Relari (YC W24)Relari on YC W24 tootega avaldatud testimine, sisaldusväljendamine ja syntheettikava AI agentide stabilne ja testimisel arendamine.

4.3 (6)

Vaadanud Daniel Nikulshyn·Uuendatud juuli 2026

Ülevaade

Relari on arendaja platvorm, mis keskendub tehisintellekti agentide töökindluse parandamisele süstemaatilise testimise ja hindamise kaudu. See aitab meeskondadel genereerida sünteetilisi andmekogumeid, käivitada automatiseeritud hinnanguid ja võrrelda agentide jõudlust realistlikes stsenaariumides enne tootmisse saatmist. Y Combinatori (W24) toetusel sihib Relari insenerimeeskondi, kes ehitavad keerulisi LLM-rakendusi ja mitmeastmelisi agente, kus traditsiooniline kvaliteedi tagamine (QA) ei ole piisav. Selle tööriistad eesmärk on tuua tarkvaraarenduse rangus – üksiktestid, regressioonikontroll ja mõõdetavad mõõdikud – mittedeterministlikele AI-süsteemidele. Platvorm toetab kohandatud hindajaid, stsenaariumide simulatsiooni ja pidevat jälgimist, muutes selle kasulikuks nii eelneva käivitamise valideerimise kui ka tootmisagentide pideva kvaliteedi tagamise jaoks.

Põhifunktsioonid

Sisaldusväljendamine andmebaasiga
Automated and scalable synthetic dataset generation
User and scenario simulation
Custom evaluators and metrics
Continuous monitoring with real-time feedback
Debug and troubleshoot AI agents
Integrate AI toolchain with CI/CD pipelines
Experimental support for multi-party conversations
Production-grade testing and deployment infrastructure

Hinnad

Mudel: Free
Kategooria: Süsteemi vaadeldavus
Hinnang: 4.3 / 5 (6)

Kasutusjuhud

Autonomous and Expert Expert Agent testing

Testing the consistency, robustness, and quality in agent testing.

Plussid ja miinused

Plussid

Purposely developed for AI agent development
Unleashes automated test automation
Rich testing experience for AI agents
Efficient evaluation across multi-agent conversations
Fast integration with other development tools
CI/CD pipeline integration capability
AI assistant testing and quality assurance
Hands-on assessment and performance analysis with real data
Seamless and reliable testing and deployment solution

Miinused

Suitable for technical teams
Continual advancement and customer requests influence roadmap
Tools need initial setup
Custom metrics are necessary
Complex API integration might be necessary for teams with different tech stacks
Compatibility issues with some AI projects
Lack of GUI for user-friendly testing
Increased setup time compared to other tools
Non-simultaneous multilingual conversations still experimental

Lahingute rekord

3 lahingus Panteonis.

Last 3 battles

Arvustused

4.3

Keskmine 6 hinnangust.

Logi sisse arvustuse jätmiseks.

Fatima Zahra

Apr 4, 2026

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on customizable evaluation metrics, and purpose-built for evaluating multi-step AI agents caught me off guard. still, I'd recommend giving it a real trial.

Robert Ainsworth

Mar 17, 2026

Solid for our team

We rolled this out across the team last quarter and supports custom metrics and evaluators. Customizable evaluation metrics fits neatly into how we already work, and customizable evaluation metrics removed a step we used to do by hand. Primarily aimed at technical teams, not non-developers, which is the main caveat, but it has held up under daily use.

Devin Walker

Feb 6, 2026

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on performance benchmarking and reporting, and supports custom metrics and evaluators caught me off guard. Primarily aimed at technical teams, not non-developers is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Carlos Mendoza

Jul 20, 2025

Compared a few options

Evaluated this against two competitors. Where it wins: scenario and conversation simulation and purpose-built for evaluating multi-step AI agents. Where it lags: may require integration work to fit existing stacks. On balance the feature set — especially scenario and conversation simulation — justifies the 5 stars for our use case.

Yuki Mori

Jul 19, 2025

Use it every day

Honestly didn't expect to like it this much. Performance benchmarking and reporting is exactly what I needed, and purpose-built for evaluating multi-step AI agents. I do wish may require integration work to fit existing stacks, but I reach for it almost every day now and it just clicks.

Leila Hassan

Jul 14, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on regression testing for LLM apps, and supports custom metrics and evaluators caught me off guard. May require integration work to fit existing stacks is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Küsimused

What are the pros of using Relari?

Relari is purpose-built for evaluating multi-step AI agents, generates synthetic test data at scale, and supports custom metrics and evaluators, with active development backed by Y Combinator.

Asked by Anya Sokolova · Jun 27, 2026

Is Relari suitable for non-technical teams?

Relari is primarily aimed at technical teams, not non-developers, and may require integration work to fit existing stacks.

Asked by Hasan Demir · May 27, 2026

What features does Relari support?

Relari supports features like synthetic dataset generation, automated agent evaluation pipelines, scenario simulation, and customizable evaluation metrics.

Asked by Marisol Pena · Apr 17, 2026

What is Relari used for?

Relari is a platform for testing, evaluation, and synthetic data generation for AI agents, helping teams improve their reliability through systematic testing and evaluation.

Asked by Hana Kobayashi · Mar 25, 2026