Tell me the one workflow you'd love to hand off. I'll design a working agent for it, right here on this page.
Build your first agent - live, on this pageSay it once.
Say it once.
Your agent does the rest.
Describe one workflow. The agent builds it live - steps, tools, and the hours it gives back.
Free signup Live in 5 minutes Experts on call
agent_builder · live
or start from
Enterto sendfree to try · draft stays on this device
- 20X
- Efficiency gain
- 50+
- Integrations
- 99.9%
- Uptime SLA
- <5 min
- Setup time
How it works
One task in. Finished work out.
You describe the workflow once. 20X plans it, connects the tools, runs every step - and learns from the result.
Loading the diagram of how 20X works
Free to start. The agent replies in seconds - no signup, no setup call.
Trusted by operators at ambitious teams
Two ways to 20X
Build it yourself. Or build it with us.
Some teams want the keys. Others want a partner. 20X supports both - the platform is fully self-serve, and Setoo consultants are on standby whenever you'd rather skip the learning curve.
Path A · DIY
Self-serve platform
Direct access to the 20X OS. Build, deploy, and scale your agent workflows with the no-code canvas - no engineer required.
- Visual workflow builder
- Pre-built agent templates
- Community + docs
- Instant onboarding
Path B · ExpertComing soon
The Performance Desk
Our consultants take the wheel and run the numbers with you: every workflow costed in tokens, every hour saved and every rupee earned tracked against a target we sign up to. Performance math, not a slide deck.
- Baseline audit with the payback maths
- Built, deployed and tuned for you
- Named consultant, monthly review
- Priced against the outcome, not hours
Opening soon - packages being finalised
The Platform
Everything for calm, autonomous operations.
A complete operating system for AI agents - orchestration, security, CRM, forms, billing. One workspace, no glue code, no janitors.
Orchestration
Multi-agent orchestration
Specialist agents coordinate across queues, tools, and human approvals - one calm control plane.
Builder
Visual workflow canvas
Drag, connect, and ship. Triggers, branching, and retries without a single line of code.
Memory
Self-learning skills
Every run compounds. Agents remember outcomes, refine prompts, and improve unattended.
Guardrails
Enterprise controls
ISO 27001 compliant, SOC 2-ready posture with RBAC, audit logs, and human-in-the-loop approval gates.
Data
Built-in CRM & forms
A unified customer record plus adaptive forms that qualify, enrich, and route in real time.
Connect
Webhook & API hub
50+ native connectors plus REST, GraphQL, and webhooks for anything custom in your stack.
See it in motion
A quiet workspace where agents actually work.
No dashboards to babysit, no scripts to maintain. Watch specialist agents orchestrate real work across your tools while your team focuses on the human parts.
Captions included. Plays inline on mobile.
20X workspace · liveAuto-playing
99.98% uptime50+ integrationsISO 27001 · GDPR · DPDP
The Multiplier
Build a 20X company - without a 20X headcount.
Internal automation that compounds. Every agent learns, every workflow improves - output multiplies while your team focuses on the work that matters.
20X
Output multiplier
Scale operations without scaling headcount.
90%
Task automation
Automate repetitive workflows from day one.
5 min
Time to deploy
From signup to live agent - no engineers.
10×
Cost reduction
Replace expensive toolchains with one system.
Ecosystem
Plays nicely with everything.
50+ native connectors plus webhooks, REST, and GraphQL for anything custom - your existing stack, orchestrated.
- Slack
- HubSpot
- Salesforce
- Zapier
- n8n
- Twilio
- Stripe
- Shopify
- Gmail
- Calendly
- Notion
- Airtable
- Discord
- Zendesk
- Intercom
- Mailchimp
- Jira
- GitHub
- Google Sheets
- Webhook
- REST
- GraphQL
- OpenAI
- Slack
- HubSpot
- Salesforce
- Zapier
- n8n
- Twilio
- Stripe
- Shopify
- Gmail
- Calendly
- Notion
- Airtable
- Discord
- Zendesk
- Intercom
- Mailchimp
- Jira
- GitHub
- Google Sheets
- Webhook
- REST
- GraphQL
- OpenAI
Solutions
Built for every business need.
How teams across industries use 20X to automate workflows, delight customers, and scale operations - with measurable outcomes from day one.
01Use case
Customer support
Agents handle 80% of tickets across chat, email, voice, and WhatsApp - humans handle the edge cases.
↓ 65% response · ↑ 40% CSATExplore
02Use case
E-commerce & retail
Shopping assistants recommend, upsell, and process returns - integrated with Shopify and Stripe.
