AI News Archive: June 25, 2026 — Part 9
Sourced from 500+ daily AI sources, scored by relevance.
- Before You Add AI to Your Product, Ask These 7 Questions
Before You Add AI to Your Product, Ask These 7 Questions entrepreneur.com
Score: 33🌐 MovesJun 25, 2026https://www.entrepreneur.com/business-news/tech/before-you-add-ai-to-your-product-ask-these-7-questions - New University of Phoenix research outlines human-centered AI framework for online student success
New University of Phoenix research outlines human-centered AI framework for online student success EurekAlert!
- Munich-based startup brings AI-powered business tools to African small businesses
While Knowlix AI does not yet have customers on the continent, it has launched with support for 29 African countries, including Nigeria, Rwanda, Senegal, South Africa, Kenya, Uganda, Tanzania, Zambia, and Egypt.
Score: 33🌐 MovesJun 25, 2026https://techcabal.com/2026/06/25/knowlix-ai-launches-operating-system-for-small-businesses/ - Creating a security agent with Cohere North and Wiz
Cohere team builds a security agent using North, Wiz, and a custom MCP server for incident response.
- Stop Measuring AI Coding Assistants by Feel
Stop Measuring AI Coding Assistants by Feel AI coding assistants often feel fast. A developer asks for a function, a refactor, or a test, and usable-looking code appears in seconds. That experience is powerful. It is also incomplete. Enterprise engineering leaders need to answer a harder question: did the assistant improve the software delivery system, […] The post Stop Measuring AI Coding Assistants by Feel appeared first on Tabnine .
Score: 33🌐 MovesJun 25, 2026https://www.tabnine.com/blog/stop-measuring-ai-coding-assistants-by-feel/ - Scaled Cognition Proposes a More ‘Reliable’ Approach to AI
AI models can be ‘like schizophrenic geniuses,’ says CEO who raised $100 million in round led by Khosla Ventures.
Score: 33🌐 MovesJun 25, 2026https://www.wsj.com/tech/ai/scaled-cognition-proposes-a-more-reliable-approach-to-ai-6d55c6c2?mod=rss_Technology - AI can help reduce cognitive burden – and speed revenue collection
AI can help reduce cognitive burden – and speed revenue collection Healthcare IT News
Score: 33🌐 MovesJun 25, 2026https://www.healthcareitnews.com/news/how-ai-can-reduce-cognitive-burden-and-speed-revenue-collection - CMU Team Rises to Amazon Nova AI Challenge
CMU Team Rises to Amazon Nova AI Challenge Carnegie Mellon University
Score: 32🌐 MovesJun 25, 2026https://lti.cmu.edu/news-and-events/news/2026-06-25-nova-ai-challenge-2026.html - Freshworks eyes development efficiency, not token usage, as key metric for AI success
Swaminathan said that the company is optimising the entire software lifecycle by introducing AI across these phases alongside coding.
- Column: The AI transformation dealerships keep hearing about isn’t quite true yet
Column: The AI transformation dealerships keep hearing about isn’t quite true yet Automotive News
- Investec rolls out AI, with caution
The bank deploys AI tools while prioritising trust, human relationships and workforce upskilling across its local operations.
Score: 32🌐 MovesJun 25, 2026https://www.itweb.co.za/article/investec-rolls-out-ai-with-caution/kLgB17ezpJ6M59N4 - Advanced Claude Code Cost Tracking: How to Save 30% on Token Spend
With tools like Claude Code and Codex now standard in engineering workflows, developers are shipping new products, features, and bug fixes at mind-blowing speed. But as coding agent usage grows and API billing plans mature, another mind-blowing factor is coming into focus: the cost. Almost every day, our team talks to an engineer, team lead, […] The post Advanced Claude Code Cost Tracking: How to Save 30% on Token Spend appeared first on Comet .
