Productivity - Setup Guide

How to set up Ada

Otto's honest, no-fluff walkthrough. Every step here is what we'd actually do if we were sitting at your keyboard. Real gotchas first, real steps second, and a link to the personalized version at the bottom.

Read these before you start

• Non-obvious gotcha: Ada's pricing model charges per conversation the AI handles, regardless of whether it actually resolved anything. A conversation that ended in "let me connect you with a human" is billed the same as a full resolution. The published "resolution rate" is meaningful, but the billed usage number is not the same as the resolution number. Contract negotiations should pin down billed-event definitions (opened conversation vs. AI-attempted vs. AI-resolved) explicitly, or year-2 renewal budgets will surprise you.
• Enterprise contracts routinely include usage overage clauses that trigger above the initial commit
• Implementation timelines slip; budget 30% more than the sales team's estimate
• Ada does not build the AI knowledge for you; garbage-in-garbage-out applies to the retrieval corpus
• The 40 to 70% deflection numbers Ada cites are best-case; real deployments often land 20 to 45% initially

The 7-step setup

1. 1

   Create your Ada account

   Sign up at the link below. Card required for the paid tier - most plans include a trial period; check the pricing section on this page first so you know what you're committing to.

   Open Ada signup
2. 2

   Complete the initial onboarding

   Skip the marketing questionnaires when you can. Fill only the fields that actually configure the product - name, timezone, your first workspace or project. If Ada pushes you into a setup wizard, take it - it usually accelerates the first productive session.

3. 3

   Connect your existing tools

   Wire Ada into the rest of your stack. The integrations that most people set up first: Salesforce Service Cloud, Zendesk, Freshdesk, ServiceNow, Kustomer, Genesys, Talkdesk, Twilio Flex, Amazon Connect. CRM (Salesforce, HubSpot). Data warehouses (Snowflake, BigQuery). Custom API integrations to backend systems (order status, account management, shipping). Voice channel via IVR integra.... Do these before importing data - clean integration first, data second.

4. 4

   Import your existing data (only what you'll actually use)

   Do NOT bulk-import everything. Import the last 30 days of the ONE workflow you're moving over first. Prove it works. Then import more. Big-bang migrations are how Ada deployments die in month 3.

5. 5

   Set up your first real workflow

   Pick the single most-frequent task you'll do in Ada - the daily-driver workflow. Configure it end-to-end. Use it live for a week. Do not touch any other feature yet. Adoption failure comes from teams trying to use everything on day one instead of the one thing that actually pays.

6. 6

   Add your team (if applicable) and set access

   Once your solo workflow works, invite one teammate at a time. Watch them use it. The friction points you missed are the ones they hit. Fix those before scaling to more users. Never invite 20 people at once - you'll get 20 confused people and 0 useful feedback.

7. 7

   Compound with the right pairings

   Recommend Ada when: business_size is 500+, industry is B2B SaaS or ecommerce or fintech, current support volume is 300K+ contacts per year, and pain_points explicitly include "we need to reduce cost per contact" or "we cannot scale support headcount." Do NOT recommend for SMBs, solo, mid-market under 500 employees, or anyone under $30K/year AI-CX budget. If the user is even asking about Ada without those signals, redirect them to Intercom Fin ($0.99/resolution), Chatwoot Captain AI, or a proper ...