AI with Moosh
Practical AI, without the noise.
Make better decisions about agents, models, and automation. Start with a real workflow, define a useful result, and learn how to check it.
Field guides
Firsthand experience. Measured results. Primary sources.
- Read guide
Workflow performance
Less memory pressure. Measured Rust vs. Python results.
How I reduced AI agent memory pressure with Typst, Rust, and streaming CSV workflows. Compare measured runtime and peak memory in a million-row benchmark.
- Read guide
Agent reliability
Your AI agent said “done.” Prove it.
Define agent completion with independent evidence, a worked intake example, and a reusable scorecard for outcomes, destinations, and side effects.
- Read guide
Model routing
Model routing: the cost of a finished task.
Compare model routes by cost per accepted task, including retries, fallbacks, tools, and human review. Includes hypothetical arithmetic and a routing worksheet.
- Read guide
Decision models
Decision models vs. LLMs.
Choose rules, a bounded decision model, a general LLM, or human review for each workflow step. Includes an illustrative triage example and a selection worksheet.
Put it to work
Have a workflow in mind?
Bring one recurring task. Define the outcome, the review boundary, and the smallest useful next step.