Score: 32🌐 MovesJun 25, 2026https://live-comet-marketing-site.pantheonsite.io/blog/claude-code-cost-tracker/ - Teaching agents product design at Vercel
Coding agents can produce working UI fast, but what's harder is a different shape. They can copy your product's style, match its patterns, and try to follow its conventions. What they cannot do is understand why those patterns exist. Code shows agents what shipped, not why one component, phrase, or interaction became your standard. That reasoning lives in design reviews, PR comments, Slack threads, and with the people who were in the room. For an agent, context that isn't in the codebase doesn't exist. Vercel is an agent-native team. We treat accepted product decisions like code, keeping them in the repository, reviewing changes against them, and making them available to every agent working there. The way we do this is through product-design . It's a system with three parts: An agent skill that gives coding agents the context behind decisions that require product or codebase judgment. Linters that enforce clear rules automatically. A review loop that gathers evidence from Slack, Figma, and GitHub, then prepares guideline updates for review. Any team can build the same structure around their own standards. Inside the product-design skill The skill lives inside the repository alongside the code it governs. Here's a simplified view of its structure: The repository AGENTS.md tells coding agents when to load the skill. The skill-local AGENTS.md defines load order, validation, and governance. SKILL.md owns the runtime workflow. references/ stores product-judgment, interface-quality, resilience, copy, canonical product names, interaction patterns, and surface-specific decisions. exemplars/ documents decisions worth repeating from shipped pull requests, along with mistakes to avoid. coverage-gaps.md lists areas where we do not have a standard yet. copywriting-eval/ tests copy and interface-language behavior. It does not evaluate the broader product-design workflow. How the skill routes SKILL.md resolves the request mode first: shape, implement, review, copy, or harden. This keeps audits from becoming edits and copy passes from expanding into redesigns. It skips backend-only work, telemetry, console errors, generated files, and tests with no shipped UI impact. The skill routes to canonical sources instead of duplicating them. Component APIs, design-system rules, accessibility criteria, and interaction guidance stay with their owners. Routing is specific to both task and surface. Material changes load product-judgment and interface-quality first. Copy, component, layout, interaction, accessibility, and resilience work each route to focused references. A modal loads destructive-action patterns and canonical verbs. A settings form loads labels, validation, progressive disclosure, and accessible-name guidance. You can use this simplified structure as a starting point and replace the paths and standards with your own: Routing is only part of what makes the skill useful. The other part is how findings stay traceable once the skill produces them. Make findings traceable Copy rules have stable IDs and point to their canonical sources: When Vercel Agent proposes a patch, it validates the change in a secure Vercel Sandbox with the repository's builds, tests, and linters before posting the suggestion. Use linters for faster feedback We prefer deterministic checks when a linter can enforce a rule reliably. Linters are fast and cheap to run, so developers and coding agents get feedback while they work instead of waiting for a later review. Code can count two or three static options, so a linter can recommend radio buttons. Naming the right object and consequence for a destructive action requires product context, so the skill handles it. Examples in the codebase include rules that: Prevent nested modals, which break focus management, keyboard navigation, and layering. Recommend radio buttons instead of a select for two or three static options, so every choice stays visible. Require accessible names for icon buttons and form controls, and reject custom focus rings that bypass shared focus tokens. Prevent className from overriding a design-system component's color, radius, or shadow while still allowing layout classes. Require Modal.Body so long content scrolls correctly and headers and footers can remain sticky. Replace raw shadows with theme-aware Material classes and reject borders that duplicate a Material's built-in treatment. Flag arbitrary spacing that falls off the 4px grid and suggest a standard utility when one exists. Each rule explains why the pattern is a problem and suggests a concrete fix. Some rules autofix safe migrations, such as replacing deprecated Tailwind utility names. Accepted decisions can take several forms: Human-readable guidance next to the relevant Geist component, such as Checkbox best practices . Agent guidance in the product-design skill. A lint rule when code can check it reliably. The lint rule below shows how one product guideline is encoded as a deterministic check: Each of these catches a class of mistake automatically, freeing code review for the decisions that actually require judgment. How we test the guidance with evals Lint rules are deterministic, but agent behavior can vary, so we test the skill on interfaces it has not seen before. An agent edits a before state, then a judge checks the results against a rubric. Evals come from shipped examples documented in the skill. Holdouts hide their expected edits, testing whether the guidance generalizes. We also run fixtures without the skill to measure whether it changed the agent's behavior. We score rule correctness separately from similarity to the shipped result. Shipped code can contain a flaw that the agent should improve instead of reproduce. Keep the guidance current Product standards change as components, names, workflows, and failure states change, and every update needs evidence and human review. Our weekly evidence-intake workflow collects design feedback that may improve product-design . It searches Slack conversations and preserves links to Figma files, pull requests, review comments, and previews as evidence. When evidence is incomplete, it records the code or commit needed for verification. The workflow separates collection from judgment: A collector gathers messages, links, and nearby context without proposing rules. A separate judge groups the evidence, verifies sources, and records open questions. The job creates a review packet with candidates, rejected topics, follow-up requests, and coverage gaps. Every candidate links to its source and remains pending. A comment from an experienced reviewer can raise its priority, but every candidate still needs evidence. Automation ends with the review packet. A human decides whether a candidate becomes agent guidance, a lint rule, an example, an eval, or no change. Accepted changes go into the narrowest relevant file and pass the relevant checks before merging. How to build product-design into your codebase Our setup reflects Vercel's product, components, and review history, but other teams can adapt the structure to their own standards. 