What can be said can be solved.

Joined June 2020
385 Photos and videos
Jun 11
Hundreds of lines of code. Multiple frameworks. Weeks of setup. Then you spend half your time maintaining all of it.
4
1
2
76
Jun 11
It's not a script runner. It uses an LLM to read the intent of your test, decide which tools to use, and execute. Screenshot → API call → Shell command → MCP server
36
Jun 11
What if your test suite was just a folder of text files? No selectors. No XPath. Just: describe what should happen. The agent figures out the rest.
16
Jun 11
And Selenium only covers the browser. APIs. Shell commands. Car dashboards. HMI panels. The moment your product goes beyond the browser you're adding another tool. And another.
25
Jun 3
8 releases. 2 months. Zero new benchmark claims. Everyone's obsessed with making AI smarter. We've been making it less likely to break.
3
1
5
89
Jun 3
Two things we'd been putting off. WebAgent is now a proper browser automation agent full Playwright tools, not just navigation. Mouse, keyboard, screenshots, the works. WebVisionAgent is deprecated. And AutomationError: a new exception type for genuinely unfixable errors. Missing credentials, unreachable services. Stops execution immediately instead of sending the agent into a retry loop.
1
60
Jun 3
Last batch and probably the biggest for flexibility. Agents can now read files and list directories on the automation target directly. And AskUI now supports any OpenAI-compatible model. Ollama, vLLM, LM Studio, Together AI, RunPod. If it exposes a chat completions endpoint, it works. Bring your own model. pip install askui --upgrade github.com/askui/python-sdk #agentdev
1
60
Mar 25
AI & Agentic Workflow News: March 18–25 Most are fighting over model IQ. The real bottleneck is the execution layer. This week marks the end of the Mac Mini era for agents. Between Anthropic's native remote execution and GitHub's 12-month LTS, we are moving from how to host to how to execute anywhere. But as builders know, a brain is useless if it can't bypass a lock screen or survive a session drop. Full breakdown on the shift to Unstoppable Execution: #AIAgents #Infrastructure #Automation #SoftwareEngineering
3
112
Mar 18
The model is the brain. The execution layer is the nervous system. 3 releases, one thesis: - v0.25: Architecture rewrite speaker-conversation pattern with pluggable cache execution - v0.26: One agent controls PC Android simultaneously - v0.27: Execution cost tracking OpenTelemetry tracing (shipped today) The full breakdown ↓ #Agents #AI #ComputerUseAgent #AskUI
2
65
Mar 3
🚨 BREAKING: The Great Migration of March 2026 has begun. Stop building chatbots. Start deploying Computer Agents. As OpenAI, Google, and Anthropic consolidate around production-grade baselines, the battle has moved from "how a model thinks" to "how a model executes". Intelligence is now a commodity. Execution is the premium. pip install --upgrade askui #AIAgents #Agent #AskUI #v0240 #ComputerAgent #GPT #Gemini
1
1
115
Feb 17
Thinking is easy. Seeing and acting is where the war is won. Feb 2026 marks the end of "Chatbots" and the rise of the "Autonomous Teammate." Here is what you need to know
3
94