| Our approach to hybrid deployment |
Ornella Altunyan |
Jan 08, 2025 |
586 |
- |
| Evaluating agents |
Ornella Altunyan |
Jan 22, 2025 |
2161 |
1 |
| How Loom auto-generates video titles |
Ornella Altunyan, Matt Granmoe |
Jan 27, 2025 |
1040 |
- |
| How Fintool generates millions of financial insights |
Ornella Altunyan, Nicolas Bustamante |
Jan 31, 2025 |
738 |
- |
| Bedrock, Vertex AI, and universal structured outputs support |
Ornella Altunyan |
Feb 11, 2025 |
385 |
- |
| Brainstore: the purpose-built database for the AI engineering era |
Ankur Goyal |
Mar 03, 2025 |
1692 |
5 |
| Brainstore is now the default |
Ankur Goyal |
Mar 31, 2025 |
616 |
- |
| Resilient observability by design |
Ornella Altunyan, Sachin Padmanabhan |
Apr 03, 2025 |
767 |
- |
| Webinar recap: Eval best practices |
Ornella Altunyan |
Apr 22, 2025 |
582 |
- |
| How Coursera builds next-generation learning tools |
Ornella Altunyan, Winnie Tam, Sophie Gao |
May 12, 2025 |
1110 |
- |
| Eval playgrounds for faster, focused iteration |
Ornella Altunyan |
May 27, 2025 |
450 |
- |
| Experiments UI: Now 10x faster |
Tara Nagar, Ornella Altunyan |
Jun 03, 2025 |
1259 |
- |
| GPT-5 vs. Claude Opus 4.1 |
Ornella Altunyan, Wayde Gilliam, Sarah Zeng |
Aug 08, 2025 |
689 |
- |
| Braintrust is not an eval framework |
Ankur Goyal |
Jul 14, 2025 |
1276 |
- |
| The canonical agent architecture: A while loop with tools |
Ankur Goyal |
Aug 07, 2025 |
891 |
- |
| Building with Grok |
Wayde Gilliam |
Jul 11, 2025 |
681 |
- |
| Five hard-learned lessons about AI evals |
Ankur Goyal |
Jul 17, 2025 |
903 |
- |
| How Graphite builds reliable AI code review at scale |
Ornella Altunyan |
Aug 25, 2025 |
1161 |
- |
| The rise of async programming |
Ankur Goyal |
Aug 19, 2025 |
846 |
- |
| Systematic prompt engineering: From trial and error to data-driven optimization |
Braintrust Team |
Aug 21, 2025 |
1444 |
- |
| A/B testing can't keep up with AI |
Mengying Li, Ankur Goyal |
Sep 03, 2025 |
732 |
- |
| AI observability: Why traditional monitoring falls short |
Braintrust Team |
Aug 21, 2025 |
1209 |
- |
| Testing different models with different prompts: A hands-on guide with Braintrust |
Braintrust Team |
Aug 21, 2025 |
592 |
- |
| Testing different models with different prompts: A systematic approach to AI development |
Braintrust Team |
Aug 21, 2025 |
1381 |
- |
| The infrastructure behind AI development: Why testing and observability matter |
Sarah Zeng |
Aug 21, 2025 |
1015 |
- |
| The 4 best LLM evaluation platforms in 2025: Why Braintrust sets the gold standard |
Braintrust Team |
Aug 21, 2025 |
2720 |
- |
| Integrating AI into production applications: Beyond the demo phase |
Braintrust Team |
Aug 21, 2025 |
1695 |
- |
| AI that knows your data |
Ornella Altunyan |
Sep 13, 2025 |
447 |
- |