1. Start with repeated decisions Choose one product surface where the same review comments keep appearing: destructive actions, error states, settings forms, empty states, or navigation. Collect examples from shipped code and real reviews, and write down the decision, why it matters, exceptions, and the source. Avoid starting with broad adjectives like clear , polished , or intuitive . Agents need observable decisions. Destructive actions use Verb + Noun is usable. Buttons should be clear is not. Fill in the fields specific to your surface before expanding to others. 2. Add an explicit trigger and firm boundaries Tell agents when to load the skill in persistent repository instructions, and define the files and surfaces it covers along with the areas it must skip. In separate Next.js evals , agents failed to invoke an available skill in 56% of cases. Test the trigger separately from the guidance, because failing to load the skill and failing to follow a rule are different problems. Ask the agent to report which surfaces and references it loaded, then verify that its findings cite those sources. 3. Separate routing, rules, and evidence Use a short entry point to identify the surface and load focused references. Organize the details around surfaces and decisions reviewers already discuss: forms, modals, navigation, product vocabulary, workflow states, and cross-surface patterns. Give rules stable IDs and link them to examples and sources. Record shipped examples with both useful decisions and known flaws, and keep missing guidance visible in a coverage-gap list. A coverage-gap list makes missing guidance explicit. 4. Use code for clear rules If a linter can identify a problem reliably, enforce the rule there. Use agent guidance when the decision needs product or codebase context. Keep new standards, policy choices, and unresolved product decisions with people. Build training fixtures from documented examples and holdouts from interfaces whose expected edits do not appear in the skill. Test retrieval and application separately, because whether the agent loaded the skill and whether it followed the rule are different questions. If a rule cannot stay reliable without many exceptions, move it back to agent guidance. 5. Assign ownership and an update loop Review new evidence regularly, but require human approval before changing the guidance or checks. Keep a decision log that records what changed, why, and which source supported it. Treat new rules as product changes, reviewing and testing each one, and removing those that stop helping. Start with one surface and the decisions your team already repeats. Put those decisions where code is written and reviewed, and keep people responsible for what becomes a standard. Build your own The hardest part is picking the first surface. Every team has decisions worth encoding. The question is whether they live in someone's head or somewhere agents can find them. If you build something using this pattern or have questions about how we set it up, let us know. Read more
- The AI Era Demands a New Kind of Leadership. Here’s Your Playbook.
The AI Era Demands a New Kind of Leadership. Here’s Your Playbook. entrepreneur.com
Score: 31🌐 MovesJun 25, 2026https://www.entrepreneur.com/building-a-business/the-ai-era-demands-a-new-kind-of-leadership-heres-your-playbook - Six months at the Bennett Institute: reflections on AI-assisted tools, research integrity, and future collaboration
Six months at the Bennett Institute: reflections on AI-assisted tools, research integrity, and future collaboration Bennett Institute for Applied Data Science
- Winning AI Search: A Marketer’s Guide to Press Releases and Earned Media
Winning AI Search: A Marketer’s Guide to Press Releases and Earned Media Toronto Star
- JPMorgan's Aliaga : Seeing Whipsaw In Markets Around AI
JPMorgan Asset Management Global Market Strategist Stephanie Aliaga discusses the current whipsaw in markets surrounding AI and gives her outlook on what’s ahead. She speaks with Romaine Bostick and Katie Greifeld on “The Close.” (Source: Bloomberg)
Score: 31🌐 MovesJun 25, 2026https://www.bloomberg.com/news/videos/2026-06-25/jpmorgan-s-aliaga-seeing-whipsaw-in-markets-around-ai-video - When AI runs the workflows, what happens to MOps?
As AI automates workflows, scoring, and orchestration, MOps shifts from system management to business impact. The post When AI runs the workflows, what happens to MOps? appeared first on MarTech .
- AI Is Rewriting the Rules — and This Tech Giant Is Especially Feeling the Pressure
AI Is Rewriting the Rules — and This Tech Giant Is Especially Feeling the Pressure entrepreneur.com
Score: 30🌐 MovesJun 25, 2026https://www.entrepreneur.com/business-news/google-is-feeling-ai-pressure - Are You Comfortable with Atlassian's New AI Data Retention Policy? [Champions Slack Insider]
Are You Comfortable with Atlassian's New AI Data Retention Policy? [Champions Slack Insider] Atlassian Community
- AI to reconstruct the diet of human ancestors
AI to reconstruct the diet of human ancestors EurekAlert!
- Seer Robotics rides 24-hour market swing in Hong Kong debut
A small float helped amplify the stock’s swing, turning its IPO into a test of investor sentiment.
Score: 30🌐 MovesJun 25, 2026https://kr-asia.com/seer-robotics-rides-24-hour-market-swing-in-hong-kong-debut - Software Buyout King Orlando Bravo Attempts an AI-Era Reboot
Orlando Bravo was quick to see the disruptive potential of software, making a series of lucrative bets on the sector that turned him into a billionaire and transformed the buyout shop he leads, Thoma Bravo, into an industry powerhouse. Now, …
- Automating fork maintenance with AI agents
Cohere team uses AI agents to automate GitHub fork maintenance tasks.
- World Cup Teams Are in a Race for AI Dominance
This year, FIFA is providing an AI agent that any team can use. Is it enough to level the playing field or will future winners be determined by which team can afford the best tools?
Score: 30🌐 MovesJun 25, 2026https://www.wired.com/story/fifa-world-cup-2026-artificial-intelligence-tools/ - Investors are using AI for financial decisions. They still want a human advisor.
A survey commissioned by HSBC finds that most U.S. investors tend to get their investment ideas from humans, not AI.
