20M+
Users served by AI Christi has designed
40%
Customer satisfaction lift
8
Global markets served

These results come from Christi's enterprise work before she founded ICX. See the work behind each number →

“We need a chatbot that actually answers questions.”

Conversation design

Conversation design is the work of writing the words, flows, and rules a chatbot or voice agent uses with a customer. ICX designs each conversation so the bot answers the question the first time, in the customer's language, on the channel they already use. That means planning not just what the bot says, but when it answers, asks, verifies, escalates, or hands off. This is ICX's Behavior Decision Set.

What you get

  • Conversation flow documents and intent maps (the logic that decides what the bot should answer)
  • Dialog scripts with a consistent tone and personality
  • Escalation paths (how the bot hands a customer to a person)
  • Testing setup and conversation tracking
  • Support for multiple languages
A designed customer conversationA short chat flow. The bot asks for an order number, gives tracking, then offers a live agent.My order is late.ASKWhat is your order number?It is 4821.ANSWERIt left today. Here is tracking.HAND OFFWant me to add a live agent?
Every turn is designed. The bot answers, asks, or hands a customer to a person.
“We need AI answers that sound like our brand, not a robot.”

Prompt engineering and LLM consulting

Prompt engineering is the work of writing the instructions that control a large language model (LLM) in production. Not every job needs an LLM. ICX starts with the Determinism Map, which decides rule-based, LLM, or hybrid per intent. Then ICX writes the prompts and guardrails that keep answers accurate and on-brand. ICX tests every prompt against real examples before launch.

What you get

  • System prompts (the master instructions that set the AI's role and limits) and prompt libraries for reuse
  • Prompt tests and evaluation sets that score AI quality before launch
  • Retrieval-augmented generation (RAG) pipelines, the setup that lets AI answer from your own data instead of guessing
  • Output reviews and guardrail design (the rules that block off-brand or unsafe answers)
  • Example sets and tone tuning so answers sound like your brand
From question to tested answerA simple flow. A customer question and your data feed a prompt with guardrails, then a tested answer.Customer questionYour dataPrompt + guardrailsyour rules, your voiceTested answer
ICX writes the prompt, adds guardrails, and tests it before launch.
“We need an AI plan that ties to real business results.”

CX strategy

CX strategy is the plan for what to automate, what to leave to people, and how to measure the difference. ICX builds that plan and ties it to numbers your leaders already watch: containment rate, CSAT (customer satisfaction score), handle time, and cost per contact. ICX then rolls the plan out across teams. Part of that plan is the State Ledger: what the system should remember, update, expire, and clear. That way the AI acts on what is true right now.

What you get

  • CX roadmaps tied to business goals
  • Workflow design and automation planning
  • User research summaries and customer personas
  • Workshops that get stakeholders on the same page
  • Metrics that show adoption and success
From plan to measured resultsA flow from choosing what to automate, to a roadmap, to rising results.What to automateWhat people handleCX roadmapResults we trackStartLiveTuned
ICX chooses what to automate. Then ICX tracks the numbers your leaders watch.

How can teams work with ICX?

ICX offers two ways to work: an embedded team extension for ongoing work, and project-based consulting with a defined scope.

Embedded team extension

ICX joins your product, engineering, or CX team as a dedicated AI specialist. That means working inside your standups, sprint planning, and cross-team projects. This fits teams that need ongoing, hands-on help.

  • Works inside your tools and rituals
  • Set hours per week or month
  • Best for multi-month work

Project-based consulting

ICX runs a defined project with clear milestones. This fits teams that need one specific outcome: a chatbot design system, a prompt audit, a CX roadmap, or an agentic AI readiness review.

  • Set scope, timeline, and deliverables
  • Milestone reviews and approvals
  • Most projects run 4 to 12 weeks

How ICX runs a project

ICX runs every engagement in three phases: Discovery, Design and Build, and Measure and Optimize. Each phase ends with a review with you.

1

Discovery

ICX learns your users, your tech stack, and your goals. ICX defines what success looks like with you before any building starts.

2

Design and Build

ICX writes the prompts and designs the flows. You review at every milestone.

3

Measure and Optimize

ICX tracks performance with real data. ICX keeps tuning until the numbers prove the value.

What is agentic AI readiness?

Agentic AI is AI that can plan a task, make decisions, and take actions on its own. Before you hand it real work, your data, your rules, and your existing chatbot setup have to be ready. ICX runs the review that tells you whether they are ready and what to fix first. That review treats the riskiest moves (stop, escalate, hand off) as deliberate decisions, not accidents. See the full Conversation Behavior Framework.

AI governance and guardrails

ICX sets the rules that decide what an AI agent is allowed to do. ICX builds the checks that catch it when it goes off script. ICX also defines who reviews what, so every action can be traced and explained.

Data readiness review

An AI agent is only as good as the data it can reach. ICX checks whether your data is clean, fast, and accessible enough for an agent to use reliably. ICX flags the gaps.

Agent orchestration strategy

ICX designs how several AI agents split up a complex job and hand work to each other. ICX also decides where a person must sign off before anything high-stakes goes through.

One framework behind every service

ICX runs every engagement through the Conversation Behavior Framework: four lenses that turn AI design judgment into something a team can review and test.

Determinism Map

Rule-based, LLM, or hybrid, decided per intent on latency, channel, memory, backend access, and compliance. See the lens →

Behavior Decision Set

The seven moves an assistant can make on any turn: answer, ask, verify, repair, stop, escalate, hand-off. See the lens →

State Ledger

What the system keeps, updates, expires, and clears, so AI acts on what is currently true. See the lens →

Turn Rhythm

Pacing and turn-taking that make a bot sound natural, because rhythm matters more than casual wording. See the lens →

Have a project in mind? Let's talk.

Get in Touch

Have questions about our process? See our FAQ.