Agents

✧ Auto Follow-ups and Auto CSAT: re-engage silent leads and measure satisfaction automatically. ✧ WhatsApp Campaigns: broadcasts with a full templates editor. ✧ New channels: SMS and Facebook Messenger, so your assistant meets customers wherever they already are. For any WhatsApp you can connect multiple numbers. ✧ Assisted Human Replies and Canned Replies: an AI co-writer in every reply box, one-tap saved answers ✧ Human-Only Mode and per-contact AI control: you decide exactly where AI replies and where humans do ✧ Contact Properties, Segments and Segment actions: CRM-grade customer data your assistant keeps updated on its own ✧ Customer Insights and expanded analytics: CSAT trends, resolution times and peak-hours activity and more. ✧ New integrations: Odoo, WooCommerce, Zoho Booking and Calendar, Outlook Calendar, and a WordPress plugin ✧ File actions: your assistant creates CSVs and PDFs on demand ✧ Newest models in your picker: Claude Sonnet 5, GPT 5.4, Gemini 3.5 Flash, Grok 4.3 and Muse Spark 1.1. You choose the model, per assistant ✧ Full Agencies Suite: sub-organizations, white-label, custom domains, spending caps and consolidated billing. You control every client account ✧ Single Sign-On (SSO) on every Business plan: Google Workspace, Microsoft Entra ID, Okta, or any OIDC provider ✧ Duplicate Assistants: clone a proven setup for the next client in seconds ✧ API access on every plan, with API key rotation: embed the assistant in your own product or a client’s ✧ Custom Roles: full RBAC (role-based access control) on every plan, so your team (or a client’s) sees only what they should ✧ Invent Chat now has a real computer: ask for a chart, doc, or analysis and get the finished file back ✧ Enterprise-grade trust: Audit Logs, session management, SOC 2 Type II certified ✧ Invent is a Meta Business Partner

🚀 AI QA Monkey v2.0.0 is Live: From One-Time Audit to Unstoppable 24/7 Defense. This is our most massive upgrade yet. We haven't just updated our engine—we've quadrupled our security coverage. Scaling from our original 25 checks, we now deploy 100+ proprietary security tests that most competitors miss. But the biggest breakthrough? True 24/7 Continuous Monitoring. Your website is now constantly guarded. Hackers don't sleep, and neither do we. As new malware, vulnerabilities, and zero-day threats emerge globally, our engine is instantly updated. If your site is exposed to a newly added threat, you receive an immediate alert—allowing you to patch the hole before attackers even know it's there. Every finding now ships with copy-paste fixes, AI remediation prompts, and a step-by-step guide. 🔹 Release Notes (What's New — v2.0.0) 🛡️ AI QA Monkey v2.0.0 — "Always-On Security" Transforming a static audit into a living, breathing, and guided security shield. 🔍 Detection — 4X Coverage Expansion (100+ Tests) Coverage has quadrupled. We now run over 100 deep-scan checks across 15 attack surfaces, including 70+ proprietary tests unavailable in competing tools. We aggressively target the newest malware and emerging vulnerabilities: • Supply-Chain & Magecart Defense: Detects compromised or abandoned third-party CDNs silently executing malicious code in your visitors' browsers. • Zero-Day & Known CVE Library Scanning: Instantly flags vulnerable front-end libraries the moment they become a threat. • Client-Side Secret Detection: Hunts down leaked API keys and tokens hidden deep in your JS bundles. • Source-Map & Build Exposure: Prevents disastrous leaks by catching production source maps that hand attackers your raw code. • Complete Email-Trust Suite: Validates SPF, DKIM, DMARC, BIMI, MTA-STS & TLS-RPT in a single, powerful pass. • Advanced Web Architecture Checks: Reflected-origin CORS, dangerous HTTP methods, GraphQL introspection, CAA & HSTS-strength validation. 🔔 The Game Changer: 24/7 Continuous Monitoring (NEW) Set it and forget it. We continuously monitor your site around the clock. Our threat engine is constantly updated with new checks for the latest malware and exploits. If your security score drops or our engine detects a newly discovered vulnerability on your site, you get an immediate email alert—stopping regressions in their tracks. 🗺️ Visibility — See What The Attackers See Our interactive Attack Surface Map visually renders your entire external footprint—subdomains, open ports, exposed files, and WAF status—as a live network graph, beautifully integrated into your web dashboard and PDF reports. 🧠 AI-Driven Remediation Intelligence Finding the problem is only half the battle. Every vulnerability now comes with copy-paste server configs, an AI Fix Prompt (ready for ChatGPT, Claude, or Cursor), and a plain-English step-by-step guide backed by a library of 45+ deep-dive remediation playbooks. 📄 Industry-Leading, Boardroom-Ready Reports Generate stunning audits in seconds: severity-ranked findings, compliance mapping (OWASP · PCI DSS · ISO 27001 · GDPR), score trends, and confidence levels, fully exportable to PDF, JSON, or CSV. 💼 Plans Scaled for Every Workflow (NEW) • One-Time Report — $29 (Yours to keep) • Monitor — $7.99/mo (Always-on early warning system) • Pro — $29/mo (Monitoring + 30 full reports/domain) • Agency — $79/mo (Up to 10 domains + 300 full reports/domain) ♻️ An Engine That Never Stops Learning As fresh CVEs, malware, and attack techniques emerge, we code the detections straight into our engine—automatically. Your scans always test against the absolute latest threats. No installations, no maintenance. Just pure security. 🔹 One-liner (Tagline) AI QA Monkey v2.0.0: Scan. Fix. Monitor. On Repeat. 100+ deep checks, a live attack-surface map, and relentless 24/7 monitoring that catches new threats before they strike.