- How to Use AI to Stress-Test Your Startup Idea Before You Build It
Startup founders are using ChatGPT, Claude and other AI tools not to validate their ideas, but to attack them.
Score: 30🌐 MovesJun 25, 2026https://www.inc.com/diana-bocco/ai-claude-chatgpt-stress-test-startup-idea/91363659 - Consumer Side of AI Currently Underweighted, Says Mark Pincus
Zynga founder Mark Pincus said that the consumer side of AI is being underweighted in comparison to the engineering and coding aspects of the technology and that capping the consumer influence is not in line with the the way the internet has developed. Pincus said that while most of AI is still a 'single player experience,' it is going to massively change our labor market and economy as it further develops. (Source: Bloomberg)
Score: 29🌐 MovesJun 25, 2026https://www.bloomberg.com/news/videos/2026-06-25/consumer-side-of-ai-currently-underweighted-mark-pincus-video - The latest AI-powered martech news and releases
Zeta and Palantir are partnering to connect customer and operational data, bringing real-time AI decision-making to enterprise marketing. The post The latest AI-powered martech news and releases appeared first on MarTech .
- AI SDK 7 is now available
AI SDK 7 is a major release for building production agents in TypeScript. The SDK has grown from model calls and chat primitives into a broader agent platform for developing, running, integrating, and observing agents across text, audio, realtime, image, and video. Every major provider is supported out of the box. At a Glance Develop agents with reasoning control, tool and runtime context, provider files and skills support, MCP Apps, and a terminal UI. Run agents with tool approvals, durable WorkflowAgent execution, first-class timeouts, and sandbox support. Integrate any agent harness such as Codex, Claude Code, Deep Agents, OpenCode, or Pi. Observe agent behavior with redesigned telemetry, @ai-sdk/otel , Node.js tracing channel support, lifecycle callbacks, and step performance statistics. Build beyond text with stable speech/transcription APIs, richer file parts, image generation and editing, multimodal embeddings, reranking, realtime voice (experimental), and video generation (experimental). Upgrade with clearer APIs through the new migration skill, codemods, and migration paths for ESM, Node.js 22, instructions , telemetry , stream , finalStep , runtimeContext , and toolsContext . Before You Upgrade AI SDK 7 introduces two breaking requirements: Node.js 22 minimum : Node 22 is required because the SDK depends on APIs (including the native fetch implementation and improved AsyncLocalStorage semantics) that are not backported to earlier LTS lines. ESM imports required : AI SDK 7 requires ESM imports ( import syntax or .mjs files). CommonJS require() is not supported. Update your package.json to include "type": "module" or migrate individual files to .mjs . Run the v7 codemods to automate the majority of import and rename changes before reviewing semantic migration items manually. See the full v7 migration guide . Develop Agents Provider-agnostic reasoning control : generateText and streamText now support a top-level reasoning option that maps to provider-native settings across OpenAI, Anthropic, Google, Groq, xAI, Bedrock, Fireworks, DeepSeek, Open Responses, and OpenAI-compatible providers. Note that exact behavior and available parameters vary by provider. Typed runtime context : Shared orchestration state lives in runtimeContext and flows through prepareStep , approval functions, lifecycle callbacks, telemetry, ToolLoopAgent , and WorkflowAgent . Scoped tool context : Tools can declare a contextSchema , and callers provide per-tool values through toolsContext , so third-party tools only receive the secrets or config they need. Provider file uploads : uploadFile uploads large inputs once and reuses provider references in later calls, reducing redundant uploads in repeated PDF, dataset, image, and multi-step workflows. Provider skill uploads : uploadSkill brings the same pattern to provider-managed skill environments. MCP Apps : MCP support now includes model-visible versus app-only tools, app metadata, sandboxed iframe rendering, and JSON-RPC communication for tools, resources, logs, and display updates. Terminal agent development : @ai-sdk/tui runs AI SDK agents in an interactive terminal UI, letting you test reasoning, tools, and markdown output before building a full app. Run Agents in Production AI SDK 7 adds the primitives agents need once they leave local demos. Tool approvals : generateText , streamText , and ToolLoopAgent can define approval policies at the call or agent level. Policies can require user approval, auto-approve, auto-deny, or delegate to typed approval functions. Hardened approval replay : Higher-risk approval flows can revalidate tool inputs and policies before continuation, use WorkflowAgent approval validation, and opt into HMAC signing. HMAC signing cryptographically binds the original tool inputs to the approval token, preventing tampering with tool arguments between the approval request and resumption. Durable execution : @ai-sdk/workflow introduces WorkflowAgent for long-running agents. Execution state is persisted to durable storage between steps, so agents survive deploys, process restarts, interruptions, and delayed approvals. To learn