FAQ
The questions
people ask.
Direct answers about my work, background, and availability.
Process & collaboration
What does engaging you look like: intro call, scoping, first 30 days?
Every engagement starts with a free 30-minute intro call. We use it to check fit. If we go ahead, discovery runs 2 to 4 weeks. You get a written proposal within a week of that call. The first artifact lands in the first month. That might be a friction map, an intent taxonomy, or an eval harness. No mystery. Every retainer has an end date. I don't bill for status meetings.
What's your process on a new engagement?
I call it Thoughtful Execution. It is how I run a project. I identify the friction points. I test approaches on real work. I keep what moves the metric. I watch how the work flows for two weeks before I propose a change. Then I run small tests, each with a way to roll back. I want the data that says a change works.
How do you measure success?
I ask the same question your users do: did it work? I track containment, latency, satisfaction, and cost. If a number moves and the user's job did not get easier, I treat that as a warning. I also check whether the system still works after I leave. The rituals, documents, and handoff specs have to survive me.
What does a successful engagement look like six months in?
Measurable eval improvements on the flows that move your north-star metric. A documented intent taxonomy your product team can reason about without me in the room. An internal playbook (prompts as versioned specs, eval rubrics, escalation rules) your designers and engineers can run without another consultant. If six months in your team still needs me to be the smartest person on the call about your own AI, I failed.
Do you work solo, or with a team?
Almost always with a team. My job is to make your existing engineers, data scientists, designers, and product leads more effective, not to replace them. My role is the translation layer. I sit between people who speak past each other. I turn business needs into specs, and model outputs into user experiences.
How do you handle disagreement with engineers?
I don't fight engineering constraints. I treat them as design opportunities. "We can't do that" almost never means the user problem is unsolvable, it means the specific approach we brought isn't the one that fits the constraint. I find a different one within bounds.
Craft & tools
Do you code, or only design?
I do foundational coding. I'm comfortable in JavaScript, Python, and SQL, and I pair heavily with Claude (Anthropic) and other AI tools to move faster without losing intent. I'm not here to replace your engineers, but I'll never be the person who can't read what your team is building.
Why do you prefer Anthropic / Claude?
Three reasons. One: Claude's writing shows more restraint, which matters in customer support. Two: in the long support chats I run, Claude's tool-use holds up. Three: Anthropic publishes research I use (AI Fluency, constitutional AI, evaluations). I still build on the stack the team already runs. I have worked in Dialogflow CX, Azure AI Foundry, and AWS Bedrock. The orchestration around the model matters more than the model name.
What's the tech stack you gravitate toward?
Multi-agent orchestration (role-specialized agents with a thin orchestrator), prompt architecture as versioned specs (not prompt strings in production), LangFuse for observability, and eval harnesses built on day one, not bolted on later. Day-to-day I live in Claude (Sonnet and Opus), Cursor, Figma, Dialogflow CX, Azure AI Foundry, and AWS Bedrock. I use Notion for specs, GitHub for everything else.
What tools and models do you use day-to-day?
Claude (Sonnet for most work, Opus when the reasoning matters), Cursor for pairing, Figma for flows, LangFuse for traces and evals, Astro for this site. On client stacks I work in Dialogflow CX, Azure AI Foundry, AWS Bedrock, and whatever prompt-orchestration layer the team has already committed to. The tool matters less than the evaluation harness around it.
What's your hot take on 'agents'?
Most agents are workflows with a language model inside. That is useful. The word agent still does a lot of extra work. The value is in orchestration: the model does cross-system work people used to do by hand. My orchestration case study shows why.
Path & perspective
Why conversational AI specifically?
I'm a natural conversationalist. I enjoy the spoken and written word, always have. Coming from hospitality, I learned that every word is intentional, that reading the room is a technical skill, and that the difference between "understood" and "felt understood" is where real experience lives. Conversational AI is that exact problem at scale. The interface is the writing. The writing is the product. I don't have to choose between my favorite things.
Your path is non-traditional, how does that affect your work?
I went from a GED, to hospitality, to workflow work, then to conversational AI. I learned to talk with people who don't share a vocabulary. That is the job now. I write so people outside the field can follow. That includes accessibility.
