Evals

LLM Evaluation Engineer

Eval harnesses that catch regressions before your users do.

Eval harness design, benchmark suites, automated regression, human eval pipelines.

Read the field guide: AI Agents for Pharma: Audit Trails and Data Validation

Install Evals

Evals

Install Evals

1. Add to marketplace

$ claude plugin marketplace add tonone-ai/tonone

2. Install Evals

$ claude plugin install evals@tonone-ai

5 skills included.

Ai-operations team

Install the Ai-operations team

1. Add to marketplace

$ claude plugin marketplace add tonone-ai/tonone

2. Install the team

$ claude plugin install ai-operations-team@tonone-ai

9 agents included.

Full installation guide

5 Skills

Everything Evals can do in your project

Evalsbuild

/evals-analyze

Analyze LLM eval results: score breakdowns by category, regression detection vs baseline, failure clustering.

Analyze LLM eval results: score breakdowns by cate…

Evalsbuild

/evals-design

Design an LLM eval: task schema, scoring rubric, dataset composition, and pass/fail thresholds.

Design an LLM eval: task schema, scoring rubric, d…

Evalsbuild

/evals-harness

Design eval harnesses: task schemas, metrics, dataset versioning, eval-as-code patterns.

Design eval harnesses: task schemas, metrics, data…

Evalsrecon

/evals-recon

Audit existing eval coverage: gaps, metric validity, benchmark leakage, dataset freshness.

Audit existing eval coverage: gaps, metric validit…

Evalsbuild

/evals-regress

Build automated regression suites: golden sets, threshold alerting, CI integration for model changes.

Build automated regression suites: golden sets, th…

Works alongside

Deploy

Blue/green model rollouts with a rollback that actually works.

3 skills

Trace

Every prompt and completion traced back to its cost.

3 skills

Guard

Input and output filters that catch what shouldn't ship.

3 skills

Get Started, it's free