Blog

Identifying & auto-correcting agent failures: findings from τ-bench

Identifying & auto-correcting agent failures: findings from τ-bench

Nina
April 29, 2025
Introducing the Atla MCP Server: purpose-built LLM Judges now at your command

Introducing the Atla MCP Server: purpose-built LLM Judges now at your command

Atla team
April 22, 2025

Latest posts

Identifying & auto-correcting agent failures: findings from τ-bench

Identifying & auto-correcting agent failures: findings from τ-bench

Nina
April 29, 2025
Introducing the Atla MCP Server: purpose-built LLM Judges now at your command

Introducing the Atla MCP Server: purpose-built LLM Judges now at your command

Atla team
April 22, 2025
Selene Mini: SOTA 8B LLM Judge, now available via API

Selene Mini: SOTA 8B LLM Judge, now available via API

Atla team
April 15, 2025
Announcing Atla’s native integration with Langfuse

Announcing Atla’s native integration with Langfuse

Atla team
March 25, 2025
Best practices for evaluating AI across multiple criteria

Best practices for evaluating AI across multiple criteria

Sashank
March 20, 2025
Build custom eval metrics with the Eval Copilot (formerly Alignment Platform)

Build custom eval metrics with the Eval Copilot (formerly Alignment Platform)

Atla team
March 5, 2025
Frontier AI needs frontier evaluators. Meet Selene.

Frontier AI needs frontier evaluators. Meet Selene.

Atla team
February 26, 2025
How to use Selene Mini locally in LM Studio

How to use Selene Mini locally in LM Studio

Kyle
February 25, 2025
From reward to reason - the role of LLM judges in training models like DeepSeek-R1

From reward to reason - the role of LLM judges in training models like DeepSeek-R1

Sashank
February 11, 2025