I recently came across Language model harnesses are compositional generalizers new article from Alex Zhang and Omar Khattab, which presents a timely argument about RLM concepts that we are exploring with RLM […]
Category: Agentic AI
Superagentic AI Speaks on RLM at the AI Engineer World’s Fair 2026
Superagentic AI returned to the AI Engineer World’s Fair 2026 Online Track with a second talk, “RLM: Recursive Language Models for Large Codebases.” The session, delivered by Shashi Jagtap, Founder […]
What’s New in SuperQode: Latest Models, Smaller Core and Python-Extensible Harnesses
The coding-model landscape is moving faster than the software around it. In the space of a few weeks, OpenAI introduced GPT-5.6, xAI released Grok 4.5, Meta launched Muse Spark 1.1, […]
Self-Optimizing Coding Agent Harnesses with SuperQode
Coding agents have become a practical part of software development workflows. Tools such as Codex-style agents, Claude Code-style agents, OpenCode-style agents, and IDE-integrated assistants are increasingly good at reading repositories, […]
Introducing SuperQode: The Era of Harness Independence and Self Harness Engineering
The Agentic coding agent market has spent the last year focused on model independence. That focus remains important, but it is no longer sufficient. A coding agent consists of a […]
Optimizing Databricks Omnigent Agents with MetaHarness
Databricks has just released the Omnigent the meta-harness for the AI agents. It is timely that Superagentic AI released meta-harness library few months ago. These meta-harness concepts sounds same but they […]
Superagentic AI at the Google I/O and CAIS Conference: Reflections from Bay Area
Last week, I returned to London from the San Francisco Bay Area with renewed energy, fresh insights, and a deep appreciation for the people driving artificial intelligence forward. Since back, […]
PyFlue 0.2.0: Bringing Flue’s Agent Runtime Model to Python
PyFlue 0.2.0 is now available. This release is a major step toward parity with the TypeScript Flue framework and introduces a clearer runtime model for building production-oriented Python agents. The […]
Dynamic Workflows Vs Recursive Language Models (RLMs): Through Academic and Industry Lenses
Anthropic launched Opus 4.8 with Are Anthropic’s Dynamic Workflows Truly RLMs in the Cloud? Anthropic recently launched the Opus 4.8, the smartest model which has highly capable coding task and […]
CodexOpt Brings Microsoft SkillOpt to Codex: Optimizing Agent Skills with Execution Feedback
Microsoft Research released the SkillOpt paper. The work has generated considerable discussion across the AI community. Researchers and engineers highlight its disciplined approach to improving agent capabilities without modifying model […]