Chatbots that know what they don’t know.
We build production chatbots for support, sales, and ops — grounded in your knowledge, eval-tested before launch, and honest enough to escalate when they should.
What’s your cancellation policy?
30 days notice, prorated refund. Last day of access is your billing-cycle end.
Can I get an exception on the annual plan?
Worth a quick chat. I’ll route you to your account team.
Why chatbots embarrass companies.
Two ways chatbots embarrass you. Either they escalate everything to a human, which defeats the point, or they confidently lie, which is worse. The fix isn’t a bigger model. It’s grounding answers in your knowledge, evaluating before you launch, and shipping a fallback policy that knows when to hand off. We build the kind that doesn’t get screenshot-shamed on Twitter.
The bot made up a refund policy that doesn’t exist anywhere in the company docs. A customer screenshotted it.
Almost every question went to a human. The bot became a dressed-up contact form.
Confident answer delivered without a source. Engineers can’t reproduce, users can’t verify, audit fails.
Four shapes, one founder-led team.
Support chatbots with deflection
Resolve repeat questions automatically with citation-backed answers. Escalate to a human when confidence drops.
Sales qualifiers
Pre-qualify leads, capture intent, and route to sales with a hot summary attached.
Internal ops assistants
Chatbots that know your runbooks, SOPs, and internal docs. Save your team from re-explaining the same things.
Knowledge base companions
Conversational search across your documentation, with the receipts. Replace "where is that doc?" Slack messages.
See case studySide-by-side with a typical agency.
We don’t outbid the cheap shops, and we don’t pretend to be McKinsey. Here’s where the real practical difference lives.
The exact tools and why we chose them.
No mystery stack, no platform lock-in. You see what we use, you read why, and you own the keys on day one.
Best at refusing what it doesn’t know — the right default for an honest chatbot.
One database for vectors, BM25, and your domain. No extra vector store to maintain.
Branded to match your site. Streaming, accessible, mobile-first.
Auto-indexed from your docs, PDFs, Notion, Confluence, or APIs.
Adversarial test set on real questions before every deploy.
Track answer quality, escalation rate, and what users actually ask.
Discover · Architect · Build · Ship.
Four stages, named timelines, named deliverables. No open-ended discovery. No moving goalposts.
Discover
We audit your knowledge sources, your top 50 questions, and what good escalation looks like.
- Top-50 questions audit
- Knowledge source map
- Escalation policy
Architect
We design retrieval, prompts, evals, and the escalation policy — and write the evals before writing the bot.
- Prompt + retrieval spec
- Escalation policy
- Eval suite
Build
Sandbox first, then production. Iterate against the eval suite, not against gut feel.
- Chatbot on staging
- Eval pass rate >95%
- Branded UI integrated
Ship
Cutover during a quiet hour. 60 days of fixes are included.
- Production cutover
- Analytics + escalation tracking
- 60 days of fixes
In production
Lawyers needed contract analysis they could trust, where a flagged clause comes back in a fixed shape the product can act on.
Structured output checked against a zod schema on every analysis call, jurisdiction carried into the prompt, and an adversarial prompt that argues the other side of a clause.
In production through 2023 and 2024, built with a product team of about thirteen. We quote no user or speed numbers until they are sourced.
Fixed price. Fixed scope. Public ranges.
Start with a free call. The free audit ends in a fixed quote in writing.
- Custom chatbot grounded in your knowledge
- Branded chat widget on your site
- Eval-tested before launch
- Production deployment
- 60 days of fixes after launch
- Fully customized to your operations
- Multi-source knowledge, complex flows
- CRM and helpdesk integrations
- Optional support after launch
The questions we actually hear on calls.
How long does a chatbot take to ship?
A focused pilot ships in 2 weeks. A multi-source production chatbot with CRM integration ships in 3–4 weeks.
Can it actually deflect support tickets?
Yes, if the questions are knowledge-answerable. Deflection depends on your knowledge base completeness and how clearly users ask. We measure deflection from week 1 and tune the answer set monthly.
How do you stop it from hallucinating?
Retrieval-first prompting with citation enforcement, an eval suite tested before every deploy, and a fallback policy when confidence drops below threshold. The bot says "I don’t know" rather than lying.
Does it integrate with our helpdesk or CRM?
Yes. We integrate with Zendesk, Intercom, Front, HubSpot, Salesforce, and any system with an API. The chatbot can create tickets, search your CRM, and pass context to humans.
Can we use it in multiple languages?
Yes. Modern LLMs handle many languages well, including Spanish and Arabic. We add language detection so each person gets answers in their own language.
Do we own the chatbot?
Yes. Code, prompts, and evals live in your account. We use Claude — you hold the API key. No platform lock-in.
Good chatbots don’t pretend to know everything. They route to humans when they should and answer with citations when they can. We build the kind your users actually want to use — and your team can trust.