AdControlCenter v1.3.0 Campaign creation got faster, and the ads finally listen to you. This release is about the gap between what you tell AdControlCenter and what it puts on the page. Three things you asked for were being quietly ignored — the language you picked, the thing you said you wanted to promote, and the countries you wanted to reach. All three now land. Your ads speak the language you chose. If your site is in Arabic but you want English ads, you get English ads. Previously the generator took its cue from the source site and overrode you. Non-Latin scripts (Hebrew, Arabic, Japanese, Chinese) render properly on the image itself. Your campaign’s actual goal reaches the creative. When you say “invite Etsy sellers to join our swap community,” the ads are now about the community — not a generic pitch for the company. The brief you write is treated as the job the ad has to do, not as background reading. Campaign creation is several times faster. The creative pipeline used to run past the platform’s execution ceiling and die silently, leaving you watching a progress bar that would never finish. It’s now split into resumable stages, with the business-analysis half computed during onboarding and reused, so every campaign after your first starts warm. Typical run: 1–2 minutes. Every country is selectable. The targeting dropdown carried 51 hand-typed countries; it now carries all 246 that Google supports. Lebanon, Jordan and about 190 others were simply unreachable before.

1. Meev is now agent-native The whole product now leads with an AI SEO agent that runs the full loop for you. - The agent tracks your AI visibility, finds the gaps, and publishes the fix, and acts only after your approval. - New Approval Ledger so you see exactly what the agent proposes, with the evidence, before anything ships. - In-product agent demo video, a cleaner agent chat, and a dedicated dashboard tour. - New AI content marketing agent landing page and a repositioned growth-agent page. - The agent now explains why a draft is held for your approval instead of auto-publishing, and is always date-aware. 2. Connect Meev to your own stack (new) Your AI visibility data now goes wherever you work. - MCP server (live): connect Meev to Claude, ChatGPT, and any MCP-compatible assistant and read your visibility, rankings, and content data right inside it. Read-only and secured, with a one-line @meev/mcp connector. - Public REST API (live): pull every metric programmatically, full OpenAPI spec, a /developers docs page, and API-key management in settings. - New /connect hub: one place to set up MCP, terminal installs, and the meev-data skill. - Per-plan connection quotas, with unlimited concurrent connections. 3. Onboarding rebuilt around your GEO Score - Visibility-first setup: get your GEO Score and a real, prioritized action plan before you reach billing. - Redesigned GEO Score reveal with an honest report (real competitors, sample-aware plan) and a smoother reveal animation. - Simpler trial start: no-card trials, in-wizard Google connection, and a finish-setup guide. 4. A fresh look - New Gilded Editorial design across the home page, blog, and marketing site. - Navigation reorganized into Platform / Solutions / Resources menus. - Agent demo video in the hero; blog reading rails that follow you as you scroll. 5. Under the hood - Higher content quality from an upgraded writing and scoring engine. - Faster site audits. - New Google Search Console index-coverage and URL-inspection tools for the agent. - First-party analytics and ad conversion tracking wired up behind the scenes.

Notis is the AI intern one message away from your entire tool stack. Dictate ideas, delegate the busywork, and let Notis update your workflows across WhatsApp, Telegram, iMessage, Slack, and email. Notis 07.26 is our biggest step since v3 — Notis now works on your own computer and inside the coding agents you already use. In this release: Your Computer: run shell commands, connect your local tools (MCP), and drive desktop apps with no API — opt-in, with an approval level you control. Notis for Coding Agents: connect once and Codex, Claude Code, and Cursor work through your Notis account — skills, integrations, and memory, everywhere. Now on GPT-5.6: every task runs on OpenAI’s newest models — same dial, sharper underneath. More: per-thread usage in the Manager, smoother trials, and reliability fixes. Read the full release: https://notis.ai/changelog/07-26

- Added Terminal for Mac: describe your strategy in plain English and AI builds the entire trading desk — charts, indicators, watchlists, and news — in seconds - Added built-in backtesting: compare any strategy against the S&P 500 and other benchmarks - Added strategy scoring across performance, safety, diversification, cost efficiency, and resilience - Improved multi-chart desk layouts with custom indicators - Free to download for Mac, no credit card required

