Today, we are launching our first commercial product: Sakana Marlin, Your Virtual CSO. Marlin is an autonomous research assistant for business, built around hours of long-horizon reasoning. Try Marlin: https://
sakana.ai/marlin
Blog: https://
sakana.ai/marlin-release
/#English
… You provide a research
AGENTS
-
Sakana Marlin Launch: Virtual CSO Autonomous Research Assistant
By
–
-
xAI Turns Grok Tasks into Grok Automations
By
–
xAI plans to transform Grok Tasks into Grok Automations. A new version will feature skills and a model selector.
-
Deep Agents: Execution Environment, the Backbone
By
–
Deep Agents deep dive from @SydneyRunkle | Part 1
— LangChain (@LangChain) 15 juin 2026
The execution environment, or the backbone of a Deep Agent. pic.twitter.com/baoiUDGvxuDeep Agents: Deep Dive by @SydneyRunkle | Part 1 The execution environment, or the backbone of a Deep Agent.
-
Lyft builds 8 AI agents solving 35% of customer problems
By
–
.@Lyft built 8 AI agents that are capable of fully resolving 35% of all customer issues.
— LangChain (@LangChain) 15 juin 2026
At Interrupt, they shared the evals used internally, how they scale evals with LangSmith, and the lessons learned along the way. https://t.co/SHmYnOo84p pic.twitter.com/VDz7VsdTGN@Lyft built 8 AI agents capable of completely solving 35% of all customer problems. At Interrupt, they shared the evaluations used internally, how they scale evaluations with LangSmith, and the lessons learned throughout
-
AI agents inaccurate due to missing context, says expert
By
–
Why do so many AI agents give inaccurate answers?
— Pascal Bornet (@pascal_bornet) 15 juin 2026
Often, it is not the model’s fault. The agent simply lacks the right context.
I recently discussed this with @Chris Hallenbeck, SVP and GM of AI & Platform at @Boomi. We dove into why "context" is the missing link for enterprise… pic.twitter.com/X469ttKNJLWhy do so many AI agents give inaccurate answers? Often, it is not the model’s fault. The agent simply lacks the right context. I recently discussed this with @Chris Hallenbeck, SVP and GM of AI & Platform at @Boomi
. We dove into why "context" is the missing link for enterprise -
Automated PR creation from issues matching VISION.md
By
–
Whenever you create an issue on one of oure open source projects, @clawsweeper will review it, and *if* it fits the VISION.md file, will pick it up and create+autoreview a PR. e.g.:
-
Claude reduces unproductive tasks time by 5X
By
–
Love how Claude reduces my unproductive tasks time by 5X.
-
Anthropic engineer shows autonomous coding workflow with Claude Code
By
–
“You're not supposed to watch Claude Code work. You're supposed to wake up and review what it shipped.”
— Charly Wargnier (@DataChaz) 15 juin 2026
In a new 14-minute live demo, an Anthropic engineer builds out an entirely autonomous workflow from scratch.
The core problem for most devs:
→ When you close your terminal,… https://t.co/KXpbmYWoiw pic.twitter.com/UW57Fs1BqC“You're not supposed to watch Claude Code work. You're supposed to wake up and review what it shipped.” In a new 14-minute live demo, an Anthropic engineer builds out an entirely autonomous workflow from scratch. The core problem for most devs:
→ When you close your terminal, -
Anthropic Ultracode: Intelligent Subroutines for Token Burning and Parallelization
By
–
havent seen many people outside anthropic ultracode yet. this thing is scarily good at burning tokens but you need to set up your repo to parallelize properly to make use of the fanout that i think subagents are best at. basically the idea is "subroutines but intelligent". when
-
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
By
–
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry Paper: https://
arxiv.org/abs/2606.14249