Tuned Tensor
DocsDashboard

Agent Skill

Tuned Tensor exposes an agent-readable skill.md file so coding agents can discover the CLI workflow directly.

Fetch the canonical skill file from /skill.md.

Quickstart for agents

The skill tells agents to prefer the open-source tt CLI for creating behaviour specs, starting runs, watching progress, checking live diagnostics, checking billing, downloading models, and serving completed artifacts locally with the behaviour spec prompt applied.

curl https://tunedtensor.com/skill.md
npm install -g @tuned-tensor/cli
tt auth login tt_your_api_key
tt init --name "Customer Support Bot" --model Qwen/Qwen3.5-2B
tt eval
tt push
tt runs start <spec-id>
tt runs diagnose <run-id>
tt runs watch <run-id>
tt models setup-runtime
tt models serve <model-id> --spec tunedtensor.json

Why this exists

Tuned Tensor is designed around a command-line workflow. An agent can manage the same source-controlled tunedtensor.json spec a developer would edit by hand, then use the CLI to sync, train, evaluate, and iterate.

See also