# Meet Alfred runs LinkedIn from your browser. Zevari runs your whole outbound department. URL: https://zevari.ai/vs/meet-alfred > Meet Alfred runs LinkedIn from your browser. Zevari is your AI SDR team for LinkedIn and email: it researches, scores your ICP, writes in your voice, and sends wait for your approval until you switch a trained specialist to Autopilot. Zevari vs Meet Alfred Meet Alfred is a mature browser-based LinkedIn automation tool - a Chrome extension or cloud session that logs into LinkedIn on your behalf and fires templated sequences. That is the model the entire first generation of LinkedIn tools is built on. Zevari is a full outbound department, running today: your AI SDR team for LinkedIn and email. Six specialists research prospects, score them against your ICP, write in your voice, and stage sends for your approval until you switch a trained specialist to Autopilot, through a hosted connector with no browser extension and no cookie injection. Run it from the Zevari app, or from Claude Code, Codex, or ChatGPT over MCP. [Connect to Claude Code](https://zevari.ai/auth/login?mode=signup&redirect=/app) [Connect your agent](https://zevari.ai/quickstart) The frame ## We share a buyer, not a category If you run Meet Alfred, you already believe LinkedIn is your best channel and you already automate it. We agree. The question this page answers is narrower: should the work happen in a browser extension that fires templated sequences, or inside the AI you already think with? One customer put it plainly on a call: "maybe I don't need Meet Alfred anymore because Zevari is doing all the stuff." That's the whole pitch - not "Alfred is bad," but "the stack you're paying for - the list-builder, the sequencer, the enrichment, the second AI tool you bolted on - collapses into one team." ### Research and ICP scoring Prospects scored 1 to 5 against your ICP with the why attached, so the agent skips the 2-out-of-5s and learns when you correct it. ### Lookalike from a known-good client Hand it one customer or a single profile URL and it finds more like them - no filter-stacking, no second list-builder. ### Inbox Radar Replies classified by intent, on-brand responses staged for your approval, so you stop scrolling for the one reply that matters. ### Campaigns and follow-ups Built and advanced by your agent on schedule, with email as the follow-up leg to LinkedIn non-responders - not a separate sequencer. Where the two diverge ## Three reasons buyers switch Three things separate an AI SDR team from a browser automator. They're the three reasons people move. ### Targeting is signal-based, not list-based Meet Alfred runs the list you hand it. Zevari scans for people who posted about your topic in the last 30 days, scores each prospect 1 to 5 against your ICP with the reasons written out, and reaches only the high-intent ones. Stop sending to a static export; start reaching people who are in-market this week. ### The messages sound like you Meet Alfred sends the template you wrote, with variables swapped in. Zevari's Voice DNA is trained on your own sent messages, so the drafts read like you wrote them - not like merge-tag mail. The AI version of you, going out to do its thing. ### The whole thing runs from one brain With Alfred you assemble a stack - the automator, a list-builder, sometimes a separate AI writer, a CRM connector. With Zevari your agent does the research, scoring, warming, campaigns, inbox triage, and email follow-up to non-responders. One console, one approval surface, one place the strategy lives. Where it lives ## In the app or in your AI, not a browser extension Meet Alfred is an extension you install and a UI you log into. Zevari runs from the Zevari app, or from Claude Code, Codex, ChatGPT, or any MCP client through the hosted Zevari LinkedIn MCP. Technical teams can also call the REST API from their own code. Add to Claude Code, then run /mcp to sign in ``` claude mcp add --transport http zevari https://mcp.zevari.ai/mcp ``` That means the research and the outreach live in one place. Your AI can already research a prospect deeply; with Zevari the team can act on what it found - connect, message, comment, post - without you stitching a list-builder plus a sequencer plus an AI writer plus a CRM connector into one fragile stack. And because Zevari holds hosted state, your campaigns keep advancing and your follow-ups keep firing on schedule - with sends still waiting for your approval until you switch a trained specialist to Autopilot. Safety ## "I don't want to be banned." That's why browser-based tools lose the buyer. When a tool logs into LinkedIn through a browser session and fires sequences on a schedule, LinkedIn sees the logs - and accounts get flagged. Zevari's answer isn't a louder adjective; it's the mechanics, and we publish the actual limits on the safety page. [Read the full safety model](https://zevari.ai/safety) Session-based connection. No browser cookies, no extension logging into LinkedIn on your behalf. Every write action - message, connection request, comment, post - waits for your approval until you switch a trained specialist to Autopilot. Enforced ceilings: 100 connection requests a week on Free*, 150 on Premium, 200 on Sales Navigator, plus a daily cap on all actions. * Free accounts: LinkedIn caps connection requests that carry a note at 3 a month. The weekly ceiling covers requests sent without a note, and Premium and Sales Navigator accounts get a far larger allowance for requests with a note. Most outreach uses a note, so Premium or Sales Navigator is the practical choice for real outbound - the full explanation is on /safety. Working hours, behavioral pacing, duplicate checks, and burst caps - so you can't overshoot by accident. The comparison, straight ## An honest table Meet Alfred does real work and a lot of teams are happy with it. What it can't be is Claude with hands on LinkedIn - that's a different architecture, not a feature toggle. | | Meet Alfred | Zevari | | --- | --- | --- | | Where it runs | Chrome