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.
Google DeepMind said (Oct 31) PlanAssist, a Gemini-based tool for routine householder planning applications in England, will be offered to 12 more local planning authorities, bringing the councils in the program to 15. DeepMind says a 12-month beta will use live applications, starting with a subset of councils, and that the UK government plans to make the tool available to every council in England in 2027 if testing succeeds. In early pilots in Barnet, Camden, and Dorset, DeepMind says the average time a planning officer spent on householder assessment tasks fell by 58%, and that more than 70% of the reports the tool drafted were approved with no edits. Planning officers keep the final decision. The tool checks submitted documents and drawings, heritage constraints and planning policy, and earlier objections, then drafts cited reports an officer can edit. DeepMind built it with the UK government, Google Cloud, and Faculty, and says householder applications account for up to 70% of officers’ workloads. A Ministry of Housing, Communities and Local Government note dated Oct 30 says the expansion sits alongside planning-rule changes that take effect Oct 31, and that the ministry is aiming to cut routine householder processing from eight weeks to four. Those time figures are the publishers’. Distinct from the June planning-prototype announcement.
Apple said (Oct 31) the first core Apple Intelligence features are coming to iPhone users in China. Testing opens November 4 with the latest iOS developer beta, and Apple plans the consumer release with iOS 27.3 in December. Other Apple platforms wait on the approvals Apple says are still required. Apple says it is working with Alibaba so some of these experiences can use Qwen, including text and image understanding in Siri, Writing Tools, and Visual Intelligence. A signed-in Qwen account, or Sign in with Apple, is how that access works. Features named in the release include Live Translation, Writing Tools, Visual Intelligence, Clean Up in Photos, Genmoji, natural-language photo search, memory movies, Priority Mail, mail summaries, smart replies, notification summaries, and type-to-Siri. The release does not include Siri AI or the other next-generation Apple Intelligence features Apple previewed at WWDC 2026. Supported phones are iPhone 16 and later, iPhone Duo, iPhone 15 Pro, iPhone 15 Pro Max, and iPhone Air, with Siri and the device language set to English or Simplified Chinese. Distinct from the June WWDC preview, which said those newer features were not yet available in mainland China.
Anthropic’s Claude Code changelog for October 31 adds pooled group budgets on the Claude apps gateway: one monthly budget a group’s members share, on top of each person’s own limit, set with pooled_budget on the spend-limits admin API. The same notes add a setting for the effort level subagents use when nothing else names one, sign-in to a Claude apps gateway from the VS Code chat panel, a form card in cloud sessions when an MCP server asks for input, and a code-review chart of findings by severity. The changelog also records that fast mode for Claude Opus 4.8 was deprecated on October 30 and will be removed on November 30, 2026. After that date, Anthropic says a fast-mode request on Opus 4.8 returns an error and does not fall back to standard Opus 4.8, and it points people to Opus 5.5. For Team and Enterprise logins, settings fetched from Anthropic’s API now apply without an approval prompt, and a stored copy that does not verify is refused. Enterprise members can add and delete network secrets on their own cloud environments. Distinct from the October 7 Haiku 5.5 release and from the October 29 marketplace notice about unofficial Claude Code builds.
Source: Anthropic
Updated October 31, 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.
