| LLMs in Prod Comes to Bangalore |
Vrushank Vyas |
Jul 29, 2024 |
1045 |
- |
| AI audit checklist for internal AI platforms & enablement teams |
Drishti Shah |
Dec 10, 2025 |
2089 |
- |
| May: Major Updates |
Vrushank Vyas |
May 31, 2024 |
355 |
- |
| HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace - Summary |
The Quill |
Apr 20, 2023 |
197 |
- |
| Agent observability: measuring tools, plans, and outcomes |
Drishti Shah |
Nov 28, 2025 |
1619 |
- |
| My Journey with AI-Driven Development: From Curiosity to Necessity |
Ayush |
Aug 18, 2023 |
602 |
- |
| We're Afraid Language Models Aren't Modeling Ambiguity - Summary |
The Quill |
May 07, 2023 |
225 |
- |
| Language Models are Few-Shot Learners - Summary |
Rohit Agarwal |
Apr 15, 2023 |
230 |
- |
| What It Means To Go To Prod |
Rohit Agarwal |
Apr 13, 2024 |
312 |
- |
| Instruction Tuning with GPT-4 - Summary |
The Quill |
Apr 16, 2023 |
241 |
- |
| CAMEL: Communicative Agents for "Mind" Exploration of LLMs - Summary |
Rohit Agarwal |
Apr 14, 2023 |
352 |
- |
| LLMs in Prod: The Reality of AI Outages, No LLM is Immune |
Siddharth Sambharia |
Dec 14, 2024 |
504 |
- |
| Gemini 3.0 vs GPT-5.1: a clear comparison for builders |
Drishti Shah |
Nov 19, 2025 |
921 |
- |
| Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes - Summary |
The Quill |
May 07, 2023 |
237 |
- |
| Towards Reasoning in Large Language Models: A Survey - Summary |
The Quill |
Jun 09, 2023 |
248 |
- |
| A Survey of Large Language Models - Summary |
The Quill |
Apr 16, 2023 |
274 |
- |
| Training language models to follow instructions with human feedback - Summary |
Rohit Agarwal |
Apr 15, 2023 |
249 |
- |
| Attention Is All You Need - Summary |
Rohit Agarwal |
Apr 14, 2023 |
248 |
- |
| Expressive Text-to-Image Generation with Rich Text - Summary |
Rohit Agarwal |
Apr 15, 2023 |
264 |
- |
| The Confidence Checklist for LLMs in Production |
Vrushank Vyas |
Jul 01, 2023 |
51 |
- |
| Eight Things to Know about Large Language Models - Summary |
The Quill |
Apr 16, 2023 |
132 |
- |
| LLMs In Prod: Day 1 |
Siddharth Sambharia |
Dec 13, 2024 |
505 |
- |
| Fortifying Your AI Stack: Palo Alto Networks Prisma AIRS Now on Portkey |
Jason Roberts |
Aug 13, 2025 |
547 |
- |
| AI tool sprawl: causes, risks, and how teams can regain control |
Drishti Shah |
Nov 20, 2025 |
1327 |
- |
| June at Portkey: Agents, AI Governance, and Twenty Six Cookbooks |
Vrushank Vyas |
Jul 08, 2024 |
405 |
- |
| LLM access control in multi-provider environments |
Drishti Shah |
Dec 03, 2025 |
1531 |
- |
| Portkey in September |
Vrushank Vyas |
Oct 05, 2024 |
922 |
- |
| GPT-4 is Getting Faster 🐇 |
Vrushank Vyas |
Oct 16, 2023 |
257 |
- |
| How Snorkel evaluates and trains top AI models |
Shae Selix |
Nov 04, 2025 |
2388 |
- |
| LoRA: Low-Rank Adaptation of Large Language Models - Summary |
Rohit Agarwal |
Apr 15, 2023 |
271 |
- |
| Open WebUI vs LibreChat: Choose the Right ChatGPT UI for Your Organization |
Vrushank Vyas |
Feb 19, 2025 |
1154 |
- |
| Elevate Your ToolJet Experience with Portkey AI |
Kavya MD |
Oct 29, 2024 |
853 |
- |
| OpenAI DevDay's Implications for LLM Apps in Prod |
Rohit Agarwal |
Nov 07, 2023 |
1041 |
- |
| Are We Really Making Much Progress in Text Classification? A Comparative Review - Summary |
The Quill |
Jun 09, 2023 |
239 |
- |
| Building Production-Ready RAG Apps |
Team Hasura |
Oct 18, 2023 |
1143 |
- |
| Launching Prompt Engineering Studio |
Vrushank Vyas |
Mar 17, 2025 |
840 |
- |
| How does an AI gateway improve building AI apps |
Drishti Shah |
Dec 16, 2025 |
1527 |
- |
| Portkey Named a Cool Vendor in the 2025 Gartner® Cool Vendors™ in LLM Observability Report |
