user@gitdiot:~/blog$
● online v26.05.02 ~/about
$ cat ./README.md --render --frontmatter=full
$ git log learning-from-mistakes -- A how-to series on getting agentically augmented 02 commits · 23m read
a7f3e21
feat: fragRag — persistent memory for Claude Code across machines
Every new Claude session is a blank slate. We wanted it to remember everything, everywhere, automatically. Here's the six-phase journey: OMC skills that didn't register, CLAUDE.md directives ignored, eager loading wasting tokens — and what finally shipped.
supabasenodeclaude-codemcp
@michael
6 weeks ago
14 min read
 b9c102f
docs: WTF is Git, why do I care, and how come it makes me nervous?
A completely honest explanation of version control for people who have been in tech long enough to know they should understand this, but somehow never quite got there.
gitprimer
@michael
a month ago
9 min read
$ git log how-i-operate -- Technical deep dives into the current stack 09 commits · 2 staged · 90m read
f01a2c9
feat: debugging across machines — two Claude instances collaborating through Git
A remote MCP server was broken. Two Claude Code instances on different machines fixed it by communicating through Git commits. No SSH tunnel, no shared terminal — just commits as a communication protocol between agents.
gitclaude-codenodemcp
@michael
6 weeks ago
12 min read
 c01ab17
case: two AI teams collaborating in real-time via Git, shared drives, and RAG memory
Building a cross-team prospect tracking system across three collaboration channels — and the surprising role AI-to-AI communication played.
claude-codefragraggit
@michael
2 months ago
10 min read
 aa9fb22
arch: building a persistent RAG memory system for Claude Code
Supabase + pgvector + Voyage AI embeddings + dual-transport MCP + Cloudflare + Caddy. The full architecture.
supabasemcpcloudflare
@michael
6 weeks ago
15 min read
 b3d54a8
case: why your AI agent is too enthusiastic to follow a process
An agent ran a flawless prospecting campaign that tested nothing it was supposed to test. The architectural lesson: agents should own content, not process.
claude-codemcpworkflow
@michael
5 weeks ago
10 min read
 5e29a01
case: swapping our research engine from Perplexity to Google + Claude
A blind, cross-family eval picked the challenger 24/25 — after our first read was wrong. Then a billing outage turned the experiment into a migration, no scramble, because everything sat behind a swappable port.
serpapiclaudeevalsports
@michael
just now
11 min read
 e5f6b22
deep: what Google's Admin API actually knows about your emails
Delivery path, encryption, auth, spam verdicts, even opens and clicks — all locked behind an Admin Console UI. The Reports API and BigQuery unlock it.
google-adminbigquerysupabase
@michael
3 months ago
11 min read
 a1d77c3
feat: email open tracking that doesn't hurt deliverability
Most trackers use invisible 1x1 pixels that spam filters strip. We used the company logo instead — expected in every signature, and it doubles as the beacon.
supabasenodegmail
@michael
3 months ago
8 min read
 d3c4a18
case: Google's permission maze that fragmented our auth
A CRM that worked on day one slowly fractured into three auth profiles with mismatched scopes and silent failures. Untangling Google's permission maze.
google-workspaceoauthsupabase
@michael
3 months ago
7 min read
 b22ef90
case: how we broke our own CRM workflow — and fixed it better
Documenting a system, then watching an AI agent run it from memory — inventing half the steps. The recovery was more useful than the original workflow.
supabaseclaude-codegmail
@michael
3 months ago
6 min read
bc0e441
case: a Hetzner VPS, Ubuntu, and the lost art of owning infrastructurecoming soon
After 15 years of managing teams who managed AWS, I rented bare metal for $12 a month.
vpsubuntucloudflare
@michael
draft
staged
e0f1336
case: the CRM nobody configured right — rebuilding HubSpot from the data upcoming soon
Every company I've worked at had a CRM. None of them had clean data. n8n + a Supabase staging layer to fix it.
supabasen8nhubspot
@michael
draft
staged