Hello, hello! 👋🏻
Everyone's talking about Claude Code this week. I've been quietly using it since August. Here's what 8 months of real usage taught me.
My CC numbers:
226 GitHub commits of 299,206 lines of code
445,303 lines of content
37 custom skills built
33 agents deployed
4.9 Million Claude tokens used
Longest session 1d and 23 min
And when I deleted 761 files
I'll share the wins, the disasters, and where I'm going deeper in 2026. Let me be clear: I don't code. What I do is orchestrate, directing AI to build what I can see but can't write myself. (Skip the "vibe coding" label. That's developers being dismissive. This is something new.)
August: The Beginning of me and CC
I was fed up with running prompts in ChatGPT and Claude at the same time. I started to look for a system that would let me be multi-AI from one interface.
Day 1: Did a test of Claude Code and created a CLAUDE.md file with project instructions
Day 2: Fixed authentication for my first MCP server (Firecrawl)
Day 3: Set up github (after almost losing everything)
Day 4: Created my first security assessment and found 19 vulnerabilities
Early Wins That Hooked Me
Crawled my entire website and updated my bio automagically
Set up 9 automated Gmail labels for 90+ newsletters via Google MCP
Built my first AI agents: Scraping Agent and SEO Agent v1
Got multi-model consensus working (GPT vs Gemini vs Claude arguing about my code)
First Major Disaster
I let Claude reorganize my project folder structure in Obsidian.
It worked... but I spent 3 hours fixing broken wiki-links.
Lesson learned: "Comprehensive" changes need checkpoints.
September-October: Building the Machine
This is when things got serious.
I went from 0 skills to 37 skills for me and team members.
Skills built:
Meetings (3-phase automation (raw to a standard format then add people and tasks, confidence scoring)
SEO Research (6-phase parallel audit process covering Google, Bing, Perplexity, ChatGPT, Claude, and Grok)
Firecrawl (web scraping workflows)
Perplexity (real-time research)
Jina (academic papers, parallel google search)
The Day It Passed 41 Tests
I built a comprehensive meeting processing system that automated task extraction, people bios, company details, and priorities.
The moment I watched pytest show 41/41 passing: "Okay, this is actually working."
Fun Discoveries
Built a skill for creating skills (very meta)
Discovered AI has strong opinions about folder naming (lowercase only, please)
Parallel execution of prompts and skills is a game-changer
November-December: The Agent Era
Here's my scaffolding
Aug was Prompts = detailed instructions
Oct Skills = repeatable procedures I invoke
Nov Agents = autonomous workers I deploy for a specific problem
Research was my number one use case so I started there and the rest just flowed.
33 agent roster by year-end (my top 10):
topic-ideator
design-review
competitor-analyzer
outline-builder
seo-orchestrator (the boss)
research-orchestrator (web research in parallel)
icp-builder
gmail-manager (email operations)
qa-checklist
documentation
These are not simple agents rather multi-LLM parallel processing machines doing hours of work at the same time. Some work in the background, some run in parallel, others only run as needed.
The Micro-RACI Governance System
After agents started doing...off-plan things, I built better governance:
Max 3 iterations before mandatory handoff
Evidence requirements (sources + confidence scores)
Never auto-publish (always get human approval)
Log everything in a very…very concise way
Consistent frontmatter templates over everything
So what? A recent quarterly research project involving over 270 companies took me two weeks in ChatGPT. I completed it in six hours over two days with Claude Code. My wife is very happy as even she (my chief AI sceptic) is seeing the progress.
NEW! Digital Marketing Boot Camp 2.0
The AI Execution Engine
Friday, February 13 | UNH Manchester
Your Marketing Plan Deserves Execution—Let AI Do the Heavy Lifting
In this one-day boot camp, participants will build real AI-powered marketing systems, including content engines, persona-driven email sequences, GEO (Generative Engine Optimization) tactics, and automation workflows, during the session. Instead of leaving with ideas, you’ll leave with working templates, prompts, and automations tailored to your audience and ready to deploy.
Led by Alec Newcomb and Marlana Trombley, this program helps marketing teams, agencies, and nonprofits execute their 2026 marketing plans faster and more efficiently.
The Numbers
Giphy
Productivity Wins
MCP Bloat: 85% token reduction (77K to 8.7K)
Meeting processing: 50 meetings a month → people → to tasks in minutes
Using multiple LLMs in parallel easily (Gemini, Claude, ChatGPT, Grok, Deepseek)
Money Saved/Made
Eliminated need for 5 separate SaaS tools ($600 a month is savings)
Competitive intelligence: Extracted 314+ Meta ads in one session
Outreach: Scored and prioritized 200+ prospects automatically in a day
What I Taught Claude Code
How "Alec" likes to work (we are partners)
Short, well-defined processes with gates like Micro-RACI are the way to go
Document and backup as you build (outdated docs are stop-the-line issues)
What Claude Taught Me
Doing it right > doing it fast. NEVER skip steps.
Tedious, systematic work is the way (I have workflows regularly run for 2-3 hours)
Single source of truth prevents chaos
Background processes need gates/kill switches
The Honest Moments
Claude is wrong (it happened enough I implemented Micro-RACI)
Claude hallucinates 10.9% of the time
The day I accidentally deleted 761 files and Github helped restore them
The day I made a mess of a Github merge. Took me two days to fix, Not pretty.
Agents using the wrong models (they love to use the older models like o3)
What's Next
Model-First Reasoning Rollout (reduce hallucinations)
6 agents queued for upgrades v2 and v3 (better handoffs and sharper workflows)
Explicit constraint modeling
State tracking built into workflows
More background Agents
Overnight Agents
2026 Philosophy
This year taught me that AI isn't about replacement, it's about collaboration. In parallel. At a scale that boggles my mind.
My best work happened when my core trio of AI’s (Claude, Gemini, ChatGPT) pushed back on bad ideas, when they fixed processes, and when the AIs argued about what to do.
The future isn't AI doing your job. It's AI arguing with you about the best way to do your job and actually listening.
Cheers,
Alec
P.S. This was a test. If you liked it, let me know if you want more of these by replying, with a hell yes.
P.P.S. If you read this and felt left out, confused, or late to the game, you are not alone watch this Video. We are all feeling it.