↑ 25% conversion · ↑ 35% AOVExplore
03Use case
Appointment booking
Voice and chat agents schedule, reschedule, and confirm bookings around the clock.
↓ 90% no-shows · 24/7Explore
04Use case
Lead qualification
Capture, score, and route leads. Agents engage prospects and hand hot ones to your CRM instantly.
↑ 3× qualified · ↓ 50% CACExplore
05Use case
Internal operations
Automate data entry, reporting, compliance, and cross-team approvals with human-in-the-loop safety.
↓ 70% manual · 0 errorsExplore
06Use case
Onboarding & HR
Guide new hires, answer policy questions, and surface training - from Slack or Teams.
↓ 50% ramp · ↑ NPSExplore
What operators say
Real teams, real hours back.
From lean startups to established operators - here's what changed for teams that put 20X to work.
"We replaced three internal tools and a Zapier maze with a single 20X workspace. Our ops team stopped firefighting - they started designing."
Priya Sharma
Head of Revenue Operations · Northwind Labs
"The consulting team mapped our workflows in a week and shipped four production agents in the next two. I've never seen this pace from an implementation partner."
Marcus Ellery
VP Operations · Basalt & Co
"20X is the first agent platform that felt calm instead of chaotic. My non-technical team owns it now - I get my engineers back."
Diego Fernández
Founder · Fieldnote
Consulting - the shortcut
Work with a 20X expert consultant.
Start self-guided with Explore at ₹4,999 - platform-led, no commitment. Human consulting begins at Start, and each rung above it buys more of our team: implementation, transformation, then your whole organisation.
- Discover - Where agents actually pay off
- Blueprint - The plan, costed in tokens
- Build - Agents wired to your stack
- Deploy - Live, with your team ready
- Operate - Someone owns it every week
Explore
₹4,999one-timeOne session, same day
Platform-led. You work through a guided session and come out with your impact areas named and ranked. No setup, no implementation, no consulting commitment.
Start
₹25,000one-time + ₹9,999/mo2 to 4 weeks, then monthly
Now our team gets involved. We assess the process in detail, run the workshops, validate the opportunity and configure the platform around your first workflow.
Transform
₹75,000one-time + ₹24,999/mo6 to 10 weeks, then monthly
Now you are actually building. Agents, automations and integrations across a whole function, with the business case measured and the process redesigned around it.
Scale
From ₹1,50,000one-time + ₹49,999/moQuarterly programme
Organisation-wide. Multiple functions and workflows, a fleet of agents, governance and analytics, with a named delivery lead who owns the outcome.
- Compare all packages, fees and delivery phases
Built by operators
A calmer way to run a business - from people who've run one.
20X is built by the team at Setoo Solutions Pvt Ltd - operators, engineers, and consultants who spent a decade wiring together CRMs, no-code tools, and duct-taped scripts for real businesses. We built the operating system we wished we'd had.
Every feature ships from that same lens: does this remove a chore, or add one? If it adds one, it doesn't ship.
Pricing
Priced on the work it does. Nothing to decode.
Every package is one pot of tokens. 1 token = ₹3 of usage, a standard voice minute costs 1 token, and that pot is the only cap.
Plans, token wallet and success fee
Business packages
One pot of tokens a month. 1 token = ₹3 of usage, and the pot is the only cap.
8,333 tokens a month · 1 token = ₹3
Transform
Most chosenWorkflows, agents and integrations across a whole function
₹24,999/ month
billed monthly · + ₹75,000 one-time setup
Suits you if: 5-25 staff, a real ERP or CRM, and manual data entry sitting between them
Where the tokens go
1,280 tokens of 8,333 tokens used · 7,053 tokens left
200 minutes
1 token / minute · ₹3200 tokens · ₹600
900 records
1 token / record · ₹3900 tokens · ₹2,700
1,200 messages
0.15 tokens / message · ₹0.45180 tokens · ₹540
0 messages
0.53 tokens / message · ₹1.60 tokens · ₹0
- Integrations
- 3 + one custom
- Numbers / agents
- 2 numbers / 3 agents / 5 concurrent
- Languages
- + 3 regional languages (HD)
- Support
- Priority WhatsApp, 1 business day
Units, rounding and what happens past the pot are answered in the pricing FAQ.
Success & Growth MathWhen Setoo runs marketing or acts as Growth Navigator: what you pay and when.Coming soon
Tokens are the 20X billing unit: 1 token = ₹3. Invoices are raised in INR (+18% GST) by default; USD is shown for reference at ₹95 / $1 and can be billed on request.
FAQFrequently
Frequently
asked.
Everything you need to know about the 20X AI operating system. Still stuck? Talk to a human.