Drishti Shah |
Oct 29, 2025 |
1051 |
- |
| April Cool: 154 PR Merges |
Rohit Agarwal |
Apr 30, 2024 |
410 |
- |
| Portkey is Joining Hacktoberfest |
Ashirwad Karande |
Oct 09, 2024 |
339 |
- |
| Prompt Injection Attacks in LLMs: What Are They and How to Prevent Them |
Sabrina Shoshani |
Dec 10, 2024 |
3011 |
- |
| Generative Agents: Interactive Simulacra of Human Behavior - Summary |
The Quill |
Apr 16, 2023 |
283 |
- |
| ⭐ The Developer’s Guide to OpenTelemetry: A Real-Time Journey into Observability |
Kavya MD |
Oct 15, 2024 |
1124 |
- |
| Tracking LLM token usage across providers, teams and workloads |
Drishti Shah |
Dec 04, 2025 |
1437 |
- |
| Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference - Summary |
The Quill |
Dec 26, 2024 |
471 |
- |
| Unpacking Semantic Caching at Walmart |
Vrushank Vyas |
Feb 05, 2024 |
576 |
- |
| Architecting for Trust: A Strategic Perspective on the MCP Registry for the Enterprise |
Rohit Agarwal |
Sep 09, 2025 |
793 |
- |
| Portkey on the AWS Marketplace |
Siddharth Sambharia |
Mar 16, 2025 |
572 |
- |
| Scaling Transformer to 1M tokens and beyond with RMT - Summary |
The Quill |
May 07, 2023 |
233 |
- |
| GPT Understands, Too - Summary |
Rohit Agarwal |
Apr 15, 2023 |
244 |
- |
| MiLMo:Minority Multilingual Pre-trained Language Model - Summary |
The Quill |
Apr 20, 2023 |
200 |
- |
| ⭐️ Analyze your LLM calls - 2.0 |
Rohit Agarwal |
Aug 07, 2023 |
621 |
- |
| Everything We Know About Claude Code Limits |
Rohit Agarwal |
Jul 29, 2025 |
736 |
- |
| Buyer’s guide to LLM observability tools 2026 |
Drishti Shah |
Nov 27, 2025 |
1518 |
- |
| SLiC-HF: Sequence Likelihood Calibration with Human Feedback - Summary |
The Quill |
May 21, 2023 |
222 |
- |
| Deep Dive: OpenAI's o1 - The Dawn of Deliberate AI |
Rohit Agarwal |
Dec 08, 2024 |
1268 |
- |
| Segment Everything Everywhere All at Once - Summary |
The Quill |
Apr 16, 2023 |
201 |
- |
| AI cost observability: A practical guide to understanding and managing LLM spend |
Drishti Shah |
Nov 21, 2025 |
1861 |
- |
| ⭐ Building Reliable LLM Apps: 5 Things To Know |
Rohit Agarwal |
Aug 01, 2023 |
1159 |
- |
| Supercharging Open-source LLMs: Your Gateway to 250+ Models |
Vrushank Vyas |
Aug 05, 2024 |
890 |
- |
| Attention Isn’t All You Need |
Siddharth Sambharia |
Aug 22, 2024 |
838 |
- |
| Generative Agents: Interactive Simulacra of Human Behavior - Summary |
The Quill |
Apr 16, 2023 |
197 |
- |
| Mixtral of Experts - Summary |
The Quill |
Jan 09, 2024 |
343 |
- |
| Portkey x Pillar - Enterprise-grade Security for LLMs in Production |
Vrushank Vyas |
Aug 15, 2024 |
485 |
- |
| Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations - Summary |
The Quill |
Jun 02, 2023 |
221 |
- |
| Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding - Summary |
The Quill |
Aug 21, 2023 |
174 |
- |
| Expanding the AI Gateway with Google Vertex AI Integration |
The Quill |
Apr 29, 2024 |
394 |
- |
| Anyscale's OSS Models + Portkey's Ops Stack |
Rohit Agarwal |
Dec 12, 2023 |
372 |
- |
| OpenAI - Fine-tune GPT-4o with images and text |
Kavya MD |
Oct 20, 2024 |
1044 |
- |
| Evaluating Long-Context LLMs |
The Quill |
Feb 14, 2025 |
371 |
- |
| How to differentiate your AI product - Jasper style! |
The Quill |
Sep 20, 2023 |
439 |
- |
| August at Portkey: 2 BILLION Requests, Guardrails, Tracing, and More |
Vrushank Vyas |
Sep 05, 2024 |
559 |
- |
| Discovering Language Model Behaviors with Model-Written Evaluations - Summary |
The Quill |
May 08, 2023 |
415 |
- |
| LLM routing techniques for high-volume applications |
Drishti Shah |
Dec 05, 2025 |
1453 |
- |