🆓 Free
$0/month
- Up to 500 free LLM runs in your first 7 days. No credit card required.
prompt2botAI agents for the work you keep repeating.
Describe a task in plain language. Build an agent for customer support, research, operations, or personal work. Connect the tools it needs and use it on the web or in chat.
View pricing and free trial terms
or
Up to 500 free LLM runs in your first 7 days. No credit card required.
Start with one useful task
Answer questions from your docs, research a topic, process data, or organize your day. Choose a starting point, connect any required accounts, and test it with your own task.
For Business
Customer Support & Booking
Automate 24/7 customer inquiries, qualify website and WhatsApp leads, and book appointments on Google Calendar.
Personal AI
Mentat: Life & Work Assistant
Your personal assistant with a dedicated WhatsApp number, voice calls, calendar sync, and its own cloud computer.
No-Code Automation
Coder & Workflow Agent
Replace fragile Make and Zapier node diagrams with plain English. Connect emails, spreadsheets, and APIs automatically.
Explore agent templates
Templates are starting instructions. Connect the tools and accounts your workflow needs.
Sales
01 / 08
Lead Qualifier & Scheduler
Start with a sales strategy template, then add your qualification questions and connect a calendar for bookings.
Simple, Transparent Pricing
Prices are in USD. Paid plans renew monthly. Pause or cancel anytime in Settings or via the AI Builder, and your bots, prompts, and chat history are never deleted.
An LLM run is one AI model call. One message or task can use multiple runs.
Recurring scheduled actions require a paid plan.
🔍 Curious
$15/month
- 1,500 LLM runs/month
- Email support
🎯 Hobby
$30/month
- 4,000 LLM runs/month
🌟 Standard
$100/month
- 24,000 LLM runs/month
- Priority support
🚀 Pro
$400/month
- 80,000 LLM runs/month
- Dedicated support
All plans include: Unlimited agents · Unlimited training links · Analytics · Embed anywhere
Agent Infrastructure
Every assistant comes with real execution power
Full VM
Agents can use an on-demand virtual machine to run scripts, process data, and generate files.
Browser
Agents can browse the web, scrape pages, fill out forms, and research websites on your behalf.
Pre-Built Skills
Plug in pre-built skills — Google Calendar, Sheets, Docs, Gmail, Shopify, voice transcription, and web search.
Custom Tools & APIs
Connect your backend APIs as tools. The agent calls your endpoints to take real actions across your systems.
Memory
Remembers past context and customer history across conversations for seamless continuity.
Proactive Schedules
Send reminders and run scheduled workflows. Recurring schedules require a paid plan.
Architectural Comparison
Why prompt2bot vs. Local Harnesses?
Local-first frameworks like OpenClaw and Hermes are great for solo experiments in a terminal. Here is how prompt2bot is architected for secure, multi-user production.
| Capability / Architecture | prompt2botProduction Ready | OpenClaw | Hermes Agent |
|---|---|---|---|
Multi-User Data Isolation Architecture & Multi-Tenancy | Structural isolation (`isolateUsers = true`) Per-conversation memory isolation enforced at the schema level. Zero risk of client data or file leaks. | Shared workspace directory Single gateway auth token and shared workspace. Files from one user session can leak to another. | Global `USER.md` memory file Stores preferences in one global file injected into every conversation, causing cross-user contamination. |
Idle Cost & Scaling Cost & Compute | Zero idle cost (serverless edge) Stateless edge run loop executes only on incoming events. Create unlimited free agents without paying for idle VMs. | Heavy persistent processes Requires dedicated persistent containers or VPS per bot, paying 24/7 server bills even when idle. | Tied to host runtime Designed for single-machine local execution or dedicated server instances. |
Code Execution & Secret Egress Security & Sandboxing | Safescript + On-Demand VMs Domain-level firewall for credentials (e.g. Stripe keys only go to Stripe) + ephemeral VMs that auto-destruct. | Direct root shell access Agent has raw host shell access without outbound network firewalling, vulnerable to malicious supply-chain scripts. | Unrestricted local terminal Executes scripts directly on local operating system with full access to local filesystem and environment. |
