Latest AI and tech news

braintrustdata.com • Sep 3 • by Braintrust

Cloud · AI agents +4

+ = Sign in to like, bookmark, or love articles.

BCE55

Trace and improve Cloudflare Agents

braintrustdata.com • Aug 13 • by Braintrust

AI agents · behavior +5

+ = Sign in to like, bookmark, or love articles.

31105

Behavior specs, an open standard for supervising long-horizon agents

braintrustdata.com • Jul 20 • by Braintrust

Web development · AI research +7

+ = Sign in to like, bookmark, or love articles.

695E3

Paper MCP vs Figma MCP for frontend agents

braintrustdata.com • Jul 15 • by Braintrust

AI infrastructure · chose +4

+ = Sign in to like, bookmark, or love articles.

6554A

How we chose the model behind Topics with Baseten

braintrustdata.com • Jul 10 • by Braintrust

LLMs · evaluating +2

+ = Sign in to like, bookmark, or love articles.

5066F

Evaluating the GPT-5.6 family

braintrustdata.com • Jul 9 • by Braintrust

Voice AI · evaluating +2

+ = Sign in to like, bookmark, or love articles.

C0719

Evaluating speech-to-text models

braintrustdata.com • Jul 7 • by Braintrust

Software engineering · filter +6

+ = Sign in to like, bookmark, or love articles.

1FD6D

Faster phrase search with shingled bloom filters in Brainstore

braintrustdata.com • Jul 2 • by Braintrust

AI research · AI agents +8

+ = Sign in to like, bookmark, or love articles.

203D1

From World Cup matchups to research maps: evaluating Parallel's web research agents

braintrustdata.com • Jun 30 • by Braintrust

DevOps & SRE · Startups +4

+ = Sign in to like, bookmark, or love articles.

DEBA5

Agent observability for startups

braintrustdata.com • Jun 30 • by Braintrust

RAG · AI research +6

+ = Sign in to like, bookmark, or love articles.

AB097

Benchmarking GLM-5.2 vs Opus 4.8 for real-world long-context retrieval

braintrustdata.com • Jun 30 • by Braintrust

Inference · Cost of AI +8

+ = Sign in to like, bookmark, or love articles.

5C961

Using OSS models to save on inference costs without cutting quality

braintrustdata.com • Jun 26 • by Braintrust

AI agents · Evals +3

+ = Sign in to like, bookmark, or love articles.

7C2D0

How to eval stateful agents

braintrustdata.com • Jun 24 • by Braintrust

AI agents · MLOps +9

+ = Sign in to like, bookmark, or love articles.

816BB

Using Braintrust to eval agentic setups from large-scale Hugging Face data

braintrustdata.com • Jun 17 • by Braintrust

Cost of AI · MLOps +5

+ = Sign in to like, bookmark, or love articles.

79808

How to test agent cost-efficiency with Braintrust

braintrustdata.com • Jun 16 • by Braintrust

MLOps · framework +2

+ = Sign in to like, bookmark, or love articles.

0FC88

How to use Braintrust with any framework or provider

braintrustdata.com • Jun 4 • by Braintrust

scale · possible +3

+ = Sign in to like, bookmark, or love articles.

06952

How we made continuous trace intelligence possible at scale

braintrustdata.com • Jun 1 • by Braintrust

DevOps & SRE · AI +3

+ = Sign in to like, bookmark, or love articles.

69BA0

AI observability is active observability

braintrustdata.com • Jun 1 • by Braintrust

Automation · available +5

+ = Sign in to like, bookmark, or love articles.

D7F24

Automate pattern discovery with Topics, now generally available

braintrustdata.com • May 21 • by Braintrust

Evals · Data governance +4

+ = Sign in to like, bookmark, or love articles.

0AA65

How to improve your golden datasets with human review

braintrustdata.com • May 21 • by Braintrust

AI agents · AI +7

+ = Sign in to like, bookmark, or love articles.

A7D20

The six generations of AI agents and how to eval them

braintrustdata.com • May 14 • by Braintrust

Evals · evaluate +2

+ = Sign in to like, bookmark, or love articles.

