500 IU credits, free until the final whistle
Construction AI Brief
Google I/O 2026 kicks off this evening at 18:00 BST. Anthropic published the canonical 'Explore → Plan → Code → Commit' methodology. Procore's Q1 results put agentic AI in the platform, not the roadmap. And someone leaked the system prompts of 32 coding agents to GitHub.

Today’s context: This brief covers the latest movements in AI tooling, adoption, and signals for construction teams. Read on for what matters and what to focus on.
The main Google I/O keynote runs tonight at the Shoreline Amphitheatre from 18:00 BST (developer keynote follows at 21:30 BST), with the conference continuing through Wednesday. Confirmed agenda topics include Gemini, Android 17, Chrome, Cloud and "more". Expected: formal unveiling of Gemini 3.5 Flash and Pro (leaked checkpoints have circulated for a week with credible benchmark results), VEO 4 / "Omni" video model territory clarification, deeper Workspace agent integration (leaked screenshots last week), and Android XR for smart glasses ahead of Samsung's Galaxy Glasses at Unpacked in July.
For construction technology leaders, the practical advice is unchanged from yesterday: hold non-urgent AI commitments until Wednesday morning. The shape of Google's offering for the next 12 months will be substantially clearer by then, and several of the leaked items would change the right answer on video, multimodal and Android-tablet site deployment choices.
Why it matters
Tonight's announcements will reset assumptions for Gemini-leaning AI roadmaps. Ask any vendor in your active pipeline to refresh their roadmap presentation by end of week.
Procore reported Q1 2026 revenue of $359m (up 16 per cent year-on-year) with a 17 per cent non-GAAP operating margin. CEO Ajei Gopal used the call to position agentic AI as embedded platform capability - "autonomous AI-driven software agents embedded in Procore's platform to execute construction workflow tasks and decision-making, leveraging proprietary construction-specific data." The company expects increased sales of its AI offerings by Q3 FY2026, and ships a wave of platform updates today including a Planning feature beta with resource-specific Gantt assignments, and a redesigned submittal experience with automated date calculations.
For UK contractors and consultants whose clients are on Procore, this changes the buying conversation. The platform AI features are now part of the existing licence rather than a future add-on. Third-party AI tools that integrate via the Procore API will need to position themselves on either differentiated capability or specific UK-regulatory fit.
Why it matters
If you sell construction software around or into Procore-using clients, expect the "do we need a separate AI tool?" question by end of summer. Be ready with the answer.
Anthropic's official Claude Code documentation now formalises the recommended four-phase methodology: Explore (Claude reads files, searches patterns, builds understanding - no modifications); Plan (Claude produces a detailed plan, opened in your editor for direct edit before execution); Code (Claude implements against the plan, with tests run and failures fixed); Commit (Claude commits with a descriptive message and opens a PR). The argument - backed by Anthropic and the Claude Code team - is that phases 1 and 2 are the cheapest in tokens and the most valuable in outcome.
This is the part to take away even if your firm does not use Claude Code: the methodology is portable to any agentic coding tool, and it gives engineering and digital teams a shared vocabulary for what disciplined AI-pair-programming actually looks like. The temptation to skip Explore and Plan is exactly where AI-assisted code review tends to fail.
Why it matters
Adopt one documented agent methodology and apply it consistently. The pattern matters more than the tool - and the pattern is now publicly endorsed by the vendor most likely to be on your engineering bench.
A clear sub-pattern from the past week's tooling releases: developers now routinely run five or ten agents in parallel, and standard terminal multiplexers are not designed for it. Herdr (released this week) is one example of the new category - a terminal multiplexer specifically for AI coding agents, with split panes, scrollback per agent, and session attach/detach for asynchronous handoff. It sits alongside Claude Code's Agent View, Cursor's Background Agents and Microsoft Agent 365 in what is becoming a layered supervision stack.
A GitHub repository maintained by Lucas Valbuena (and the EliFuzz/awesome-system-prompts mirror) collects the leaked system prompts and tool schemas of more than 28-32 production AI coding agents: Cursor, Windsurf, Claude Code, Devin, v0, Lovable, Replit, Manus, Augment Code and many others. The repo has crossed 137k stars and 34.2k forks. Crucially, the JSON tool schemas are included - not just the prompt text - so what each tool has been permitted to do is visible alongside how it is told to behave.
This is the most useful free reference now available for anyone designing their own AI agent. Patterns to study: guardrail framing, tool-use protocols, refusal templates, file-system permission scopes, web-fetch restrictions, and how leading vendors handle the "agent claims success but silently failed" failure mode (the topic of Tejas Kumar's IBM "Harnesses in AI" talk this week).
Why it matters
Before building or buying an agent for project-critical workflows, read several of these prompts back-to-back. The differences in tool permissions are where security risk actually lives.
50 free Intelligence Units. Set up your first project in under 20 minutes. No credit card needed.
Get 50 free Intelligence UnitsDaily practical AI insight for construction teams. What changed, why it matters, and what to ignore.
50 free Intelligence Units - automate your programme admin
We help construction teams turn AI into useful work, not noise. Understanding what’s changing in AI is the first step. Making it work on-site is the real difference.
The Building Safety Regulator's latest Gateway 2 figures, covering the 12 weeks to 28 June, show approvals up to 77% and external remediation running at 85%, though internal higher-risk works still crawl at a 28-week median. The Bank for International Settlements, given fresh airing by Bloomberg on 14 July, warns the AI capex boom underneath the data centre pipeline is financed in ways that could turn boom to bust. And ServiceTitan's 2026 report says the share of contractors seeing measurable results from AI has doubled in a year to 38%.
Found this useful? Share it.
For construction software teams running multiple coding agents (or for IT teams managing operational agents across procurement, document automation and project controls), this is the supervision layer your insurer and audit team will eventually ask about. Standardise early.
Why it matters
Treat agent supervision as a deliberate architecture decision, not a tool choice. Pick a control surface, document it, and apply it consistently across teams.
McLaren Construction is deploying FieldAI-powered robot dogs across its UK sites, announced on 6 July, in what FieldAI calls its first UK deployment, after a trial on the Passivhaus refurbishment of the LSE's 35 Lincoln's Inn Fields building. And Newforma pushed a Microsoft Teams connector into Konekt on 13 July, pulling the messages, edits and deletions that used to vanish into the audit trail. Two ends of the same job: capturing the record of what was built, and the record of what was said.
NG Bailey, one of the UK's biggest engineering and services contractors, is creating a chief AI officer role as part of its 2030 strategy, moving AI from a pilot to a governed board responsibility. The Cyber Security and Resilience Bill moving through Parliament reclassifies data centres as essential services, pulling contractors and specialist subcontractors into a more cyber-conscious procurement environment. And Google's Gemini 3.5 Pro, with a reported two-million-token context window, is being lined up for a 17 July release, though as of early July it is leaks rather than an official launch.