Ranla is lifecycle and transactional email: automations, audiences, and sends, with a built-in agent that drafts and asks before anything goes out.
Lifecycle and transactional mail. Campaigns that prove lift before they go always-on. Talk in Slack like a teammate, or let Autopilot stay inside your caps.
2,000 most recent · 400/day · 15% holdout. Nothing sends until you approve.
Hey. You signed up for Acme back in March and never finished setting up. That's usually our fault, not yours.
So I did the step you stopped at. Your workspace is ready and there is nothing left to configure.
If it's useful, you can pick up where you left off today.
Talk in that window, or in Slack next to your team. Agent window and Slack → · AI agent →
You do not click through templates, campaigns, and automations to get work done. You talk, and the agent can make templates, build campaigns, set up automations, and work audiences. The dashboard is still there when you want it. Sends still wait on your rules.
Ask for a welcome, a trial-ending note, a receipt. It drafts in the thread and publishes when you say so.
Audience, angle, holdout. It drafts the campaign in the same window and asks before anything sends.
Promote a campaign into an always-on automation, or ask it to build the flow from scratch.
Describe who should get the send. It builds the segment from product events.
Same window that can open a GitHub PR. Same agent in Slack. How the agent window and Slack work →
Ranla includes a built-in agent that drafts campaigns and automations, then asks before anything sends. Add it to Cursor, Claude, Grok, or any MCP client. The agents talk to each other. Ranla still drafts and asks.
Ranla connects a GitHub repo, scans the codebase, instruments the events the platform needs, and opens a pull request. You review and merge. Nothing ships until you do.
Connect GitHub. The agent reads the codebase, wires the events audiences and automations need, and opens a pull request. You review and merge.
Missing activation? A trial-ending moment with nothing behind it? The agent recommends events from the product. With the repo connected in the workspace, it instruments those events and opens a pull request. Campaigns and code changes from the same place.
Lifecycle email and product instrumentation in one platform. Marketing and engineering do not need two tools for that. How the agent window works →
2,000 most recent · 400/day · 15% holdout. Nothing sends until you approve.
Ranla waits here, not in your inbox.
Talk in the window, in Slack next to your team, or add Ranla to Cursor, Claude, or Grok. They talk to each other. Then install via a GitHub pull request.
Campaigns that win become always-on automations. Email + SMS via Twilio.
Campaigns, automations, and the agent optimize the primary goal. Holdouts prove whether a send moved it.
Name the goals that mean winning. The primary goal is what campaigns and the agent optimize; holdouts prove whether a send moved it.
Treated converted at 2.5× the holdout. Opens do not count.
312 skipped · 112 unsubscribed · 98 suppressed · 102 frequency cap
Measure lift against people who got nothing, on the goals you named.
When someone writes back, classify intent, draft in your voice, and send only when the confidence gate clears.
Priced on people engaged in the last 90 days, not raw list size. Emails included; overage only past your plan. SMS bills through your Twilio account.
A lifecycle and transactional email platform for PLG SaaS. Ranla runs automations and audiences from product behavior, and includes a built-in agent that drafts and asks before it sends. SMS steps run through your Twilio account.
Small and mid-market PLG SaaS teams that need an email platform, not an agent to bolt onto mail they already send. If your last few thousand signups have never received an email from you, that is the job.
Yes, and most people start there. Connect GitHub and the agent scans the codebase, instruments the events Ranla needs, and opens a pull request you review. It can also recommend events you should add and write those into the same repo. If you already use PostHog, Amplitude, or Mixpanel, connect that instead. Ranla copies the moments that matter for people with an email, no PR required. Either path is enough.
Yes. Connect a GitHub repo in the workspace. The agent scans the product, recommends events you are missing, instruments them, and opens a pull request. You merge. It does not push to your default branch. Analytics connect is the other on-ramp if you would rather not change the repo.
No. Talk in the agent window. It can make templates, build campaigns, set up automations, and work audiences, the same place it can open a GitHub pull request. The dashboard is still there when you want it. Nothing sends until your rules say so.
Only if you tell it to. You pick the mode: Draft leaves everything for you to send, Propose asks before each send, Autopilot lets it send inside your limits. Any audience over 5,000 people needs your approval in every mode, and Ranla can tighten its own limits but never loosen them.
Yes. Ranla sits in Slack like a teammate. DM it, @mention it in a channel, or use /ranla. Brief it, approve a send, snooze, see what it is doing. Open the app when you want the canvas or the full picture.
You set the frequency cap, the daily account cap, and the audience size above which a send waits for you. They are enforced in the send path rather than asked for in a prompt, so they hold on every send. Defaults are two emails per person per week at least 48 hours apart, and sends stop mid-flight if complaints pass 0.1% or bounces pass 5%.
You pick the outcome that counts (activation, paid conversion, a first key action), and Ranla holds back a control group that gets nothing. Comparing the two is how you see whether a campaign moved that number or whether those users would have converted anyway. Campaigns that do not beat the control get dropped, and what does beat it shapes the next one, so the work compounds instead of repeating.
Both, in that order. Ranla starts with campaigns because that is how it finds out what works on your users, and a campaign that beats its holdout gets promoted, with your approval, into an always-on automation that fires for every user who hits that moment from then on. You can also ask it to build a standard automation outright, like a welcome sequence, a trial-ending series, or a win-back. Campaigns and automations share one frequency count per person.
You can see a draft written for your product in a couple of minutes without signing up. Real sends wait on setup finishing and on having something to segment on, usually the same day you connect analytics and pick moments, or merge the tracking pull request.
It can, through one API, sharing the same suppression list so a marketing unsubscribe never blocks a password reset. Transactional and lifecycle mail go out the same way.
Yes. Add the hosted MCP server (https://mcp.ranla.ai/mcp) in Cursor, Claude, Grok, or any client that speaks MCP. The agents talk to each other. Ranla still drafts and asks. Send rules and approvals stay in Ranla.
No. Other agents talk with the same Ranla agent that drafts and asks. Draft, Propose, and Autopilot still apply. Any audience over 5,000 people still needs your approval. Slack and the app still work.
Start sending for free. Paid plans start at $99/mo, priced on people engaged in the last 90 days (product use or email open/click), not raw list size. Each plan includes emails; usage above the included amounts bills as overage. SMS goes through your Twilio account.
Connect a GitHub repo, or analytics. Then talk in the agent window: templates, campaigns, automations. It still asks before it sends.