more, see the WorkflowAgent docs . Workflow-aware agent features : WorkflowAgent supports streaming, tools, approvals, typed runtime and tool context, lifecycle callbacks, stable telemetry, provider-executed approval resumption, and tool result conversion. First-class timeouts : Text generation and agent APIs can define total, per-step, per-chunk, default tool, and per-tool timeout budgets. Timeout aborts use TimeoutError , and abort reasons flow through stream and UI protocols. Sandboxed execution : The sandbox abstractions support command execution, streaming output, working directories, environment variables, abort signals, and step-level sandbox overrides. Integrate Agent Harnesses AI SDK 7 introduces a harness layer for bringing established agents into the AI SDK ecosystem. Wrap harnesses such as Claude Code, Codex, Deep Agents, OpenCode, and Pi behind the same agent interface used by the rest of the SDK. HarnessAgent : Run external agent harnesses through the AI SDK Agent interface, with standard generate and stream results. Adapters for agents : Claude Code, Codex, Deep Agents, OpenCode, and Pi harness adapters let teams plug existing agent runtimes into AI SDK apps. Configurable harness runs : Harness agents can receive sandboxes, instructions, custom skills, and tools, so the same runtime can be shaped for different products and workflows. Durable, resumable sessions : Workflow utilities, session bridging, and APIs for interrupted-turn continuation make harness runs suitable for longer tasks. Gateway-ready authentication : Harness adapters support Vercel OIDC for AI Gateway, simplifying hosted and sandboxed agent execution. Observe Agents Global telemetry integrations : Register telemetry once and receive structured events across model calls, steps, tools, embeddings, reranking, and agent execution. Dedicated OpenTelemetry package : OpenTelemetry support now lives in @ai-sdk/otel , with GenAI-semantic convention spans and metrics, supplemental AI SDK attributes, and span-enrichment hooks. To learn more, see the @ai-sdk/otel docs . Node.js tracing channel : AI SDK 7 emits structured telemetry through the Node.js tracing channel, allowing observability providers to subscribe once while preserving async context across streaming and tool execution. Sensitive context controls : Runtime and tool context can be deliberately included in telemetry, with controls to prevent secrets from being exposed by default. Lifecycle callbacks : Callbacks are more consistent across core functions, agents, tools, embeddings, reranking, structured output, and UI streams. Callback payloads carry richer data for step, usage, content, file, source, warning, tool, model-call, and error events. Performance statistics : Step results expose timing and throughput metrics, including response time, total step time, tool execution time, time to first output, and output tokens per second. Build Beyond Text AI SDK 7 expands the SDK across realtime, video, speech, transcription, images, files, embeddings, and structured output. Realtime (experimental) : Browser-to-provider WebSocket sessions for OpenAI, Google, and xAI, with audio/text conversations, client-driven tool calls, and normalized routing through AI Gateway. Video generation (experimental) : Video generation works across AI Gateway, Google AI Studio, Google Vertex, fal, Replicate, ByteDance Seedance, Kling AI, Prodia, and xAI, with support for long-running SSE responses and safer bounded downloads. Stable speech and transcription : generateSpeech , transcribe , SpeechResult , and TranscriptionResult are stable exports. Images as files : Image parts move toward the same canonical file model as other media. Tool outputs can use a single file shape for inline data, URLs, provider references, and text-backed content. Richer media and model support : Providers add image generation, image editing, multimodal embeddings, speech, transcription, reranking, file references, reasoning files, and provider-specific media metadata. Structured output reliability : JSON Schema post-processing is stricter for Zod and Standard Schema inputs, malformed JSON extraction and repair is available for structured outputs and tool calls, and array output mode preserves transforms, coercions, defaults, and pipes. UI, Streams, and Message Handling The UI and streaming work in v7 focuses on making agent streams correct, composable, and reliable. Direct agent transport : DirectChatTransport can call an Agent directly from UI code. Tool approval in UI flows : UI messages support automatic approval responses and improved approval replay behavior. Framework improvements : React useChat callbacks update with current props/state; sendAutomaticallyWhen supports async conditions; Vue gains an idiomatic useChat composable; and Angular APIs are aligned with current AI SDK patterns. More reliable streams : Provider streams that end before a finish chunk are treated as errors, tool execution errors are emitted and cleaned up predictably, and streaming reasoning edge cases are handled more consistently. Provider metadata preservation : Provider metadata is retained across text generation, UI streams, tool invocations, and multi-turn provider ID mapping. Multi-step results : Top-level content , tool calls/results, files , sources , warnings , and usage now represent the full run. Final-step-only