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. There's no SSH tunnel and 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
2 weeks ago
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; it's expected in every signature and 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, then 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