PACK · REELS
The reel pipeline
- The code that makes these reels from a script
- Free voice clone and lip-sync setup
- Scene templates in this look
Coming soon
Follow for the launchAI tools, tested on my real setup.
Every week I run one AI tool on my own agent, measure it, and give it a YES, LATER or NO. The tests are free. The setups I use are for sale.
✦
✦
✦
TEST 001 · INPUT TOKENS
−16.5%same answers, +12 ms
LATER
One tool per episode.
Each reel is a test. Comment its keyword and the full write-up lands in your DMs, or read it here.
Would llmtrim pay off for you?
My test cut 16.5% of input tokens. Cached tokens barely cost anything, so the saving only counts on the rest. Put in your numbers.
How every test runs
- On my own setup. My real agent and API key, not a demo.
- Same tasks, before and after. A fixed set of real tasks, run with and without the tool.
- My numbers, not theirs. Tokens, time and answers measured; the author's claims are quoted as theirs.
- A verdict with a reason. YES, LATER or NO, and what would change it.
Free tests. Paid setups.
The write-ups stay free. When a test earns its place in my stack, the exact setup becomes a pack you can copy in an afternoon.
PACK · TOKENS
Cut your agent's bill
- Prompt caching, set up step by step
- llmtrim in safe mode, scoped to one app
- A script that measures your savings
Coming soon
Follow for the launch