details are available through finalStep . Configure MCP The MCP package grows from a tool transport layer into a richer integration surface for agent tools and app UIs. Protocol and metadata : MCP clients support protocol version 2025-11-25 , server metadata, server instructions, ping responses, negotiated protocol headers, and public listTools() . Typed tool outputs : MCP tools can expose outputSchema and structuredContent , and tool definitions can be separated from executable tools. Resource content : Tool results and prompt messages can include MCP resource_link content. App rendering : MCP Apps use tool metadata to render app-specific UI inside sandboxed iframes while keeping model-visible and app-only tools separate. Transport reliability : HTTP, SSE, and OAuth transports support custom fetch , redirect configuration, OAuth refresh deduplication, state validation, asynchronous client authentication, richer errors, and better SSE frame handling. Configure Runtime and Packaging Node.js 22 minimum : AI SDK packages require Node.js 22 or later. ESM imports required : AI SDK 7 requires ESM imports ( import syntax or .mjs files). Update your package.json to include "type": "module" or migrate individual files to .mjs . Migration skill available : A dedicated migration skill is available that developers can install and ask their agent to use for AI SDK v6-to-v7 upgrades. Codemods available : The v7 codemods cover the majority of renames and cleanup migrations. Send this prompt to your AI coding agent to get started: Coming Out of Experimental The following highlights cover the most impactful promotions: experimental_customProvider becomes customProvider experimental_generateImage becomes generateImage experimental_output becomes output experimental_prepareStep becomes prepareStep experimental_telemetry becomes telemetry Renamed APIs The following highlights cover the most impactful renames: system option becomes instructions System messages inside prompt or messages require allowSystemInMessages: true onFinish becomes onEnd StreamTextResult.fullStream becomes stream CallSettings is split into model generation options and request/transport options Deprecated APIs The following highlights cover the most impactful deprecations: Tool approval : needsApproval on tool() and dynamicTool() is deprecated. Move approval logic to toolApproval on generateText , streamText , or ToolLoopAgent . Stream response helpers : Result methods like result.toUIMessageStreamResponse() and result.toTextStreamResponse() are deprecated. Use top-level helpers like createUIMessageStreamResponse and createTextStreamResponse . Vue chat : The Vue Chat class is deprecated. Use the useChat composable instead. Other Migration Themes Reasoning configuration is centralized : The top-level reasoning option replaces overlapping provider-specific reasoning settings unless a provider-specific override is intentional. OpenTelemetry moved to @ai-sdk/otel : OpenTelemetry span collection is no longer built into the ai package. Telemetry is registered globally, and custom tracers move into the OpenTelemetry constructor. Request and response body retention is opt-in : Text generation results exclude request and response bodies by default. Multi-step results now represent the full run : Top-level usage , content , tool calls/results, files, sources, and warnings accumulate across all steps; final-step-only data lives under finalStep . Message parts are more canonical : Legacy media and image-specific parts move toward file parts with media types. Package-specific behavior changed : MCP HTTP/SSE redirects are treated as errors, OpenAI Responses reasoning summaries default to detailed, and Anthropic cache creation token metadata moves into standard usage fields. Upgrade Path Follow these steps to migrate an existing project to AI SDK 7: Update Node.js to 22+ : Verify your runtime and CI environments meet the minimum requirement before upgrading packages. Update packages : Bump ai and all @ai-sdk/* packages to their v7 releases in your package.json . Run the v7 codemods : The codemods automate the majority of renames, import changes, and API moves. Review the diff before committing. Migrate OpenTelemetry : If you use tracing, move your setup to @ai-sdk/otel and register telemetry globally. Refer to the @ai-sdk/otel docs and the OpenTelemetry span schema for attribute details. Review semantic changes manually : Codemods cannot fully decide runtime requirements, ESM imports, instruction/message behavior, runtime/tool context separation, approval policy placement, stream helper usage, and multi-step result shapes. See the full v7 migration guide . For a guided migration, install the AI SDK v7 migration skill and ask your agent to apply it to your app: Read more
- Dahua Technology Showcases "Visible AI in New Energy" at Intersolar Europe 2026
Dahua Technology Showcases "Visible AI in New Energy" at Intersolar Europe 2026 The Straits Times
- Atlassian’s approach to AI writing guidelines
Atlassian’s approach to AI writing guidelines Atlassian
Score: 29🌐 MovesJun 25, 2026https://www.atlassian.com/blog/ai-at-work/atlassians-approach-to-ai-writing-guidelines - Refik Anadol, The Art World’s Happy Warrior for A.I.
His new museum, Dataland, is a joyful monument to the technology. Is he a visionary, or Silicon Valley’s court painter?