Fit & scope
Who do you work best with?
Teams who already have something in production, know where it's falling short, and want a partner who will tell them the truth about why. I'm less useful to teams who want a vendor to rubber-stamp what they've already decided.
Who do you not work with?
Projects that exist to launch a press release, not to serve a user. Companies launching AI they'd be embarrassed to show to their grandmother. I've done the work of building for real people at scale; I'm not going to unbuild it on a side project.
How big an engagement will you take? Minimum and maximum?
Best fit for 3-12 month retainers where we can build, measure, and iterate. I also take 2-4 week diagnostic sprints when a team needs an outside read before committing to a larger build. I don't take multi-year vendor contracts; by year two you should have internalized the playbook.
Do you run workshops or team trainings?
Yes. Half-day and two-day formats on eval-driven conversation design, intent taxonomy, prompt architecture as product spec, and multi-agent orchestration. Audiences range from product and design teams to ops leaders who need to understand what AI can and can't do for their workflow. Email for topics and availability.
Do you offer 1:1 coaching or portfolio reviews?
I don't take open-ended 1:1 mentorships. My calendar won't support it. I do host occasional paid portfolio reviews for conversation designers transitioning into AI product work, usually in cohorts. Meanwhile, the ICX blog and the essays on this site cover most of the ground I'd repeat on a call.
Can you help with my AI strategy if I'm pre-product?
Sometimes. The bar is whether I can point at a user problem worth solving. If you have that, I can help shape what to build. If you don't, I'll tell you that before I take your money, and point you toward finding it.
Logistics & terms
How do I hire you?
Book a free 30-minute intro call from the Contact page, or email [email protected] with a one-paragraph brief. Engagements run through Intelligent CX Consulting, LLC at https://intelligentcxconsulting.com. Either path lands on my desk and I respond within two business days.
Are you open to full-time roles, or just consulting?
Both, honestly. I run consulting engagements through Intelligent CX Consulting, and I'm open to the right full-time role in conversational AI design, AI product, or applied AI. The resume is at christi.io/resume. For roles, email [email protected] with the team and the problem you're hiring for, and I'll reply within two business days.
Where are you based and do you travel for work?
Dallas-Fort Worth, Texas. I work remote with US clients by default. The Texas Triangle covers most of my in-person work. I travel quarterly or by request for workshops, on-site design sprints, and conference talks. International engagements are case-by-case, typically as remote advisory with one or two in-person weeks.
What's your rate structure: hourly, project, or retainer?
Retainer by default for multi-month work. Fixed-scope pricing for 2 to 4 week diagnostic sprints. Hourly only for expert-witness work or board advisory, when the hours are hard to predict. I share numbers by email. I don't negotiate rates in public.
How do you handle NDA and references to past clients?
Everything on /work has been scrubbed or approved for public reference. Specific client attributions are available on request and usually fine once we've signed mutual NDAs. I won't share confidential metrics, internal documents, or team names without written permission, even on calls with prospects. I expect the same courtesy for your project.
Do you work with agencies or subcontract?
Yes. I partner with a small set of design studios and data-science consultancies where a conversational-AI specialist is missing from their bench. White-label is fine if the end client knows a specialist is in the room and I can speak to them directly during scoping. I don't take work where the agency needs me to pretend I'm full-time staff.
Can I reference you in a case study if we work together?
Yes. I want to write about the work too. My default is an anonymized write-up after launch, unless we agreed otherwise while scoping. I won't use your logo or name without written sign-off. If the work is under a strict NDA, I still want one public line we both approve, such as "about $2M in estimated annual support savings, an estimate, not audited." We agree on the words before anything goes live.
What about speaking, writing, or advisory roles?
Yes to speaking, writing, and advisory work. I speak on conversational AI, orchestration, content engineering, and eval-driven product work. I write here and on the ICX blog. I take quarterly advisory roles when a team wants a named expert in the room. Send the date, the audience, the format, and the budget. I reply within a week.
Work with me
Two ways to work with me.
Consulting through ICXA few consulting engagements each quarter through Intelligent CX Consulting . Start at services.
Hiring ChristiOpen to conversational AI, AI product, and applied AI roles. View my résumé.