AF001

How to evaluate multi-turn conversations

braintrustdata.com • May 11 • by Braintrust

Evals · eval +2

+ = Sign in to like, bookmark, or love articles.

E9834

Why your traces and evals belong in the same place

braintrustdata.com • Apr 28 • by Braintrust

DevOps & SRE · Evals +5

+ = Sign in to like, bookmark, or love articles.

3888B

How to earn stakeholder trust with evals and observability

braintrustdata.com • Apr 13 • by Braintrust

AI policy · AI +4

+ = Sign in to like, bookmark, or love articles.

5E701

How to prepare for AI compliance and governance

braintrustdata.com • Apr 8 • by Braintrust

Languages · MLOps +7

+ = Sign in to like, bookmark, or love articles.

7BD27

Agentic eval development with the Braintrust CLI

braintrustdata.com • Apr 6 • by Braintrust

DevOps & SRE · AI +6

+ = Sign in to like, bookmark, or love articles.

35EB8

How Brainstore works: architecture for AI observability at scale

braintrustdata.com • Apr 3 • by Braintrust

Languages · MLOps +4

+ = Sign in to like, bookmark, or love articles.

E3FCE

Braintrust CLI and MCP

braintrustdata.com • Mar 27 • by Braintrust

Evals · eval +1

+ = Sign in to like, bookmark, or love articles.

1E2A6

Evals are the new PRD

braintrustdata.com • Mar 19 • by Braintrust

DevOps & SRE · AI +2

+ = Sign in to like, bookmark, or love articles.

CEADD

What is AI observability?

braintrustdata.com • Mar 17 • by Braintrust

AI · Evals +5

+ = Sign in to like, bookmark, or love articles.

AC919

Evals for PMs: A practical guide to AI product quality

braintrustdata.com • Mar 12 • by Braintrust

Privacy · supporting +2

+ = Sign in to like, bookmark, or love articles.

B9BA0

Supporting privacy and compliance for EU teams

braintrustdata.com • Mar 10 • by Braintrust

Evals · eval +1

+ = Sign in to like, bookmark, or love articles.

9D785

How to build your first offline eval

braintrustdata.com • Feb 25 • by Braintrust

DevOps & SRE · automatically +5

+ = Sign in to like, bookmark, or love articles.

BA493

Automatically discover what matters in your production traces with Topics

braintrustdata.com • Feb 25 • by Braintrust

DevOps & SRE · optimize +2

+ = Sign in to like, bookmark, or love articles.

B8CB8

Trace keynote recap: See it, improve it, optimize it

braintrustdata.com • Feb 17 • by Braintrust

Startups · MLOps +6

+ = Sign in to like, bookmark, or love articles.

063BB

Braintrust's series B: building the infrastructure for production AI

braintrustdata.com • Feb 12 • by Braintrust

AI · performance +2

+ = Sign in to like, bookmark, or love articles.

EB73A

The 5 pillars of AI model performance

braintrustdata.com • Jan 22 • by Braintrust

Languages · Software engineering +2

+ = Sign in to like, bookmark, or love articles.

C7930

Testing if "bash is all you need"

braintrustdata.com • Jan 21 • by Braintrust

Cybersecurity · MLOps +7

+ = Sign in to like, bookmark, or love articles.

248CB

Security is a choice: how Braintrust lets you decide where your AI data lives

braintrustdata.com • Jan 20 • by Braintrust

AI · AI agents +4

+ = Sign in to like, bookmark, or love articles.

D926C

Building observable AI agents with Temporal

braintrustdata.com • Jan 13 • by Braintrust

MLOps · Software engineering +5

+ = Sign in to like, bookmark, or love articles.

AE946

Debugging Ralph Wiggum with Braintrust Logs

braintrustdata.com • Dec 23 • by Braintrust

AI coding tools · MLOps +5

+ = Sign in to like, bookmark, or love articles.

E81E2

Claude Code meets Braintrust

braintrustdata.com • Dec 22 • by Braintrust

Languages · DevOps & SRE +6

+ = Sign in to like, bookmark, or love articles.

C5FDB

AI observability beyond Python and TypeScript