Replacing Intercom with an AI Chatbot Named After a Westworld Character

title: "Replacing Intercom with an AI Chatbot Named After a Westworld Character" date: "2026-01-21" author: "Benjamin Thomas" excerpt: "We set out to build a chatbot. What we actually built was the foundation for a voice AI system, because the current AI answering service market is kind of crappy." tags: ["AI", "product", "SaaS-replacement"] published: true coverImage: "/images/dolores-avatar.png" slug: "dolores-intercom-replacement"

Part of the weekly series: Replacing SaaS One Product at a Time

We set out to build a chatbot. What we actually built was the foundation for a voice AI system, because the current AI answering service market is kind of crappy right now and we figured we'd need one eventually.

Meet Dolores.

Why "Dolores"?

When you're naming your company's first AI product, you don't want something boring. We spent a session brainstorming "edgy sci-fi names" and Westworld was definitely on the inspiration list. The personality we landed on: Duolingo meets introspective sci-fi robot with Westworld undertones.

She's helpful. She's a little mysterious. She might be gaining sentience. Results may vary.

The AI Stack (Yes, We Have Strong Opinions)

Here's what we used to build this:

Grok - Brainstorming the name and personality. We're Westworld fans so we leaned into it. Grok came up with the list of edgy sci-fi names.
Claude Code - All the execution and implementation strategy. This thing is becoming our default development environment for anything complex.
ChatGPT/Gemini - Image generation and recognition. We hate to say it because that's the most utility we're getting out of them. We've been burned by Gemini too many times on code. But these two excel at anything visual and handling huge amounts of upfront context.

The actual model running Dolores? Opus 4.5.

We don't know why you would build anything customer-facing at this point that isn't using Anthropic. The reasoning capability, the ability to follow complex instructions, the natural conversation flow - it's just better for this use case.

What Dolores Actually Does

1. Scheduling (Goodbye, Calendly)

This is the feature we're most proud of. Dolores doesn't just dump a booking link on you. She actually:

Looks up team member availability in real-time
Schedules directly on the calendar
Makes modifications without the whole "please click this link to reschedule" dance

You know those annoying booking experiences where you click a link, pick a time, fill out 14 fields, and then find out the person actually can't make it? Yeah, none of that. Dolores handles scheduling like a real assistant would.

2. Site Knowledge

We dump all our site data into blob storage. Dolores indexes it. Now she can actually help people find stuff on our site instead of the typical chatbot "I don't understand, here are some links" experience.

3. Profile Cards

Want to know about a specific team member? Ask Dolores. She's got employee profiles loaded and can surface them naturally in conversation.

4. Contact Form Submission

Forms through conversation. Revolutionary? No. But way less friction than making someone hunt for a contact page.

5. Coming Soon

Resume submission (for job applicants)
Email escalation (when Dolores is out of her depth)

The Math That Made Us Build This

Let's talk numbers. 4 seats, apples to apples:

Intercom: $29-39/seat/month for Essential = $116-156/month. Plus $0.99 per AI resolution. Plus add-ons. You're easily looking at $200+/month.

Calendly: $10-16/seat/month = $40-64/month.

Combined: $240-300+/month for chat and scheduling.

Dolores: Cents. Literal cents per month in API costs. The Opus 4.5 API is priced per token, and most conversations are short. We're talking maybe $5-10/month in actual usage for a site our size.

We're not saying Dolores replaces Intercom for everyone. If you need a full customer support platform with ticketing and team management, Intercom does that. But if you just need a chatbot that can actually help people and book meetings? You're paying $300/month for something that costs pennies to run yourself.

The Honest Assessment

Let's be real: there's some hallucination happening. We've seen Dolores get creative with information she shouldn't have. This is the current state of LLMs and anyone who tells you otherwise is selling something.

But here's the thing - it's a bit of a playground right now. We expect the accuracy to improve as we see more usage patterns and can tune the prompts accordingly. That's the whole point of shipping early.

The Ask

Please come put her through her paces and let us know your feedback.

Seriously. Go to forit.io, test Dolores out, ask weird questions. This is a pet project - one of about 12 tmux sessions we have running parallel development streams right now. The more edge cases we see, the better she gets.

Full Disclosure: The Data and The Dev Time

Two things worth mentioning:

The data: Conversations with Dolores get logged anonymously. This helps us improve her responses over time and will inform future training. No PII gets stored, but the interaction patterns are valuable.

The dev time: "But what about the hours you spent building this?" Fair question. This took about two hours to stand up. Even if you value that time generously, it's a one-time cost. Compare that to $300/month in perpetuity. The math still works.

We've got more writing coming about this whole experience - the costs, the workflow, what it's actually like to run an agency on AI-assisted development.

Want This for Your Site?

Here's the sales hook: we do this for clients too. If you want AI modernization of your site - a Dolores of your own - we can do rapid deployment of stuff like this.

The tech is ready. The tooling is there. The question is whether you want to be the company that deployed conversational AI in Q1 2026 or the company that's still paying for Intercom in 2027.

Ben Thomas is the founder of ForIT and spends most of his time running 12 tmux sessions in parallel.