Human-in-the-Loop Approvals Safety & Governance | Secure Admin Approvals When talking to third parties, sensitive tool execution pauses and requests 1-tap owner approval via WhatsApp/chat. | No multi-tenant authorization Any interacting user can trigger full agent tool capabilities unless custom middleware is written. | No external verification gate Lacks role-based permission verification when interacting across untrusted external contacts. |
Chat-Native Multi-Channel Messaging & Channels | Native WhatsApp, Telegram, E2EE, Email Built-in WhatsApp (Official + Supergreen), Telegram, Alice & Bot (E2EE), AgentMail, quote replies, and emoji reactions. | Webchat & terminal first Requires complex self-hosted bridge architecture and manual webhook configuration for messaging apps. | CLI / terminal wrappers Primarily local CLI oriented with basic community chat adapters. |
Time to Production Deployment & UX | < 1 minute setup (AI Builder) Conversational AI builder creates prompt, tools, and channel connections automatically. 1-click Talk-to-Skill launcher. | Manual orchestration Requires terminal setup, Docker image building, gateway token management, and infrastructure maintenance. | Local developer setup Requires Python environment setup, local API key configuration, and manual tool wiring. |
Architecture & Multi-Tenancyprompt2bot
Multi-User Data Isolation
Structural isolation (`isolateUsers = true`)
Per-conversation memory isolation enforced at the schema level. Zero risk of client data or file leaks.
Cost & Computeprompt2bot
Idle Cost & Scaling
Zero idle cost (serverless edge)
Stateless edge run loop executes only on incoming events. Create unlimited free agents without paying for idle VMs.
Security & Sandboxingprompt2bot
Code Execution & Secret Egress
Safescript + On-Demand VMs
Domain-level firewall for credentials (e.g. Stripe keys only go to Stripe) + ephemeral VMs that auto-destruct.
Safety & Governanceprompt2bot
Human-in-the-Loop Approvals
Secure Admin Approvals
When talking to third parties, sensitive tool execution pauses and requests 1-tap owner approval via WhatsApp/chat.
Messaging & Channelsprompt2bot
Chat-Native Multi-Channel
Native WhatsApp, Telegram, E2EE, Email
Built-in WhatsApp (Official + Supergreen), Telegram, Alice & Bot (E2EE), AgentMail, quote replies, and emoji reactions.
Deployment & UXprompt2bot
Time to Production
< 1 minute setup (AI Builder)
Conversational AI builder creates prompt, tools, and channel connections automatically. 1-click Talk-to-Skill launcher.
Learn
Thoughts on agents, architecture, and shipping fast
Your AI Assistant Belongs in WhatsApp, Not Another App
2026-10-29
Every few months a new standalone AI assistant app launches. You download it, grant it permissions, try two or three prompts, and then forget the icon exists by the following Tuesday. The model is ra...
How Small Businesses Automate WhatsApp Support and Booking Without Node Builders
2026-10-28
If you run a clinic, a consulting practice, an agency, or an online shop, your customers do not want to fill out a web form and wait two days for an email. They message you on WhatsApp or open the cha...
How to Build Cheap, Safe, Proactive Agents
2026-10-05
Most people building AI assistants today build chatbots. You send a message, the model runs, it answers, and then it goes to sleep until you send another message. That works fine for search or one-of...
Why Your Agent Harness Needs a Decision Model
2026-09-27
Most agent frameworks make a quiet assumption that turns out to be expensive: they treat the language model as the only hammer in the toolbox. Whenever the harness needs to make a choice, it prompts...
Benchmarking Our Agent Harness on FrontierHarness with GLM-5.3-Flash
2026-09-14
When the FrontierHarness Eval results came out, they confirmed something we have argued for a long time: the model is only half the equation. The harness changes everything. The benchmark ran the exa...
The Harness Tax: Benchmarking Agents on the Exact Same Model
2026-09-03
Most popular agent frameworks like Pi, OpenClaw, and Hermes share an unstated assumption. They assume an agent is a long-running process in a private VM or terminal, running shell commands, modifying...
Built on great open source
prompt2bot relies on open source libraries and skill infrastructure.