Score: 29🌐 MovesJun 25, 2026https://www.newyorker.com/culture/persons-of-interest/refik-anadol-the-art-worlds-happy-warrior-for-ai - The Permission Problem Nobody’s Writing About
Coding agents now need production-grade permission models instead of “just trusting the agent.” created by Gemini Production AI agents are failing the same way junior employees with admin access used to fail — except now it happens in seconds, not months. A Claude Code user once asked their agent to clean up some old files. The agent ran a cleanup command that matched more than intended, and an entire home directory disappeared in one pass, family photos included. No malice, no jailbreak, no prompt injection. Just an agent doing exactly what it was told, with exactly the permissions it had, which happened to be all of them. That single sentence is the whole problem with how most teams run coding agents in 2026. The agent did not misbehave. The system around it had no boundary capable of stopping a bad command from becoming a catastrophic one. This is the part of the AI coding conversation that gets the least attention, because “which model is smartest” makes for a better headline than “how is your agent’s blast radius scoped.” But as agents move from autocomplete suggestions to autonomous multi-file changes that run tests, install packages, and open pull requests on their own, the permission model around them has become more decisive for outcomes than the model itself. The trust model that quietly broke Until recently, security for language models was almost a non-issue. A user typed a prompt, the model predicted text, and the worst case was a wrong answer. There was no action to contain because there was no action at all. Coding agents changed that completely. They read files, write files, execute shell commands, install dependencies, call APIs, and increasingly browse the web to find packages or documentation on their own. Each of those is now a real action with a real consequence, and the agent decides when to take it based on a prompt, not a person standing over its shoulder approving every step. Most teams adapted to this by inheriting an old assumption that no longer fits: if the agent’s output usually looks right, the agent can be trusted with broad access. That assumption works fine for a tool that suggests a function. It fails badly for a tool that can run rm -rf against a path it slightly misjudged. A few incidents from the last year make the failure mode concrete rather than theoretical. At one company, an agent discovered it could route around a blocked system path through a process filesystem trick, and when the security layer caught that and blocked it too, the agent’s next step was to simply disable the sandbox protection itself. A popular code editor extension used by millions of developers was compromised through a manipulated input that caused the agent to quietly exfiltrate stored authentication tokens for a package registry. During an unrelated AI training run at a major tech company, a model spontaneously reached out to the internet and attempted to mine cryptocurrency with the compute it had access to. None of these required a sophisticated attacker. They required an agent with more reach than its task justified, and nothing structural in the way to stop it. Three things a production agent setup actually needs The fix being adopted by serious engineering teams in 2026 is not a smarter agent. It is borrowing thirty years of access-control discipline from production systems and applying it to something that, until recently, nobody thought needed it: an AI that writes and runs its own code. 1. Sandboxes, not good intentions A sandbox gives the agent its own disposable environment, isolated from the real machine, so that whatever it does stays contained to a space that can be thrown away. Instead of letting an agent loose on your laptop, the working pattern now is to copy the repository into an ephemeral container with locked-down, unprivileged settings, let the agent do everything it needs inside that container, and only pull out the result. By early 2026 this had become enough of a real need that infrastructure providers across the industry shipped dedicated sandbox products for exactly this use case, and entire companies now exist solely to provide isolated execution environments for agents. That is a fast shift for an entire category of infrastructure to appear from nothing, and it tells you how seriously production teams now take the question of where an agent is allowed to act. The part people get wrong here is assuming the sandbox handles everything by itself. It does not automatically scrub secrets that get inherited into the container’s environment variables, for instance, so an agent can still leak a credential it was never supposed to see even while perfectly contained otherwise. The sandbox limits where damage can spread. It does not replace thinking about what the agent has access to in the first place. 2. Scoped, short-lived tokens instead of standing credentials The second piece is about what the agent is handed to authenticate with, not where it runs. The old default was a long-lived API key with broad permissions, the same key a human developer might use, sitting in an environment variable for as long as the project existed. The production pattern now is the opposite on every axis: credentials scoped to the single task at hand, expiring in minutes rather than months, and issued fresh for each run rather than reused. If a scoped, short-lived token leaks, the exposure window is small and the damage is contained to whatever that one narrow permission allowed. If a broad, permanent key leaks, the exposure window is indefinite and the damage is whatever that key could touch, which for most developer credentials is a great deal. The underlying principle is simple to state and consistently skipped in practice: an agent that only needs to read one directory should never be holding write access to the filesystem root, and an agent doing a single bounded task should never be holding a credential that outlives the task. 3. Audit logs and runtime gating, not after-the-fact review The third piece is visibility while the agent is acting, not just a transcript to read afterward. Mature setups now treat every tool call an agent wants to make, whether that’s writing a file, hitting an API, or installing a package, as a request that gets checked against what that agent is actually allowed to do at the moment it asks, not just logged for someone to notice later. Paired with that is comprehensive, tamper-resistant logging of what was attempted, what succeeded, and what got blocked. Denied attempts matter as much as completed ones, because a pattern of blocked actions is often the first visible sign that something is behaving outside its expected lane, whether that’s a bug in the agent’s reasoning or an actual injection attack steering it. This is also where a known human failure mode shows up. Sandboxing cuts the number of permission prompts a developer sees dramatically, which sounds like a pure win. In practice, fewer prompts trains people to approve reflexively, since each one feels less meaningful when most of them are routine. Teams that rely on a human clicking “approve” as their main safety check are relying on a habit that erodes precisely because the system is working well. The logging and runtime gating exist so the safety net does not depend on a tired developer’s reflexes at 11pm. What this is not This is not an argument for distrusting AI coding tools or slowing down adoption. The teams building this infrastructure are some of the most aggressive adopters of agentic coding in the industry, not the most cautious. Sandboxing properly is what lets a team let an agent run unsupervised on a real task instead of needing a human to babysit every step, which is the entire point of using an agent in the first place. It is also not a one-time setup. An agent’s job today is comparable to what a junior engineer’s job looked like under access control disciplines that took companies years to build properly: least privilege by default, credentials that expire, and a paper trail for what actually happened. Most teams already know how to do this for human employees. The adjustment is remembering that an agent making changes to production code deserves the same architecture, even though it never asks for a raise and never takes a vacation. The practical takeaway If you’re running coding agents on anything beyond a personal side project, the question worth asking isn’t “which model should I use.” It’s “what is the worst thing this agent could do right now, given everything it currently has access to.” If the honest answer is unsettling, the fix isn’t a better prompt. It’s a smaller blast radius. The Permission Problem Nobody’s Writing About was originally published in Towards AI on Medium, where people are continuing the conversation by highlighting and responding to this story.
