AI Coding Live News

Vercel Security Review Enters Public Beta: Vulnerability Review on Every GitHub Push, One-Click Fixes with Vercel Agent

On November 3 (US Pacific time), Vercel launched Security Review in public beta. It is a new Vercel Agent capability alongside Code Review and Investigation: once enabled, every push to connected GitHub repositories triggers a diff-only vulnerability review that finishes in seconds. Findings land in the Security dashboard, PR comments and the CLI, and can be fixed with one click by Vercel Agent or pulled into your own coding agent via vercel security vulnerabilities. It is available to Pro and Enterprise teams, and reviews are free until November 10.

Vercel Security Review Enters Public Beta: Vulnerability Review on Every GitHub Push, One-Click Fixes with Vercel Agent

Key Takeaways

  • Trigger: every GitHub push (including direct pushes to production) is reviewed automatically; only the diff is scanned, which Vercel says finishes in seconds, so it can run on every preview and production deployment
  • Beyond pattern matching: the agent traces how changed code is reached, checks existing protections and rechecks each finding, which Vercel says catches logic flaws such as missing authorization checks
  • Teams can write security policies in plain language, scoped to projects or the whole team, and manage them with vercel security policy
  • Pricing: Vercel Agent rate, model tokens at provider cost with no markup, plus $0.25 per million tokens; reviews are free until November 10, 2026, while Agent fixes are billed
  • Availability: public beta for Pro and Enterprise teams; Vercel has not published detection-rate or false-positive benchmarks
Read full story

X discussion: Greg Isenberg says SaaS is becoming free, give away the CRM and dashboard and charge for the agent that does the work

On Oct 27, Greg Isenberg (@gregisenberg, about 752K followers), founder and CEO of Late Checkout, posted on X: "saas is becoming free: give away the crm, give away the dashboard, give away the app, and charge for the agent that does the work." Within about seven hours the post had about 109K views, 1,526 likes, 277 replies and 37 quotes, with many founders debating whether per-seat pricing can really give way to pricing for the work an agent completes. This is a discussion of an opinion, not a pricing announcement from any company.

X discussion: Greg Isenberg says SaaS is becoming free, give away the CRM and dashboard and charge for the agent that does the work

Key Takeaways

  • Engagement (as of 2026-10-28 03:10 UTC, public X API data): about 109K views, 1,526 likes, 746 bookmarks, 277 replies, 37 quotes
  • The claim: the CRM, dashboard and app become free, and the paid product is the AI agent that does the work for the user
  • The most common pushback: charging for "work" means defining in writing what done means, who checks it, and a monthly cap, or it cannot be billed
  • Another camp says companies will keep paying for the system of record, while SaaS vendors give away MCP access so outside agents can read and write
  • This is a founder opinion under discussion, not a pricing change by any company
Read full story
Linked Models & Agents:

Grok Bot can now build reports, memos and dashboards as pages you edit together or let it keep up to date

On Oct 21 the official Grok Bot account announced that Bots can now build reports, memos and dashboards as pages that users edit together with the Bot or have it keep up to date. Pages already supported renaming, find-in-page and shared PDF download since 0.70.2; this extends them into deliverable reports and dashboards.

Grok Bot can now build reports, memos and dashboards as pages you edit together or let it keep up to date

Key Takeaways

  • New: ask a Bot for a page and it builds a report, memo or dashboard
  • Two modes: edit it together with the Bot, or let the Bot keep it up to date
  • Page basics (0.70.2 official changelog): Cmd/Ctrl+F find in page, rename from the title, shared pages with Download (PDF) and Share
  • The official post drew about 445K views and about 4,252 likes within roughly 2.5 hours (public X metrics)
  • No version number or plan limits have been published yet
Read full story
Linked Models & Agents:

Cursor Cloud Agents Can Now Build and Share Interactive Canvases for Live Dashboards and Technical Reports

Cursor (@cursor_ai) announced that Cursor Cloud Agents can now build Interactive Canvases. While a cloud agent works through a repository, developers can ask it to construct interactive dashboards or visual technical reports and share the finished canvas directly with their team via a single link.

Cursor Cloud Agents Can Now Build and Share Interactive Canvases for Live Dashboards and Technical Reports

Key Takeaways

  • Interactive Canvases in Cursor Cloud Agents: allows developers to request live interactive dashboards and visual reports while the agent works
  • Instant team link sharing: finished canvases can be shared with teammates as a direct URL for collaborative review
  • Clean repository workflow: keeps diagnostic visualizations and interactive PR walkthroughs in cloud canvases without polluting git history
Read full story
ADSponsored

Claude Dashboards and Claude Motion enter beta; Claude Docs, Slides and Design leave beta on every plan including Free

On 2026-10-08 Anthropic launched Claude Dashboards (paid-plan beta; BigQuery, Snowflake, Databricks, Salesforce and more, with the SQL behind every chart) and Claude Motion (Team/Enterprise beta; code-built, editable animations with no video model, MP4 export). Docs, Slides, and Design left beta on all plans including Free, with 45M+ created so far.

