8 min read

Supervising the synthetic workforce: Observability for AI agents requires managers, not metrics

Enterprise AI agents aren’t APIs — they’re semi-autonomous systems that need supervision like employees. Learn why observability isn’t enough and how to build governance for your synthetic workforce at scale.

Matan-Paul Shetrit

Writer Engineering

Recent

11 min read Anyone can build software now — and it’s causing hell for developers

10 min read Reflect, retry, reward: Self-improving LLMs via reinforcement learning

9 min read Beyond the demo: What I’ve learned deploying production AI for enterprises

6 min read Introducing Palmyra X5

14 min read Model Context Protocol (MCP) security

8 min read

Supervising the synthetic workforce: Observability for AI agents requires managers, not metrics

Matan-Paul Shetrit

11 min read

Anyone can build software now — and it’s causing hell for developers

May Habib

10 min read

Reflect, retry, reward: Self-improving LLMs via reinforcement learning

Shelly Bensal

9 min read

Beyond the demo: What I’ve learned deploying production AI for enterprises

Ugo Osuji, customer AI engineer

6 min read

Introducing Palmyra X5

Writer Team

14 min read

Model Context Protocol (MCP) security

Muayad Ali, Director of Engineering

7 min read

WRITER is now available for LangChain: Build powerful AI applications with ease

Sam Julien

4 min read

Writer SDK 2.0 release: async jobs, model delegation, and more

Sam Julien

10 min read

Expecting the unexpected: A new benchmark for LLM resilience in finance — FailSafeQA

Writer Team

10 min read

Self-evolving models, not test-time compute methods, are the future of AI

Waseem AlShikh

10 min read

The incentives of model innovation

Waseem AlShikh

10 min read

A breakdown of LLM agent types

Waseem AlShikh

10 min read

Synthetic data: Busting the myths holding back enterprise AI progress

Waseem AlShikh

5 min read

WRITER RAG tool: build production-ready RAG apps in minutes

Hollis Kool

5 min read

Navigating the challenges of generative AI and “vendor lock-in” in enterprises

Waseem AlShikh

10 min read

The three keys to escaping AI POC purgatory

Sam Julien

6 min read

Introducing self-evolving models

Waseem AlShikh

13 min read

Why AI-native enterprise apps are the business brain of the future

Waseem AlShikh

8 min read

Introducing actions
with Palmyra X4

Sam Julien

21 min read

Vector database vs. graph database

Ksenia Anske

11 min read

RAG vector database explained

Ksenia Anske

14 min read

How to build an embedded app with graph-based RAG

Sam Julien

4 min read

Introducing Writing in the Margins

Writer Team

6 min read

Simplify financial app development with the WRITER Framework and Palmyra Fin

Sam Julien

6 min read

Introducing Palmyra Med and Palmyra Fin

Sam Julien

10 min read

The new paradigm: AI-native enterprise applications

Waseem AlShikh

6 min read

RAG benchmarking: Writer Knowledge Graph ranks #1

Writer Team

6 min read

Introducing Writer AI Studio

Sam Julien

10 min read

Short transformers: easily prune redundant LLM layers

Melisa Russak

10 min read

The rise of domain-specific Large Language Models

Waseem AlShikh

10 min read

Q&A with Knowledge Graphs

Waseem AlShikh

10 min read

Insights from LLM Control Theory

Waseem AlShikh

10 min read

Comparative analysis of retrieval systems in the real world

Writer Team

10 min read

OmniACT: a groundbreaking dataset and benchmark for autonomous agents

Waseem AlShikh

10 min read

OmniACT: A dataset and benchmark for enabling multimodal generalist autonomous agents for desktop and web

Writer Team

10 min read

Why we chose DPO over RHLF

Waseem AlShikh

10 min read

LLMs: Skills, behaviors, and knowledge

Waseem AlShikh

4 min read

Meet Palmyra Med, a powerful LLM designed for healthcare

Writer Team

10 min read

Palmyra Med: instruction-based fine-tuning of LLMs enhancing medical domain performance

Writer Team

10 min read

Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning

Writer Team

10 min read

Grammatical error correction: a survey of the state of the art

Writer Team

10 min read

Fusion-in-Decoder: Achieving state-of-the-art open-domain QA performance

Writer Team