AgentSwarms — Our Biggest Release Yet: 100+ Executable Framework Notebooks, Voice Agents, Website Embeds & More TL;DR — what's new: -103 executable, in-browser notebooks across 9 agent frameworks — no setup, run every cell live. -Voice agents you build with speech-to-text + text-to-speech and talk to right in the browser. -Website embeds — drop a standalone agent or a multi-agent task bot onto your own site with one iframe. -30 interactive field-engineering blogs + 25 interactive presentation decks -9 hands-on failure-mode labs + a 38-cell failure-modes notebook covering 12 real production failures -17 free, no-login interactive AI tools -Detailed swarm execution traces — tokens, cost, latency, every handoff -20 runnable industry templates AgentSwarms is a learn-by-building platform for Agentic AI: build, run, test, and ship AI agents and multi-agent swarms — and actually learn the frameworks by running real code, not reading about it. This is our largest update to date. Here's everything that's new. 1. Framework-specific notebooks with executable cells — learn every major agent framework by running it We shipped 103 notebooks with live, editable cells that execute right in your browser — zero installs, zero API keys to wrangle. There are dedicated, in-depth tracks for OpenAI Agents SDK, Google ADK, LlamaIndex, Mastra, LangChain, LangGraph.js, and AWS Strands SDK — plus Vercel AI SDK and VoltAgent. Each track walks the whole arc: fundamentals → typed tools → multi-agent handoffs → memory → guardrails → evaluation, with clear, beginner-friendly explanations next to code you can change and re-run. Start here: https://agentswarms.fyi/notebooks 2. Build voice agents with TTS + STT — give any agent a voice and talk to it You can now turn any agent into a voice agent using a speech-to-text → LLM → text-to-speech pipeline, pick from 11 studio voices, and talk to it live in the Voice Playground — tap the mic, speak, and hear it answer back. Fork a ready-made sample to get started in seconds. Because voice runs on the same engine as chat, your tools, RAG, memory, and guardrails all carry straight over. Try it: https://agentswarms.fyi/voice-playground 3. Build an AI backend and embed agents + multi-agent task bots on your website Ship what you build. Embeds turns any agent or swarm into a widget you paste into your own site with a single iframe — no backend to stand up. Choose an Agent embed (a streaming chat panel that answers with the agent's full brain) or a Swarm embed (a run-and-return task bot where a whole multi-agent workflow executes server-side and returns the result). Every embed gets domain-locked API keys, a per-embed daily request cap, and serves anonymous visitors with no login. Details: https://agentswarms.fyi/docs/embeds 4. New interactive field-engineering blogs and presentations Our library now includes 30 field-engineering blog posts, each with custom interactive visuals you can click through — covering AI agents in financial services, multi-agent simulation, deploying MCP servers to AWS/Azure/GCP, voice agents, security, retrieval, cost control, and framework deep-dives. Alongside them are 25 interactive presentation decks on everything from LLM internals to multi-agent orchestration and LLMOps. Read them: https://agentswarms.fyi/blog 5. A lot more failure-mode labs and notebooks Real agents fail in ways demos never show, so we built the practice ground for it: 9 hands-on failure-mode labs in the swarm canvas that inject a real fault — a coordination deadlock, a cascading error, a runaway loop, a prompt injection — and then grade your fix. They're backed by a 38-cell "Failure Modes Lab" notebook that reproduces 12 production failure modes (hallucinations, sycophancy, RAG poisoning, context rot, cost blow-ups, goal drift, and more) and ships the exact fix for each. Start at https://agentswarms.fyi/learn 6. Free interactive AI tools We added 17 free, no-login browser tools for everyday agent work: a RAG chunking visualizer, prompt-injection tester, semantic chunker, swarm-architecture visualizer, PII redactor, multi-agent token-cost calculator, LLM-as-a-judge builder, tool-schema generator, GraphRAG triplet extractor, synthetic RAG-eval dataset generator, and more. Open and use them instantly: https://agentswarms.fyi/tools 7. Detailed swarm execution traces Every multi-agent run is now fully traced and replayable. Step through each node's inputs and outputs, every tool call and handoff, and read per-run token usage, cost, and latency on a timeline — the raw material for debugging, evals, and cost dashboards. No more guessing why a swarm did what it did. 8. More runnable industry templates We expanded the template library to 20 one-click, runnable industry templates — support triage / knowledge-base agent, research RAG, sales outreach, code reviewer, CRM data cleanser, long-context analysis, and more. Each spins up a working agent or swarm you can run immediately and adapt. Browse them: https://agentswarms.fyi/templates

🎨 Design & Editing • Easier image editing • Improved text editing mode • Better-looking projects from first prompt • One-click project duplication • Improved desktop and mobile responsiveness