Tessl - Blog · Scour

How Small Can an Agent Model Get? The Nemotron Floor

Cursor's new leaderboard shows teams the most popular plugins, skills and MCPs

Covers 2 stories including New comment by Alifatisk in "SpaceX to buy Cursor for $60B"

The new Tessl review: now you decide what "good" looks like:

AI Agent Governance: 10 Takeaways from Engineering Leaders on Agentic Development

Why Warp is betting engineering leaders are done picking a favourite coding agent

Covers 3 stories including Warp – The Intelligent Terminal

Open-Source Agents vs Sonnet 4.6: GLM 5.2, MiniMax M3, Kimi 2.7 and Qwen 3.7 Tested

How I Scan My Agent Context Across GitHub with Skill Inventory

Why Your Gemini Bill Doesn't Match the Model Names

Claude Fable 5 vs Opus 4.8: The Mythos Hype Meets Reality

Covered by newsletter.gtmengineering.ai

Reflection Before Augmentation

The State of the AI Coding Stack: Agent Skills, Harnesses, and Enablement at AI Native DevCon London 2026

Covers 8 stories including Generate golang structs from protobuf

Same quality, a quarter of the cost: Should DeepSeek Flash be your model of choice?

The hidden cost of agentic software development: why context engineering matters

Covers Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

Anthropic details how attackers are weaponising Claude Code — but says AI will ultimately give defenders the edge

Covers 9 stories including Project Glasswing: Securing critical software for the AI era

AI Native DevCon Day 2: From Agent Demos to Operating Models

The model's solved, now comes the hard part: Reviewability as the bottleneck

Covers Kilo Code - Move at Kilo speed

AI Native DevCon Day 1: Making AI Agents Ready for Enterprise

Covers Where are the uploaded skill folders stored on the MacOS file system?

AI Coding Agent Accuracy: Opus 4.7 vs 4.8

Opus 4.8 tops the LLM leaderboard with 95% on skill evals

Why We're Changing Our Default Eval Model

Log in to enable infinite scrolling