| Author here. I wrote up the background and motivation in more detail here: https://medium.com/@davidfowl/tally-52f4b257b32a The short version: Tally is not doing LLM-based classification at runtime. It’s a local, deterministic rule engine. Rules live in files, run offline, and are fully inspectable and hopefully explainable. LLMs are optional and only used to help author and refine rules, because the hard part isn’t applying regex — it’s maintaining and evolving rule sets as new messy merchant strings show up. Once rules exist, there are zero model calls. This grew out of me initially using coding agents to generate one-off scripts for my own CSVs. That worked, but all the logic lived in prompts. The pivot was realizing the rules are the real artifact worth keeping and sharing. If you want to hand-write rules, run offline, or use local models, that all works. Docs with the concrete workflow are here: https://tallyai.money/guide.html Happy to answer concrete questions. |