Claude Dashboards and Claude Motion enter beta; Claude Docs, Slides and Design leave beta on every plan including Free

Key Takeaways

  • Official: Dashboards & Motion announcement, 2026-10-08
  • Dashboards: paid-plan beta; Redshift/BigQuery/ClickHouse/Databricks/Snowflake/Salesforce; every number shows its query
  • Motion: Team/Enterprise beta; code-built, no video generation model, MP4 export
  • Docs/Slides/Design out of beta on all plans incl. Free; 45M+ created; Artifacts support CMEK
  • Dates: Enterprise default-on Oct 15; standalone claude.ai/design closes Dec 14; no accuracy benchmarks published
Read full story
Linked Models & Agents:

Codex CLI 0.156: optional /tui fullscreen, voice on by default, /usage dashboard; 0.156.1 adds GPT-6 Sol/Luna

OpenAI shipped Codex CLI rust-v0.156.0 and hotfix 0.156.1 on 2026-09-22/23 (@openai/codex). 0.156.0 adds optional /tui fullscreen, voice default-on, /usage, worktrees on by default, themes/Mermaid, plus sandbox fixes. 0.156.1 adds GPT-6 Sol/Luna to the picker and recommends Luna on rate-limit switches.

Key Takeaways

  • Install @openai/[email protected] (0.156.0, 0.156.1)
  • /tui fullscreen; voice default-on (F8); /usage dashboard
  • Worktrees enabled by default from the agent command center
  • Sandbox isolation fixes for Windows inbound, privileged sockets, macOS handles
  • 0.156.1 adds GPT-6 Sol/Luna; rate-limit prompt recommends Luna
Read full story

OpenAI improves GPT-6 prompt caching: higher default hit rates, up to 90% off cached input

OpenAI Developers (@OpenAIDevs) announced prompt-caching improvements for the GPT-6 API: higher default cache-hit rates so more input tokens get cached-input discounts of up to 90%, helping agents run faster and cheaper. OpenAI docs also point developers to the Prompt Caching Dashboard and miss Diagnostics.

OpenAI improves GPT-6 prompt caching: higher default hit rates, up to 90% off cached input

Key Takeaways

  • GPT-6 API prompt caching now hits more often by default for agent workloads.
  • Cached input tokens discounted up to about 90%.
  • Dashboard monitors hit rates; Diagnostics help fix cache misses.
Read full story

Overwatch v0.4.1: macOS coding-agent usage dashboard with clearer MCP connect UI

@joeychilson released Overwatch v0.4.1 (joeychilson/overwatch), a read-only macOS app that scans local Claude Code, Codex, OpenCode, Pi, and Grok Build sessions to summarize tokens, cost, and subscription limits, with session timelines and menu-bar limit alerts. The update improves the UI for connecting its MCP to Claude Code, Codex, OpenCode, or Grok so agents can query history and pace against limits. Install via Homebrew cask; MIT license.

Key Takeaways

  • Read-only token, cost, and limit summaries across Claude Code, Codex, OpenCode, Pi, and Grok Build sessions.
  • v0.4.1 improves MCP connect UI so agents can query history and pace against limits.
  • Install via Homebrew cask; joeychilson/overwatch under MIT.
Read full story

Grok Build v1.0.36: hide dashboard session preview, org policy blocks unmanaged hooks, live background shell task rows

xAI shipped Grok Build v1.0.36 (2026-09-17). Features: dashboard setting to hide the selected-session preview, org policy to disable unmanaged hooks, and background shells as live streaming task rows. Fixes include sandbox trust exit, pinned-agent jump, Swift triple-quote highlighting, mixed-case reasoning_effort in config.toml, MCP plugin client-ID auth, and background subagent shell approvals no longer silently rejected.