Showing 5 of 41 questions
Platform
20X is an AI operating system for real business operations. Teams use it to build, deploy, and run autonomous voice and chat agents that answer customers, qualify leads, book appointments, chase payments, and complete back-office work across phone, web, WhatsApp, SMS, and email - without writing code. It is built by Setoo Solutions Pvt Ltd and combines agent orchestration, a visual workflow builder, a knowledge base, a built-in CRM, analytics, and 50+ integrations in one workspace.
20X removes the repetitive, high-volume work that limits growth: missed calls and slow first response, unqualified leads sitting in a queue, no-show appointments, order and delivery questions, refund and policy queries, feedback collection, and manual data entry into your CRM. Instead of hiring more agents for every spike in volume, you deploy an AI agent that handles the first 80% end to end and hands the remaining 20% to a human with full context.
A chatbot answers questions. A 20X agent completes work. Each agent has a goal, a knowledge base, tools it can call (transfer a call, hit your API, write to your CRM, send a follow-up), guardrails, and a measurable outcome such as lead qualified, booking confirmed, or ticket resolved. It runs on real telephony with barge-in speech, works in Hindi and English, and every conversation is recorded, transcribed, scored, and costed.
Solopreneurs and one-person businesses all the way up to enterprise teams. A single founder can run 20X alone - the agent becomes the receptionist, the follow-up caller, and the support desk you cannot afford to hire yet. Beyond that, operations, support, sales, and founder-led teams in e-commerce, healthcare, education, real estate, financial services, logistics, and services businesses - typically 1 to 5,000 people - use it to scale coverage without scaling headcount. Agencies and consultants also use 20X white-labelled to deliver AI operations to their own clients.
Answer inbound support calls and chats 24/7, run outbound calling campaigns, and follow up on WhatsApp, SMS, and email from the same agent. On day one it can qualify and score leads, book, reschedule, and confirm appointments, send WhatsApp or SMS confirmations and reminders after a call, run email and messaging campaigns alongside voice, collect feedback and NPS, answer product, pricing, and policy questions from your own documents, transfer to a human when needed, and log every outcome to your CRM through webhooks.
Build & launch
No. Agents are configured from a dashboard using plain-language instructions: describe the job, pick Hindi or English, choose a voice and tone, upload your reference documents, and connect the channels. Non-technical operations teams launch their first working agent the same day, and most reach a live pilot in under an hour.
Build & launch
A first agent is live in minutes using a template for support, lead qualification, booking, or internal operations. A production rollout - knowledge base tuned, call flows tested, CRM webhooks wired, and campaigns scheduled - typically takes one to two weeks. Enterprise deployments with custom telephony, SSO, and compliance review usually run three to six weeks with our team.
Build & launch
Yes. Every agent has a built-in simulator and playground. You can speak or type to the agent in your browser in Hindi or English, replay its reasoning, verify prompt instructions and tool calls, and fine-tune tone, pacing, and escalation rules before it ever handles a live customer.
Build & launch
Yes. Choose from a library of natural voices, adjust speaking speed, set the personality and tone - professional, empathetic, or friendly - script the greeting and closing, define what the agent must never say, and set exactly when it escalates to a human.
Build & launch
Campaigns move through four states: Draft while you configure, Running when live, Paused to stop calls without losing configuration, and Resume to bring the campaign back. Prompts, voices, and knowledge can be updated at any time, and changes take effect on the next conversation.
Language & voice
Hindi and English are fully supported today for both speech recognition and speech generation, including natural Hinglish code-switching within a single conversation. Additional languages are available in beta, and enterprise customers can request priority language enablement.
Language & voice
Any model you choose - the LLM is a configurable setting per agent, not a lock-in. Pick the model in the agent settings and switch it later without rebuilding anything. In practice 20X runs on frontier models from OpenAI and Google Gemini, selected for low latency and accurate reasoning, with GPT-4.1 recommended for most production agents. Speech recognition uses Google Cloud Speech-to-Text and speech generation uses Google Cloud Text-to-Speech.
Language & voice
Conversations run near real time. Low-latency models paired with streaming speech recognition and synthesis keep responses within a natural conversational gap, and full-duplex barge-in means that if a customer interrupts, the agent stops speaking immediately, listens, and responds to what was actually said.
Language & voice
Inbound and outbound phone calls over standard telephony, voice directly in a web browser, and text across website chat widgets, SMS, and WhatsApp. The same agent, knowledge base, and CRM record work across every channel, so the customer never repeats themselves.
