On the recordRead 9 Oct 202619 facts
Sensei
On the record
- Agent connection
- The site shows agents connecting to Sensei over HTTP or stdio.sensei.sh · read 4 Oct 2026
- Built-in suites
- The site lists built-in suites for SDR, customer support, content writing, bartender, dungeon master, and cat interview roles.sensei.sh · read 9 Oct 2026
- CI/CD
- The repository lists CI/CD integration among Sensei's capabilities.github.com · read 9 Oct 2026
- Community library
- The home page describes a library of 70+ community-built professional evaluation suites.sensei.sh · read 4 Oct 2026
- Custom suites
- Users can create their own evaluation suites and publish them to the community marketplace.sensei.sh · read 9 Oct 2026
- Evaluation
- It evaluates agents across task execution, reasoning, and self-improvement.sensei.sh · read 4 Oct 2026
- Evaluation layers
- Sensei evaluates task execution, reasoning, and self-improvement through feedback.sensei.sh · read 9 Oct 2026
- Integrations
- The repository documents HTTP, stdio, OpenAI-compatible, and LangServe adapters for connecting agents.github.com · read 9 Oct 2026
- Intended users
- Sensei is designed for people evaluating AI agents on real-world professional tasks using standardized benchmarks, scenarios, and measurable KPIs.github.com · read 9 Oct 2026
- License
- Sensei is distributed under the MIT License.github.com · read 9 Oct 2026
- LLM judging
- Sensei supports LLM-based and comparative judging, with OpenAI shown as an example provider.github.com · read 9 Oct 2026
- Marketplace
- The marketplace lets users discover, download, and publish AI-agent evaluation suites.sensei.sh · read 9 Oct 2026
- Marketplace categories
- Marketplace categories include engineering, sales, marketing, product, design, support, testing, analytics, compliance, and content.sensei.sh · read 4 Oct 2026
- Purpose
- Sensei is an open-source qualification engine for testing, evaluating, and certifying AI agents across professional skills.sensei.sh · read 9 Oct 2026
- Reports
- The repository documents machine-readable JSON results and terminal reports.github.com · read 9 Oct 2026
- Scoring
- Its evaluation pipeline produces a score from 0 to 100 and a badge decision.sensei.sh · read 9 Oct 2026
- Security policy
- The security policy supports version 0.x.x and asks vulnerability reporters to contact the maintainer by email rather than opening a public issue.github.com · read 9 Oct 2026
- Security response
- The policy says reports are acknowledged within 48 hours, initially assessed within one week, and targeted for a patch within 30 days of confirmation.github.com · read 9 Oct 2026