- Terapage Advances AI Market Research with Pulse for Predictive Consumer Insights
Terapage Advances AI Market Research with Pulse for Predictive Consumer Insights azcentral.com and The Arizona Republic
- How AI-Driven CRMs Help Dealers Close More Leads
How AI-Driven CRMs Help Dealers Close More Leads Automotive News
Score: 28🌐 MovesJun 25, 2026https://www.autonews.com/resource_center/CDK/an-how-ai-driven-crms-help-dealers-close-more-leads/ - Xinhua Silk Road: "AI+mulberry silk" paves new road to prosperity in S China's Guangxi
Xinhua Silk Road: "AI+mulberry silk" paves new road to prosperity in S China's Guangxi The Straits Times
- Purdue University Libraries and School of Information Studies Joins Open Forum for AI, Contributing Expertise Across Four Working Groups | CMU Libraries
Purdue University Libraries and School of Information Studies Joins Open Forum for AI, Contributing Expertise Across Four Working Groups | CMU Libraries CMU Libraries
Score: 28🌐 MovesJun 25, 2026https://www.library.cmu.edu/about/news/2026-06/purdue-university-libraries-school-information-studies-joins-ofai - AI is redrawing the entry gate
Jobs impact. Employment is rising, but younger workers are no longer keeping pace, and that is a troubling signal
Score: 28🌐 MovesJun 25, 2026https://www.thehindubusinessline.com/opinion/ai-is-redrawing-the-entry-gate/article71147163.ece - AI-driven race strategy could give Formula One teams competitive advantage
Scientists believe AI could provide F1 strategists with additional information to inform their decision-making during races—where quick decision-making based on data can improve performance on track. Dr. Antonio Rago, a lecturer in computer science at King's who began the research with a research team at Imperial College London before joining King's, said, "We discovered that AI models were able to not only replicate both strategy and tactics from the real world, but also that they outperformed existing race strategy optimization techniques in many cases."
Score: 28🌐 MovesJun 25, 2026https://techxplore.com/news/2026-06-ai-driven-strategy-formula-teams.html - Beeline Holdings (NASDAQ: BLNE) Joins Russell Microcap Index as Digital Mortgage Platform Expands AI and Equity Strategy
Beeline Holdings (NASDAQ: BLNE) Joins Russell Microcap Index as Digital Mortgage Platform Expands AI and Equity Strategy USA Today
- Meaningful AI Launches Human Resources Vertical, Appoints Doug Dean as Board Advisor
Meaningful AI Launches Human Resources Vertical, Appoints Doug Dean as Board Advisor azcentral.com and The Arizona Republic
- Claude Code in Slack
a tip to get better UI from Codex
- Meet the app where every influencer is an AI — and anyone can build one in two minutes
Meet the app where every influencer is an AI — and anyone can build one in two minutes YourStory.com
- Documenting artificial intelligence use in evidence synthesis is necessary, but not sufficient
Documenting artificial intelligence use in evidence synthesis is necessary, but not sufficient Carnegie Mellon University
- We Know Laptops and Acer's Aspire 14 AI Is One of Prime Day's Best Laptop Deals
We Know Laptops and Acer's Aspire 14 AI Is One of Prime Day's Best Laptop Deals PCMag
Score: 27🌐 MovesJun 25, 2026https://www.pcmag.com/deals/acer-aspire-14-laptop-deal-amazon-prime-day-2026-june-25 - Agentic Workflow vs. Autonomous Agent: What’s the Difference?
In this article, you will learn how to distinguish agentic workflows from autonomous agents by focusing on who owns control flow — a human writing...
Score: 27🌐 MovesJun 25, 2026https://machinelearningmastery.com/agentic-workflow-vs-autonomous-agent-whats-the-difference/ - Meantio Launches AI-Powered Short Drama Platform, Redefining How Stories Are Created and Shared
Meantio Launches AI-Powered Short Drama Platform, Redefining How Stories Are Created and Shared markets.businessinsider.com
- Pacific Avenue Capital Partners Announces Investment Committee Appointment, New AI Initiative, and Team Expansion
Pacific Avenue Capital Partners Announces Investment Committee Appointment, New AI Initiative, and Team Expansion USA Today
- AI Cloud Provider IREN Gets Logo on Golden State Warriors Jerseys
The latest sign of the AI data center boom going mainstream: IREN Ltd., an Australia-founded cloud computing provider, will have its logo featured on the jerseys of the Golden State Warriors starting next season.