No slides, no hype. I teach by building live on YouTube and X: AI agents, local models, and AI workflows, mistakes included. Join live and ask questions in chat, catch the replays on YouTube, and follow on X for the latest AI updates.
people trained through talks, workshops, and mentoring
2.2k+
GitHub stars on the open-source tools I teach with
25+
years shipping software, the context behind every video
Workshops & talks
Bring an AI workshop to your school or organization.
The same way I teach on the livestreams, run for your students, faculty, or team: hands-on sessions on AI Agents, Local Models, and AI Workflows, in plain language. Online via Zoom, with on-site options on request.
OpenAI said (Oct 22) the Decisions API is generally available. Built with GPT-6 Luna, it answers bounded questions from text, images, and structured inputs, and OpenAI says it is up to 10× faster than GPT-6 Luna through the Responses API. Since public beta, OpenAI added a native GPT-Live integration, prompt caching, and inference residency in the US and EU. Developers can pass native JSON, include images in question instructions, and ask up to 400 questions per request, twice the previous limit. Answer types stay predicate (a probability from 0 to 1), choice (one supplied option, plus probabilities and confidence), and score (a probability-weighted average of ordered level indices). Pricing is $0.10 per million input tokens and $0.01 per million cached input tokens, with no output-token charge. Regional processing is available in the US and EU, and zero data retention is available to eligible customers. Quoted customer results are the customers’: Box about 5× faster route selection on 30 certificate-of-insurance cases at the same accuracy as the Responses API; Datadog 40× faster p95 with comparable accuracy; Ramp 4× faster and 30% cheaper than GPT-6 Luna; Sierra under 280 ms p95, about 3× faster and 90% lower cost per call; Speak cut time to next action by over 90%, from 1.4 seconds to 0.13 seconds, in a GPT-Live test. Distinct from the Oct 6 public-beta card and from TypeSafe Jev, Cloudflare Clef, and GPT-6 Luna on the Responses API.
Anthropic said (Oct 22) it is donating Agent Skills, the open standard for giving agents specialized knowledge and workflows, to the Agentic AI Foundation under the Linux Foundation. Anthropic says more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot, and VS Code, have integrated the standard since it was published in December 2025, and that 1 million skills have been published and nearly 280 million installed. A skill is a folder with a SKILL.md file plus any scripts or reference files. The donation includes the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain. People can keep using or contributing without joining the foundation. Engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as lead maintainers. Anthropic has proposed versioned releases, a formal proposal process, and security guidance for people who write and install skills. Distinct from Anthropic’s earlier donation of the Model Context Protocol to the same foundation and from the U.S. Department of Energy’s Genesis Agent Skills package.
Google DeepMind and Google Research, with the World Resources Institute and the International Institute for Applied Systems Analysis, released (Oct 22) Forest Typology (ForTy) 2020. The map labels every 10-by-10-meter patch of land as primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops and agroforestry, or other land, using UN Food and Agriculture Organization definitions. An early time series tracks those classes each year from 2017 to 2025, including where natural forest was replaced by plantations or farms. The model takes AlphaEarth Foundations embeddings as a key input and was trained on about 1.7 million labeled locations. Against more than 9,000 expert-reviewed sites, DeepMind says ForTy picked the right forest type 90% of the time and separated forest from non-forest 95% of the time. Each class also has a probability score so users can set their own threshold. The 2020 map, described in Scientific Data, and the time series are free on Google Earth Engine under an open license. Distinct from last year’s Natural Forests of the World 2020 map and from Ai2’s same-day OlmoEarth v1.3 embeddings.
Source: Google DeepMind
Updated October 22, 2026
What I teach: AI Agents, Local Models & AI Workflows
AI Agents
Autonomous agents with memory, tools, and skills that do the work, not just chat about it.
I teach AI Agents, Local Models, and AI Workflows to people who want to use AI, not just read about it. Before the channel: senior engineering roles at Standard Chartered Bank and Ohmyhome (Nasdaq), then a run of AI products built and shipped end to end. That's why every video, talk, and post is grounded in what actually ships.
Livestreams AI builds on YouTube and X
Speaker at NTU Singapore, PSIA, and DICT Philippines
300+ trained through workshops and mentoring
Open-source maintainer: Codex orchestrator, Local Evals, Agent Monitor
Subscribe on YouTube for the next livestream and follow on X for the latest AI updates. Want a workshop for your school or organization, or help with a product? Book a call.
