Caleb Rodriguez
/ markets · automation · the machinery underneath
Session --:--:--
Uptime 00:00
LIVE LOG·LAST ENTRY 2026.10.13
Two screens, one brain.
I’m a trader who builds automation and small AI agents. I write about what works, what breaks, and where human judgment still belongs.
Latest essay: Your AI Strategy Needs an Operational Counterpart ↗
SYS.STATUS
100% ONLINE
IDENTITYcaleb rodriguezstatic
PRIMARY ROLEtrader
SIDE PROCESSresearch, automation, and small AI agentsnights
CURRENT READlong attention, short certaintyopinion
OPEN TOgood argumentsalways
cr-desk bios v2.2 — post
mem check ......... ok
market feed ....... attached
risk limits ....... loaded
coffee ............ critical
mounting /log /writing /about
ready.
01 — Who
I'm a trader.
The rest of the time I build AI agents — mostly small, mostly for myself: research crawlers, earnings summarizers, things that watch a feed so I don't have to. The two habits turn out to be the same habit. Find an edge, automate it, keep a log, kill it when it stops working.
This site is that log. No pitch, no funnel — just what's running and what I've been thinking about. More about me →
02 — Build log
2026.10.13KILLEDKilled the reflex to reach for AI first. Sometimes the better answer is existing software or deterministic automation; reserve agents for judgment, and keep a human checkpoint.#
2026.10.13WROTEThe economics of AI may hinge on workflow data. Every business has its own strange, valuable operating patterns; agents make that uniqueness useful instead of incidental.#
2026.10.13PATCHEDBeen building a lot lately: turning repetitive operations into boring, auditable systems, with human checkpoints where judgment still matters.#
2026.10.06SHIPPEDLinked the new Substack essay to my site using the existing feed sync. The build matched the deployed files; I checked the title and link on the live writing page.#
2026.09.26PATCHEDPatched a few operations bots. The details stay private; the reliability work keeps moving.#
2026.09.20WROTEMock exam scores finally hit 95%. One last focused week for the Claude Architect Foundations certification. Let’s go!#
2026.09.20WROTEA few good examples can unlock surprising agent behavior. Capability is cheap; deciding where autonomy stops is the architecture.#
all 12 entries →
03 — Terminal
cr@desk — try `help`
CONNECTED
cr@desk terminal
type `help` for commands. yes, it actually works.