Skip to content
Back to the index

Evals Coach

evalscoach.comAgent evaluation & testing

PulseGate's liveness check found it on 8 Oct 2026; it is registered on GitHub and has been in the index since 7 Sep 2026. How this is checked

Evals Coach is a Claude plugin that helps AI product managers turn feature descriptions or real outputs into runnable evaluations. It guides users through criteria, test cases, graders, judge prompts, and release gates, producing outputs that can be used with existing evaluation stacks.

Inferred · not functionally tested

WebCLICloud-managed
Evals Coach preview
Visit evalscoach.com
2stars
8features
2026since

Overview

6 features

Purpose: Designing reliable AI evaluations without needing specialized eval engineering expertise.

Inferred · not functionally tested

Audience: AI product managers

Inferred · not functionally tested

Functions: analytics

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: unknown

Recorded constraints: pricing: unknown · license: Proprietary · platforms: CLI, WEB · deployment: browser, cli, cloud_managed

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: evalscoach.com · github.com. These links do not verify the individual claims.

In the Agent evaluation & testing space, Evals Coach takes a focused approach. Inferred · not functionally tested: It focuses on designing reliable AI evaluations without needing specialized eval engineering expertise. Inferred · not functionally tested: It is built as a B2B product for AI product managers. Basis unknown · not verified: It runs on the web and the command line.

Evals Coach first shipped in 2026. The project is developed in the open on GitHub with 82 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are feature description intake, evaluation questions, and test case design.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Feature description intake
  • Evaluation questions
  • Test case design
  • Failure mode tracking
  • Grader design
  • Judge prompts

Topics: Inferred · not functionally tested

Tags
llm-evaluationeval-designrelease-gatesai-product-management
AI capabilities
Text
Inference: Cloud API

JSON profile · Text profile · Access guide

Built with & integrations

Hosting
Vercel
AI providers
anthropicopenai
Written with
Claude Code
Runs on
BrowserCLICloud-managed
Written with — evidence
Claude Code
commit 7448a92304a6 · since Sep 2026
Detected from
openai
bgpt- in the HTML
Vercel
x-vercel-id header · x-vercel-cache header

Trust & compliance

Public signals
HTTPSGitHub · ★ 2Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed7 Sep · 20:14 UTC
    Show HN: Evals Coach – a Claude plugin to help PMs write good evals seen via Hacker News firehose (Algolia)
    Source: Hacker News firehose (Algolia) · Open

Frequently asked questions about Evals Coach

What is Evals Coach?
Inferred · not functionally tested: Evals Coach focuses on designing reliable AI evaluations without needing specialized eval engineering expertise. It is catalogued under Agent evaluation & testing on PulseGate.
Who should use Evals Coach?
Inferred · not functionally tested: Evals Coach is a B2B product built for AI product managers.
What platforms does Evals Coach run on?
Basis unknown · not verified: Evals Coach runs on the web and the command line.
Is Evals Coach still maintained?
PulseGate's liveness check found it on 8 Oct 2026. Its GitHub repository shows 82 commits in the last 90 days.
When did Evals Coach launch?
Evals Coach first shipped in 2026.
Is Evals Coach open source?
Basis unknown · not verified: Evals Coach has a public GitHub repository.

Similar projects

Closest matches by what these projects do