Language & voice
A prepaid token balance includes 2 concurrent sessions, and you can buy additional concurrency as your volume grows. Above that, real-world capacity also depends on your telephony provider's configured concurrent-channel and calls-per-second limits, so it scales with the trunk capacity you provision. We help size both during onboarding based on your peak-hour volume, and enterprise deployments regularly run hundreds of simultaneous calls.
Language & voice
The agent triggers the transfer tool and the platform dials your configured destination number and hands the caller over immediately. Because delivery depends on the telecom network, outcomes such as busy, unanswered, or switched-off numbers sit outside platform control, and transfers are executed as direct handoffs without a post-transfer pickup confirmation. Best practice is to pair transfer with a callback or ticket fallback so no customer is lost.
Knowledge & data
Upload your own material - PDFs, product catalogues, price lists, SOPs, policy documents, and existing FAQs - into the agent's knowledge base. The agent retrieves from your approved content when answering, so customers get company-approved answers instead of invented ones, and you update behaviour by updating the document.
Knowledge & data
You decide the fallback. The agent can say it does not know and offer a human transfer, capture the customer's contact details and promise a callback, create a ticket, or send follow-up information by SMS or email. Unknown questions are logged so you can close the gap in the knowledge base.
Knowledge & data
Yes. Configure webhooks in the API section and 20X pushes call and session details - contact, transcript, summary, outcome, and custom fields - into your CRM, helpdesk, or data warehouse in real time. Agents can also call your own REST APIs mid-conversation to check an order, verify a customer, or book a slot. Deeper bi-directional CRM sync is on the roadmap through Workflows; today's webhook and API model already covers most production use cases.
Knowledge & data
Yes. Attach dynamic variables such as name, city, order ID, plan, due amount, or account balance to any contact through CSV upload or single-contact entry. Those variables reach the agent before the call connects, so it opens with the right context instead of asking the customer to identify themselves.
Campaigns
Create a campaign, assign a Hindi or English agent, and add contacts three ways: upload a CSV, paste raw numbers in bulk, or add contacts one by one with name, phone, and email. Every number must include its country code, for example +919876543210. 20X then dials, holds the conversation, answers questions in real time, records the outcome, and pushes results to your systems.
Campaigns
Lead follow-up and requalification of old databases, appointment reminders and confirmations, payment and renewal reminders, delivery and order confirmations, post-purchase feedback and NPS, event and webinar invitations, and win-back campaigns. These are high-volume, script-stable calls where speed of contact matters more than nuance.
Measurement
The dashboard tracks call minutes and average handling time, token and speech API cost per agent, call, and campaign, and success rates by outcome - resolved, lead qualified, transfer initiated, callback requested. Every call and chat is recorded and transcribed with a summary, so quality teams can audit conversations and monitor active calls from the logs view.
Measurement
Teams commonly report first-response time falling from hours to seconds, 60 to 80% of routine contacts fully resolved without a human, three times more leads contacted within the first five minutes, and a sharp drop in no-shows once reminders are automated. The honest answer is that results depend on your volume, data quality, and how tightly the agent is scoped - we set baseline metrics with you during the pilot.
Security
Yes. 20X is ISO/IEC 27001 compliant and maintains a SOC 2-ready posture (SOC 2-ready, not SOC 2 certified) with role-based access control, audit logs, encryption in transit and at rest, human-in-the-loop approval gates, and enterprise SSO as an add-on. We support GDPR and India's DPDP Act obligations, publish an EU AI Act transparency position, and sign DPAs. Recordings, transcripts, and retention windows are configurable, and your data is not used to train foundation models.
Pricing
20X is priced in tokens, not plans: 1 token = ₹3, and a voice minute on the full stack - speech in, speech out, reasoning, and memory - costs about 1.67 tokens. There are no tiers to compare and no bundles to decode: top up tokens and every agent runs from the same balance, paying only for what your business needs. You can estimate any workload with the pricing calculator, and teams above 25,000 minutes a month can talk to us about committed-use discounts. INR is shown at ₹95 / $1.
Pricing
Chats your customer starts are never metered; messages you start are. Replies inside a conversation the customer opened - and the records filed from them - cost 0 tokens, in line with WhatsApp's 24-hour customer service window. Messages you initiate are counted by category: utility updates and follow-ups at the utility rate, marketing campaigns at the campaign rate. Sending pauses at your allowance until you approve the extra, so nothing runs up a bill unannounced.
Pricing
Four metered units, all priced in tokens at ₹3 a token. One call minute is a minute of the agent speaking, inbound or outbound. One record is a complete file the agent captures - an order, a listing, a lead, a booking. One utility message is a single one-way update you send after something happened. One campaign message is a single promotional message you start. Chats, comments and DMs a person starts - and your replies inside WhatsApp's 24-hour window - are 0 tokens and unlimited.
