Weekly digest · 2026-W27

June 29, 2026 – July 5, 2026

5 entries · 30 min total · Foundations & Protocols (5) · Industry Verticals (4) · Models & Frontier (1)

Entries

Day 105 · July 5, 2026The July 2026 Model Wave -- Under the HoodDay 99 marks a course-correction: after 22 industry verticals, this series returns to what it was built for -- teaching new AI technology in depth.
Day 104 · July 4, 2026Agentic AI in Construction & the Built EnvironmentConstruction is the last giant analogue industry -- roughly $13T of global output, productivity nearly flat for decades, and a project that still moves hand-to-hand through drawings, RFIs, submittals and change orders.
Day 103 · July 3, 2026Agentic AI in Logistics & Last-Mile DeliveryLogistics is the original multi-hop, multi-party relay -- freight quote to doorstep crosses brokers, carriers, warehouses, customs, and couriers -- and in 2026 that entire relay is collapsing into one orchestrated agent…
Day 102 · July 2, 2026Agentic AI in Agriculture & Food SystemsIn 2026 the farm itself becomes the agentic loop — agents sense (satellite, drone, soil IoT), decide (agronomy, irrigation, input optimisation) and act (autonomous tractors, laser weeders, irrigation valves) across the…
Day 101 · June 29, 2026Agentic AI in Travel & HospitalityTravel is the original multi-step, multi-party transaction — and that is exactly what makes it a natural agentic vertical.

Takeaways of the week

Re-route on evidence, not price sheets Re-run your 200-pair golden set across the new tiers (Luna/Sonnet 5/Terra/Fable 5) and compare cost-per-successful-task, not per-token price — Sonnet 5's tokenizer emits ~30% more tokens for the same text, so the $2/$10 promo (ends Aug 31) is cheaper than it looks on paper only if your tasks complete. Wire OTEL gen_ai spans before switching so the comparison is measured, not vibes. Day 105
Exploit the 1M-token default deliberately Sonnet 5's native 1M context changes the RAG-vs-context math for repo-scale and long-trajectory work — but context engineering (Day 39) still wins: structured retrieval plus a curated context beats stuffing a million tokens of noise, and at 30% token inflation, stuffing is also expensive. Use the window for what only it can do: whole-codebase reasoning, full multi-hour trajectory replays, and long-document synthesis with adaptive thinking deciding the effort. Day 105
Start with the document grind, not the excavator RFIs, submittals and schedule review are observable and reversible -- Gilbane proves the scale. Measure on RFI turnaround, schedule slips caught and rework avoided. Ground every answer in the drawing set; hallucinated spec = poured in concrete. Day 104
Gate every machine in hardware Scoped per-machine SPIFFE identity, geofenced dig envelopes with grade and speed caps, remote-supervisor takeover as the default, and a sub-second physical E-stop maintained as its own IEC 61508 safety case -- this becomes a CE certification requirement under the EU Machinery Regulation in January 2027. Day 104
1. Start with the visibility + exception loop, not the dispatch Deploy a control-tower agent (project44 pattern) to monitor, notify, and propose — observable and reversible. Measure on exception-handling labour reduced and time-to-re-route, not dashboards. Gate autonomous dispatch behind a proven quoting-agent stage first. Day 103
2. Make the promise trail the product Scope every agent's SPIFFE SVID to rates:read + quote:propose + notify:send; human owns every committed delivery window and every re-tender above a $ threshold. One OTEL->WORM trace per commitment satisfies EU AI Act Annex III + FMCSA AV audit + carrier-contract penalty defence simultaneously. Day 103
Start with the advisory loop, not the sprayer Conversational agronomy, scouting and disease detection are observable, reversible and proven at 2M-farmer scale. Ground every recommendation in label data and local regulation — a hallucinated dose is a lost crop or an unsafe residue. Measure on yield lift, input savings and water saved. Day 102
Gate every actuation in hardware Scoped per-machine identity: sense, diagnose and propose freely; actuate only inside a geofence with speed/rate caps and chemical whitelists. Default to remote-operator takeover (the Carbon ATK pattern) and engineer the sub-second E-stop as a physical relay with its own safety case — the EU Machinery Regulation makes this a certification requirement from January 2027. Day 102
Automate the relay, keep a human on the price and the complex re-book Search, itinerary building, routine booking, in-policy payment and simple re-booking are the proven starting points; let agents run them end to end. Keep the dynamic-price commit, open-ended spend, multi-carrier disruption and the exception with a human. Measure on look-to-book, cost-to-serve and time-to-rebook — not on dashboards. Day 101
Make payment authority and the reasoning trail the product Give every agent a scoped spend cap and an identity-verified checkout (the PayPal pattern), and wire OTEL→WORM once: the same evidence defends a chargeback, answers a DOT / EU261 refund claim and satisfies EU AI Act Article 50. Never let an agent invent a refund or compensation promise — ground every refund and charge in fare and route policy. Day 101

Viral and open-source picks

X Hosted MCP Server (api.x.com/mcp) Day 105
Bedrock Robotics / Bedrock Operator Day 104
Project44 Movement Intelligence Platform Day 103
LaserWeeder Day 102
Mindtrip -- the AI that books your flight in the chat (Sabre + PayPal) Day 101

Watch list

Day 100 — the milestone retrospective: '100 Days of Agentic AI'. We grade the series' biggest calls (the compression thesis, the Aug 2 countdown, the IPO race, the protocol stack), and distil the 10 technologies that mattered most in 100 days — plus what to… Day 105
Day 99: Agentic AI in Gaming & Interactive Entertainment -- agent-driven NPCs with persistent memory, AI game-dev copilots, and generative worlds, with content moderation and player safety as the binding constraint. Day 104
Day 98: Construction & the Built Environment — agents that plan, procure, and supervise building sites, with safety compliance and materials traceability as the binding constraints. Day 103
Day 97 — Agentic AI in Logistics & Last-Mile Delivery: agents that quote, route, dispatch and hand off freight across carriers, warehouses and the doorstep, with autonomous trucks and delivery robots as the actuation layer and delivery-promise liability as… Day 102
Day 96: Agentic AI in Agriculture & Food Systems — agents that sense, decide and act across the farm and the food chain (crop monitoring, irrigation and input optimisation, autonomous machinery, yield and supply forecasting), with the physical-world safety… Day 101