AI Weekly Malaysia

Cloudflare launched Auto Router in public beta through AI Gateway: set your model to `cloudflare/auto` and each request is routed to a model judged 'capable enough' for the task instead of a manually chosen frontier model. Cloudflare reports up to 30% cost savings from its own internal use through its OpenCode harness and Cloudflare OS agent harness, versus using only frontier models it names as OpenAI Sol and Anthropic Claude Opus. The published post is truncated right where the results section begins, so the full measurement details are not in the text provided.

Why: If you already route LLM calls through Cloudflare AI Gateway, this is a one-line change (`cloudflare/auto`) you can A/B against your current model choice, which matters most for teams whose non-technical workflows are burning Opus-class tokens on tasks like email or thread summarisation. Treat the 30% as a vendor internal figure, not a benchmark: run it on your own traffic and compare quality on your hardest tasks before making it the default, because routing decisions you cannot see are also routing decisions you cannot easily debug.

At OpenAI's Dev Day, Sam Altman revealed a limited-preview "Decisions API" that gives the Luna model a predefined set of options to pick between — image categories, agent behaviors — and returns that choice fast. It looks like a clone of Jev, a model released earlier in September by TypeSafe AI that acts as an LLM-based classifier outputting probabilities over a fixed choice set cheaply and at high speed. TypeSafe CEO Diogo Almeida joked on X about "clone wars" and said OpenAI's interest could signal that building in a "System One" (fast, intuitive) way is the future; TechCrunch notes it's unclear how close the two products are, and hasn't yet spotted developers using Decisions API.

Why: If you're paying per-token for agent routing or classification steps, the pitch here is real: Jev-style endpoints replace an open-ended generation call with a probability over a fixed list of choices, which developers using Jev reportedly found faster and cheaper than augmenting an LLM. OpenAI's version is limited preview with no public developer reports, so don't re-architect on it yet — but it's worth benchmarking Jev on your own routing/classification workload now, since that one is already shipping.

John Lindquist (creator of egghead.io, now building mega.dev) demos eight uses of Jev, described in the episode as a 'TypeSafe AI decision model' and 'a decision engine, not a chatbot.' The demos include a real-time voice to-do app that classifies and executes commands with no visible pause, data deduplication and record merging in milliseconds using confidence scores, Jev as a multi-level app router, a chess match against a low-reasoning LLM for speed/cost comparison, and multi-agent coordination with collision avoidance. The episode also covers where Jev falls short and when to reach for a full generative model, with Vercel AI Gateway, OpenRouter, and Opus 5.5 referenced as surrounding tools.

Why: The reusable pattern here is narrow decision calls (routing, classifying, deduping) instead of one big generative model for everything: John chains sequential Jev calls, adds multi-step classification when one pass isn't enough, and pairs confidence scores with multi-model validation before merging records. Note the title's 'fastest, cheapest' claim is not backed by any number in the text, and no prices or latency figures are given, so treat the cost advantage as unverified until you benchmark it yourself on your own traffic.

At its Dash Forward 2026 event, DoorDash unveiled a six-propeller delivery drone and formally named the service DoorDash Air, built by the DoorDash Labs team that previously made the Dot sidewalk delivery bot. DoorDash says it designed the system backwards from ground operations — loading, kitchen handoff, packaging — and runs all human, bot, and drone deliveries through one coordination layer called the Autonomous Delivery Platform (ADP), which routes orders using weather, flight range, and ground traffic to decide which orders are worth flying. The company received FAA Part 135 air carrier certification in July and says it sized the whole system around 13 years of order data covering more than 500,000 marketplace restaurants; Harrison Shih, who heads DoorDash Air, said they 'started with what people order' rather than with the aircraft.

Why: There is no Malaysian or Southeast Asian angle in this piece and nothing here that changes what a local builder ships, buys, or prices this week — it is a US delivery company describing its own product and its own certification milestone, so treat it as background reading rather than an action item. The one transferable idea, if you are building routing or multi-modal dispatch software, is ADP's framing: pick the mode (human, bot, drone) after scoring the job on weather, range, and ground traffic, not before. Nothing in the text supports a claim about cost, availability, or timeline for anyone outside DoorDash's US operations.