Pricing
A package pot is a monthly allowance and resets at the start of each billing month; top-up tokens you buy on top of it stay on the balance while the account is active. You can move up a package at any time and only pay the difference in setup fee between the two rungs, and you can move down at the next billing month.
Pricing
Call time is rounded up to the next whole minute per call, so a 40-second call bills one minute. Messages are never split - each send is one unit at its published rate, even though a utility message costs a fraction of a token. Fractional rates are kept at full precision while the month is added up, and only the monthly total is rounded to the nearest whole token on the invoice.
Pricing
Nothing lands unannounced. We warn you as the pot nears empty, and when it is empty outbound work - calls you place, utility and campaign messages you send - pauses until you approve a top-up. Chats your customers start keep working and stay free. You then approve a top-up pack (₹2,000 · 667 tokens, ₹5,000 · 1,750 tokens +5%, ₹12,000 · 4,400 tokens +10%) or move up a package. No overage is ever billed without your approval.
Pricing
You can start free and run real calls rather than a demo. Because 20X is fully prepaid, there is no plan to cancel: top up tokens when you need capacity and stop when you don't. Tokens stay on your balance for 12 months from purchase, and refunds follow our published refund and cancellation policy.
Pricing
Yes - through the 20X partner programme: on-premise or VPC deployment under your own brand and domain, with reseller and multi-client workspaces for agencies and consultants. See the partner programme page, or a 20X consulting engagement can scope a dedicated deployment with you.
Pricing
Both paths work. Most teams self-serve with templates and the visual builder. If you want speed, a 20X expert consultant runs one method - Discover, Blueprint, Build, Deploy, Operate - so you go live with proven flows instead of experiments.
Pricing
Four rungs, published upfront. Explore is ₹4,999 for a self-guided discovery session on the platform - no setup, no implementation, no consulting commitment. Start is ₹25,000 one-time plus ₹9,999 a month for guided implementation, and this is where our team gets involved. Transform is ₹75,000 plus ₹24,999 a month for real AI workflows, agents and integrations. Scale starts at ₹1,50,000 plus ₹49,999 a month for organisation-wide transformation with governance and analytics. Platform tokens are billed separately (1 token = ₹3).
Pricing
One promise: in one session, you know where AI could create value in your business. Explore is platform-led and self-guided - you work through a structured discovery session and come out with your potential impact areas identified and your opportunities prioritised, in writing. It does not include a quantified ROI model, because real ROI needs your actual business data and deeper discovery; that work belongs in Start and Transform. There is no setup, no implementation and no consulting commitment, and the fee is credited into a Start engagement begun within 60 days.
Pricing
One-time fees are billed 50% upfront and 50% on go-live, with scope fixed in writing before work starts. The monthly fee on Start, Transform and Scale begins at go-live and is cancellable with 30 days notice. Add-ons such as extra integrations, voice or language variants, and team training are quoted before work begins, never added afterwards.
Pricing
Yes. 20X runs a three-route partner programme. Referral partners join free and earn 20% of a client's net token spend for 12 months. Reseller partners pay $499 a month (waived above 23,75,000 tokens a month) and buy tokens 25-40% below list. White-label partners pay $2,500 one-time onboarding plus $1,500 a month, ship 20X under their own brand and domain, and buy tokens 35-45% below list. On-premise and VPC deployments are scoped through consulting.
Pricing
Margin is earned on performance, not negotiated. Your rolling three-month token volume across all clients sets the tier: Authorised up to 4,75,000 tokens a month (25% reseller / 35% white-label), Silver 4,75,000-23,75,000 (30% / 38%), Gold 23,75,000-95,00,000 (35% / 42%), Elite above 95,00,000 (40% / 45% with custom terms). Tiers are reviewed quarterly, upgrade immediately, and never drop more than one step at a time.
Pricing
Referral commissions are calculated monthly on collected net revenue and paid within 30 days of month close, with a $100 minimum payout that rolls forward. Resellers and white-label partners buy wholesale tokens on net 30 invoices and keep whatever they charge their client above that. Services you deliver yourself are 100% yours; builds 20X co-delivers split 70/30 in your favour.
Pricing
Reseller and white-label partners contract with, bill, and support their own clients - 20X stays behind your brand and provides second-line support. Registered deals are protected for 90 days, and 20X will not bypass a partner on a protected registration. Referral partners hand the account to 20X and still earn on it for 12 months.
ReadyReady to 20X
Ready to 20X
your productivity?
Ship your first autonomous agent in under five minutes, or let a Setoo consultant design the whole thing with you.