Topic · ai
AI agents
Agents in real enterprise environments - routing, permissions, tooling and the unglamorous work that decides whether one ships.
Notes
19 published
019Claude Opus 5.5 and GPT-6 Sol: flagship capability at mid-tier prices, three weeks laterOn 22 September 2026 Anthropic shipped Claude Opus 5.5 and OpenAI shipped GPT-6 Sol and Luna. The capability that was the flagship at the start of the month now costs a mid-tier price, which makes every model routing table written in August out of date.TECH NOTE · 7 MIN018Decision models: what Jev, Solar Decide and Span-01 mean for enterprise workflowsIn September 2026 three vendors shipped models that return a typed answer and a probability instead of text. For routing, triage and compliance flags that is a better interface than prose, provided you demand the calibration evidence and build a branch for "unsure".TECH NOTE · 8 MIN017Claude formalised Fermat's Last Theorem in Lean: what 13 million checked lines teach about verifying agent outputAnthropic's agents produced the first end-to-end, computer-checked proof of Fermat's Last Theorem in 11 days. The mathematics was not new. The verification was, and so is what it shows about where trust has to sit when output outgrows anyone's ability to read it.TECH NOTE · 8 MIN016Meta Muse Spark 1.3 and the Contributor tier: the discount is paid in training dataMeta released Muse Spark 1.3 on 2 September 2026 with a model trained to ask before it acts, and kept a Contributor tier that costs a fraction of Standard in exchange for training on your prompts and completions. The behaviour is the better story. The pricing is the one that needs a policy.TECH NOTE · 7 MIN015OpenAI Astra for Law: the model is not the product, the index isOpenAI launched Astra for Law on 17 September 2026. It is GPT-6 Astra plus legal instructions, settings and a US-only Legal Search Index, not a new model. The benchmark gain came from retrieval, and that is the lesson for anyone building legal AI outside the US.TECH NOTE · 8 MIN014OpenAI DevDay 2026: dots agents get their own computer, a day after OpenAI held back GPT-6.1 AstraOpenAI launched dots, always-on agents with their own cloud computer, browser and rules, on 29 September 2026. The day before, it said the next Astra model would not ship because it did not meet OpenAI's bar for staying within scope and authorization. Read together, those two announcements are the most useful thing DevDay said to anyone building agents.TECH NOTE · 7 MIN013Ternary Bonsai 2 27B: Qwen3.8-27B in 5.9GB, and where the 98% stopsPrismML released Ternary Bonsai 2 27B on 17 September 2026, a ternary-weight build of Qwen3.8-27B that fits in 5.9GB and keeps 98.2% of the full model's benchmark average. On long-horizon agent tasks it keeps about three quarters. Here is how to read both numbers before you replace a 4-bit quant.TECH NOTE · 8 MIN012A successful pilot is not a decisionThe most common outcome of an enterprise pilot is not failure. It is a pilot that works, is agreed to have worked, and is followed by nothing.OPINION · 4 MIN011The code got cheaper. The reading didn'tAn agent can produce more code in an afternoon than I can properly read in a week. The constraint moved, and most of the workflows built around it have not.OPINION · 4 MIN010MCP went stateless: what the 2026-07-28 spec changes if you run agentsThe Model Context Protocol dropped sessions at the protocol layer. No initialize handshake, no Mcp-Session-Id header, every request self-describing. Here is what actually breaks, what gets easier, and what I would change first.SYSTEM NOTE · 6 MIN009A 27B model under Apache 2.0: what Qwen3.8-27B changes for local AIAlibaba published Qwen3.8-27B weights on 14 August 2026 under Apache 2.0, dense rather than mixture-of-experts, with a 262k native context. The licence matters more than the benchmark scores, and here is why.AI NOTE · 6 MIN008Saudi Arabia is an interesting place to build enterprise AINot for the reasons usually given. The interesting parts are the constraints - data that will not move, Arabic as a first-class requirement, and buyers who ask hard questions early.OPINION · 3 MIN007What I actually use AI for as a technical founderA practical list, including the parts where it does not help and the places I have decided not to let it near.FOUNDER NOTE · 2 MIN006The best architecture is sometimes hybrid: local + cloud AIHybrid is usually the right answer and usually implemented badly - arrived at by accident rather than designed, which gives you the costs of both and the clarity of neither.SYSTEM NOTE · 2 MIN005Local AI vs cloud AI: what actually makes sense for Saudi companies?The comparison usually gets made on price, which is the least interesting axis. Here is how the decision actually breaks down, including when the honest answer is cloud.AI NOTE · 4 MIN004Why I'm interested in Mac minis for local AI deploymentsA small machine on a shelf is a genuinely viable AI deployment target now. Here is what that is good for, and the parts people leave out.BUILD LOG · 3 MIN003"No source, no claim" should be the default for high-stakes AIIn legal, compliance and finance, a confident wrong answer costs more than a refusal - and unlike a refusal, it does not announce itself.OPINION · 3 MIN002AI agents are easy to demo. Production agents are different.The demo works because you chose the input. Production is where an agent meets a permissions model, a flaky API and someone who will not read the output carefully.AI NOTE · 3 MIN001The architecture behind a source-grounded legal AI assistantRetrieval as a gate rather than a hint, citations carried as data rather than text, and why corpus preparation matters more than model choice.SYSTEM NOTE · 2 MIN
Work
001MyAdvisor.aiAn Arabic-first legal AI platform for Saudi and international business law, built on one rule - no source, no claim.LEGAL AI
IN DEVELOPMENT→002MyAdvisor.ai Due DiligenceThe due-diligence module - built to produce evidence a lawyer can check, not answers they have to trust.LEGAL AI · DUE DILIGENCE
IN DEVELOPMENT→003Local AI & agent infrastructureLocal-first AI infrastructure: running AI agents on local hardware for real business workloads, and working out where that genuinely beats the cloud - and where it does not.AI INFRASTRUCTURE
ACTIVE→
IN DEVELOPMENT→002MyAdvisor.ai Due DiligenceThe due-diligence module - built to produce evidence a lawyer can check, not answers they have to trust.LEGAL AI · DUE DILIGENCE
IN DEVELOPMENT→003Local AI & agent infrastructureLocal-first AI infrastructure: running AI agents on local hardware for real business workloads, and working out where that genuinely beats the cloud - and where it does not.AI INFRASTRUCTURE
ACTIVE→