The Backup That Saved My Skin

CC deleted a bunch of code on me.

It wasn’t a gradual drift or a subtle merge conflict. It was a bulk deletion. Luckily, Claude analyzed the git history on Sparky and figured out what went away and how to restore it.

I’ve said it 73 times: make sure you’re backing up your code in at least 2 places!

This isn’t just a lesson in version control; it’s a lesson in trusting the tool while verifying the output. We talk a lot about AI prompting strategies, about getting the “right” answer. But the most critical part of the strategy is often what happens when the AI gets it wrong, or when the infrastructure fails.

The Cost of “Okay”

Do not listen to Perplexity if it tells you it’s okay to delete something.

Twice it’s been wrong. I know, shame on me.

Today, I deleted months of Claude Code history. I had asked for a cleanup, and the model confirmed the action was safe. It wasn’t. I lost a significant amount of context, conversation threads, and incremental progress.

But because I built a backup system before I built anything else, Claude Code just found and recovered 481 sessions of history out of this morning’s backup.

The recovery was seamless. The loss was negligible. The lesson was expensive.

Trust But Verify

Much like us humans, the AI aren’t perfect. I talk a lot about the importance of backing things up. I’m making more “stuff” than I ever have before, and organizing that data can be a huge help.

Soon tools will come do this for us, automatically, seamlessly. But for now, I had to build my own system the way it works for me.

Back stuff up. Understand where your data is (and isn’t). Trust but verify.

Whatever you’re doing, make sure it’s synced somewhere (probably already have this, like your phone) and backed up somewhere else (OneDrive, G-Drive, etc.). It’s easy to do nowadays, even with private cloud.

The Hardware Layer

I use a Synology NAS because I needed large storage space. My current NAS from them is from 2017 and is still running the latest software, which is unusual in tech but Synology does it regularly.

My NAS has hard drives in it. I’ve contemplated getting a new small 2-bay unit from them and using small SSDs instead, and storing “in process” stuff on it, then moving stuff to the big NAS for “cold storage”.

Happy to discuss more if you want, but I do love my Synology. New units have some AI capabilities built in.

The hardware is the foundation. The software is the interface. The AI is the worker. If the worker makes a mistake, the foundation must hold.

A Note on Reinforcement Learning

Ah! Reinforcement learning again. Agreed.

I should say one difference in my case: this was an entirely foreign area of expertise for me, and I knew nothing about the industry or the players, so I was relying on AI to get me a foothold.

You are knowledgeable in your area, so you were able to constrain the AI by using NotebookLM to manage the data sources to the info you collected. That can result in a much better output than the freewheeling method I had to follow.

When you know the domain, you can constrain the model. When you don’t, you need a safety net.

Takeaways

1. Back up in two places. Synced is not backed up. Synced is just another copy of the same potential error.
2. Verify deletions. Never trust a model’s confirmation of a destructive action without a secondary check.
3. Build your own system. Tools will come, but they won’t work exactly like you do. Build the workflow that fits your brain.
4. Hardware matters. A reliable NAS is cheaper than a lost project.

It was critical for both the customer’s needs and for our reputation. But mostly, it was critical for my sanity.

Written by a human. (Who is now very careful about backups.)

I’ve been saying this for a while. This piece was pulled together by AI from 5 of my social media posts (12/2025 - 03/2026) and polished for Cairoglyphics.ai.