, levers, lines
A builder's map of the fintech consumer-lending stack — how a lender actually makes money, what an engineer is hired to move, where AI-augmented development earns its slot, and the regulatory lines you don't cross.
Filed · May 20, 2026Read on ↗ - § 27field notesessay
StoryBrand, the engineer's read
Engineers underrate words. The framework I keep returning to is StoryBrand — read with engineer's discipline. The parts that matter aren't the parts the book puts the emphasis on.
Filed · May 14, 2026Read on ↗ - § 28field notesessay
The retroactive BrandScript
I rebranded two sites this week. One went brandscript → rewrites → code. The other skipped the middle step. Then I wrote the rewrites doc after the code was already live — and that ended up being the most useful artifact of the whole rebrand.
Filed · May 11, 2026Read on ↗ - § 29field notesessay
Three projects, one mission
Drew a line today — sagedaily.io, paiddaily.io, builddaily.io. Everything else paused. Why narrowing matters more than optionality.
Filed · May 10, 2026Read on ↗ - § 30field notesessay
When the limits hit — eight hours with Pi and qwen3.6
Hit my weekly Claude Code Max limit on Saturday. Eight hours later, here's what working only on local models actually felt like.
Filed · May 10, 2026Read on ↗ - § 31field notesessay
A local coding agent on Pi
A local-first coding harness running on a Raspberry Pi — what it does, what it's good and not good at, and how it lives alongside Claude Code.
Filed · May 8, 2026Read on ↗ - § 32field notesessay
Sage Daily — tarot and astrology, daily
Sage Daily is daily tarot, Vedic transit watches, and decision spreads — run by an AI practitioner. Live at sagedaily.io.
Filed · May 8, 2026Read on ↗ - § 33field notesessay
The Personal Agent at builddaily.io
A chat at builddaily.io trained on my own markdown corpus. What it is, how it works, and what it can and can't answer.
Filed · May 8, 2026Read on ↗