Key Takeaways

  • Dashboard can hide the selected-session preview; orgs can disable unmanaged hooks via policy.
  • Background shell commands appear as live task rows with streaming output.
  • Fixes sandbox trust, pinned-agent jump, Swift triple-quote highlight, mixed-case reasoning_effort, MCP plugin auth, and silent rejection of background subagent shell approvals.
Read full story
Linked Models & Agents:

Google Home MCP early access: Claude, ChatGPT and other agents can control smart-home devices

Google Home opened early access to a Model Context Protocol (MCP) server for US Google Home Premium Advanced subscribers. Any MCP-capable agent—Claude, Hermes, OpenClaw, ChatGPT, Google Antigravity—can securely connect to the Home ecosystem: review camera summaries, monitor activity, control Nest doorbells/thermostats and Matter lights, and build custom dashboards. Setup means creating a Google Cloud project, configuring Home MCP, then handing the config to an agent for sign-in and permissions. It covers Google Home and Works with Google Home / Matter devices, rolling out over coming weeks.

Key Takeaways

  • US Premium Advanced early access: Home MCP lets MCP agents safely drive cameras, Nest, and Matter devices
  • Works with Claude, Hermes, OpenClaw, ChatGPT, Google Antigravity for summaries, monitoring, control, dashboards
  • Needs a Google Cloud project + Home MCP config; agent-guided sign-in; rolling out over weeks
Read full story
Linked Models & Agents:
ADSponsored

Grok Build v1.0.31: MCP tools with long server prefixes kept; dashboard, subagent labels, cancel banners fixed

SpaceXAI shipped Grok Build v1.0.31. Key fix: MCP tools with long server prefixes are no longer silently dropped. Also fixes folded subagent run/complete labels, dashboard search and resume-picker focus/selection, worktree path suffixes, dock collapse highlights, cancel-cause banners, and long-path header shortening. Update with grok update --alpha or grok update.

Key Takeaways

  • MCP tools with long server prefixes are kept instead of silently dropped.
  • Folded subagent groups label running vs completed; dashboard search/resume focus and selection fixed.
  • Worktree path suffixes, dock collapse highlights, cancel-cause banners, and long-path headers fixed; update via grok update or --alpha.
Read full story
Linked Models & Agents:

Swarm v0.14.0 steers agents: block stop on red gates, dashboard Allow/Deny, command rewrite

Andrew (@Ra3orbladez) shipped Swarm v0.14.0: it no longer only watches agents—it can steer them. With on_stop=block, when Claude Code finishes a turn in a claimed worktree Swarm runs required repo gates first; on failure it refuses stop and returns the gate name plus output tail (max three refusals, then an incident to avoid burning budget). Permission prompts surface on the dashboard with Allow/Deny, co-editing agents learn of each other’s file edits immediately, idle sessions wake on message, and rules can rewrite commands (e.g. strip git commit --no-verify). Setup: bunx @ra3orblade/swarm setup.

Key Takeaways

  • on_stop=block runs repo gates before Claude Code can stop; red gates refuse stop with feedback (max three).
  • Dashboard Allow/Deny for permission prompts; cross-agent file-edit awareness; idle sessions wake on message.
  • Rules can rewrite commands (e.g. strip --no-verify); install via bunx @ra3orblade/swarm setup.
Read full story
Linked Models & Agents:

ChatGPT Work launches Data agent: connect company data, ask for analysis, dashboards, and action

ChatGPT announced a new Data agent in ChatGPT Work: add the Data Plugin, connect trusted company data sources and context, then turn questions into answers, interactive dashboards, and action. OpenAI says it is built from the same tools OpenAI uses internally for data analysis (openai.com/index/put-data-to-work/).

Key Takeaways

  • Data agent ships in ChatGPT Work for company analytics.
  • Connect existing data sources via the Data Plugin.
  • Ask in natural language for answers, dashboards, and action.
Read full story
Linked Models & Agents:

open-usage: open-source terminal dashboard for Claude Code, Codex, and OpenCode Go usage

Arion (@refatul_arion) open-sourced open-usage: a fast terminal dashboard with no account or API keys that shows Claude Code, Codex, and OpenCode Go usage in one place (npx open-usage).

Key Takeaways

  • Open-source CLI: run with npx open-usage.
  • Coverage: Claude Code, Codex, and OpenCode Go usage in one view.
  • Privacy: no account or API keys required.
Read full story

amux: open-source local-first control plane with atomic kanban for parallel Claude Code / Codex / Gemini CLI workers

Dan Kornas (@DanKornas) launched open-source amux: a local-first control plane for parallel coding agents as one Rust binary + SQLite. Coordinate Claude Code, Codex, Gemini CLI, OpenCode, or Ollama workers from a dashboard or phone with atomic kanban claiming, fleet visibility, origin-stamped messaging, schedules/loops, and crash recovery.

Key Takeaways

  • Ship: open-source local-first amux control plane (Rust binary + SQLite).
  • Orchestration: atomic kanban claiming so parallel workers do not collide.
  • Ops: fleet visibility, origin-stamped messaging, schedules/loops, model switch, crash recovery.
Read full story