I wrote a whole guide! https://simonwillison.net/guides/agentic-engineering-patterns/ …
AGENTS
-
LangSmith Fleet template: Software Engineer coding agent from Slack, Linear, GitHub
By
–
LangSmith Fleet template spotlight: Software Engineer Ships code from Slack, Linear, and GitHub in a sandbox A coding agent that takes issues from @Linear
, writes and verifies the code, and opens a PR. Triggered directly from Slack. -
Abacus AI Agent Adds Claude Fable Mode for Task-Specific Model Routing
By
–
Abacus AI Agent Now Has Claude Fable Mode Route to the best model based on your agentic task > Fable – hard coding
> GPT 5.5 – data analysis
> Gemini – research
> Opus 4.8 – design and ppt
> DeepSeek – Agent Swarms
> GPT 5.5 + Opus 4.8 – mobile apps BUILD, CREATE AND -
AI chatbots give invisible wrong facts in news, Stanford study finds
By
–
1 in 10 Americans now get news from AI chatbots. When @Stanford researchers tested them with 2,100 real news questions, they found that the chatbots can get facts wrong in invisible ways. Here's what they discovered: https://
hai.stanford.edu/news/reading-t
odays-headlines-through-ai-a-real-time-audit-of-six-commercial-chatbots
… -
Full-text search JSON filtering with custom inverted index for SmithDB
By
–
How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latency of 400ms? Here’s an inside look at how we built a custom inverted index from scratch for SmithDB.
-
Claude Fable 5 as orchestrator model for long agentic workflows
By
–
You can use Claude Fable 5 as the orchestrator model inside Computer. Available to all Pro and Max users! It’s really really good for long running agentic workflows. https://t.co/c6uPF0dpZv
— Aravind Srinivas (@AravSrinivas) 10 juin 2026You can use Claude Fable 5 as the orchestrator model inside Computer. Available to all Pro and Max users! It’s really really good for long running agentic workflows.
-
Cursor’s code review agent faster, cheaper, and finds more bugs
By
–
Cursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs.
— Cursor (@cursor_ai) 10 juin 2026
You can also use /review to run Bugbot locally to catch and fix issues before pushing code. pic.twitter.com/Pl7lhoR6TECursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs. You can also use /review to run Bugbot locally to catch and fix issues before pushing code.
-
Tori agent uses SpaceXAI data for market sentiment analysis
By
–
Read more about how Tori, eToro's agent, leverages models and real-time data from SpaceXAI to help consumers analyze market sentiment https://
x.ai/news/grok-etoro -
Agentic AI drives tech services to pick role, from enabler to builder
By
–
Agentic AI is pushing tech services to pick a clear role, from enabler to full solution builder. Each choice affects skills and delivery, so organizations must decide where to invest and how to scale. Source @McKinsey Link https://
mck.co/4cCZTGm via @antgrasso -
Community-funded Fable run for GTA-VI-caliber open-world game
By
–
Someone should set up a community-funded Fable run with a prompt like: "/loop until you've created a GTA-VI-caliber open-world game with a quality and scope surpassing what is shown in the initial trailers" Happy to write the prompt if someone organizes this!