extension / cloud browser session | Inside Claude Code or Codex (or any MCP client) | | Connection model | Logs into LinkedIn for you (browser-based) | Session-based connection, no browser cookies | | Targeting | Lists and saved searches you build | Signal-based: posted-in-30-days, ICP scoring 1-5 with reasons | | Message writing | Templates with variables | Voice DNA - trained on your sent messages | | Sends | Sequences fire automatically | Writes staged for human approval until you switch a trained specialist to Autopilot (message, connection, comment, post) | | Warming | Auto-endorse / view add-ons | Warm-by-default: comments, reactions, profile views before the ask | | Inbox | Reply detection, basic | Inbox Radar - replies classified by intent, drafts staged | | Safety posture | Weekly limits, randomization | Weekly ceilings, daily action caps, working hours, behavioral pacing, duplicate checks, burst caps | | Who does the work | You build the lists and launch the sequences | Six specialists run it from the Zevari app or your AI; sends wait for your approval until you switch a trained specialist to Autopilot | | Strategy lives in | The tool's UI | Your plan, ICP, and voice, held by the team | When to stay on Meet Alfred: if you want a self-contained browser tool, you don't work inside Claude Code or Codex, and templated sequences against lists you build are getting you the volume you need - it's a solid tool for that job. Switch to Zevari if you already run Claude (or want to), you're tired of stitching a list-builder plus a sequencer plus an AI writer plus a CRM connector into one fragile stack, you want signal-based targeting and messages that sound like you, or "I don't want to be banned" is the sentence keeping you up. FAQ ## Questions buyers ask when they're switching ### Is Zevari a Meet Alfred alternative? Yes, for the same job - running LinkedIn outbound - but it is a different architecture. Meet Alfred is a browser-based automation tool that logs into LinkedIn for you and fires templated sequences. Zevari is your AI SDR team for LinkedIn and email: it researches prospects, scores them against your ICP, writes in your voice, and stages sends for your approval until you switch a trained specialist to Autopilot, through a hosted connector with no browser extension and no cookie injection. Many buyers consolidate their stack onto Zevari rather than run both. ### Will Zevari get my LinkedIn account banned? No. If Zevari is the only tool running outbound on your LinkedIn account, and you use the account lightly yourself while Zevari is working, we guarantee it. Zevari's Safety Center paces every action like a person and counts every action the account takes against its limits: 100 connection requests a week on Free* accounts, 150 on Premium and 200 on Sales Navigator, daily caps, working hours and burst limits. Anything that would cross a limit waits for the window to reset. If another automation tool runs on the same account, or you use it heavily by hand at the same time, those actions fall outside Zevari's count, and we cannot guarantee it. The weekly figure covers connection requests sent without a note: LinkedIn caps requests that carry a note at 3 a month on a free account, and gives Premium and Sales Navigator a far larger allowance, so Premium or Sales Navigator is the practical choice for real outbound (see /safety). ### Do I need Meet Alfred and Zevari both? Most people do not. Zevari does the research, ICP scoring, voice-matched message writing, campaigns, warming, inbox triage, and email follow-up to non-responders in one place. The common path is to consolidate the stack - one customer told us "maybe I don't need Meet Alfred anymore because Zevari is doing all the stuff." ### Do I need LinkedIn Sales Navigator to switch? No. You can start without it. Sales Navigator only raises your weekly connection limit (to 200 a week, versus 100 on Free* and 150 on Premium) - it is not required to run Zevari. ### Can it find people who are posting about a topic and reach out to them? Yes. That is signal-based targeting: Zevari scans for people who posted about your topic in the last 30 days, scores each one 1 to 5 against your ICP with written reasons, and reaches only the high-intent prospects - instead of running a static list export. ### Does it actually send messages, or just draft them? Both, in stages. While you train it, it drafts and you approve: every write action - message, connection request, comment, post - waits for your sign-off before anything is sent. Once a specialist has earned it, you switch it to Autopilot and it sends on its own, and you can switch it back at any time. ### I'm not technical. Can I still switch off Meet Alfred? Yes. You do not need Claude Code or Codex. The same six specialists, Prospecting, Signals, ICP Scoring, Voice Writer, Follow-up, and Reply Qualifier, run your LinkedIn and email outbound from the Zevari app, and every send waits for your approval until you switch a trained specialist to Autopilot; you approve from the review queue. ## Consolidate the stack into one team Same approval-gated engine on both lanes. Reach Zevari over MCP for Claude Code and Codex, or our REST API from your own code. ### You run Claude Code or Codex Connect Zevari to your AI in a minute - signal-based, in your voice, with an approval on sends by default. Connect over MCP for Claude Code and Codex, or call our REST API from your own code. [Connect to Claude Code](https://zevari.ai/auth/login?mode=signup&redirect=/app) ### Let the team run it Don't run Claude Code or Codex? The same six specialists, Prospecting, Signals, ICP Scoring, Voice Writer, Follow-up, and Reply Qualifier, run your LinkedIn and email outbound from the Zevari app. Sends wait for your approval until you switch a trained specialist to Autopilot. [Build my AI team](https://zevari.ai/auth/login?mode=signup&redirect=/app) Zevari - a full outbound department for LinkedIn and email. Sends wait for your approval until you switch a trained specialist to Autopilot.