In my role leading product teams, the AI product roadmap isn’t just a plan—it’s the operating system for how we discover value, prioritize with rigor, and ship with confidence. The pace has changed, the stakes are higher, and the best product managers are now orchestrating AI capabilities, data, and customer insight in near-real time.
Master the evolving art of the AI product roadmap. Prioritize smarter, turn data into direction and insight into action, only much faster.
When I say “AI product roadmap,” I’m talking about a living system that blends strategy, discovery, and delivery. It’s less about dates and more about outcomes, risk reduction, and sequencing learning. In practice, that means combining AI Strategy with product roadmapping and sprint planning, then validating each bet with real customer signals.
For prioritization, I anchor on outcomes vs output OKRs and connect them to measurable signals across the funnel. Continuous discovery keeps insights flowing, while a unified approach to analytics and retention analysis tells me where the lift is. This lets me rank initiatives not just by impact and effort, but by how quickly we can learn, iterate, and compound value.
On discovery, product trios are non-negotiable. We prototype early with gen ai and LLMs for product managers to accelerate concept validation and reduce ambiguity. When customers can co-create through in-app guides or lightweight product tours, we turn vague needs into crisp problem statements and testable hypotheses far faster.
On delivery, I pair tight feedback loops with experimentation. A deliberate cadence of A/B testing and strong instrumentation ensures we’re learning every sprint, not just launching. The goal is to de-risk decisions quickly, keep momentum high, and translate signals into roadmap movement without thrash.
Under the hood, the AI stack matters. I rely on a retrieval-first pipeline to ground models in trusted data, and I’m intentional about privacy-by-design and data governance from day one. As agentic AI patterns emerge, I put evaluation workflows in place so we can ship confidently—and safely—without slowing down innovation.
Finally, alignment is the multiplier. Clear narrative roadmaps tied to customer outcomes help stakeholders see trade-offs, while crisp interfaces with go-to-market and CRM integration close the loop from roadmap to revenue. When everyone can trace a line from AI strategy to shipped value, prioritization becomes easier and trust grows.
If you’re feeling the acceleration, you’re not alone. With the right AI product toolbox—rooted in discovery, grounded in data, and delivered through tight feedback loops—you can move faster, learn smarter, and build products your customers can’t live without.
By 2026, the AI Product Owner will be the keystone role that turns AI strategy into measurable business outcomes. In my teams, this seat bridges market insight, model capability, data governance, and shipping velocity—so product decisions are not just clever, but compliant, reliable, and fast.
I often describe the remit simply: "Here is your clear guide to the AI product owner role (skills, responsibilities, how it differs from PM) and ways AI tools supercharge delivery." In practice, the AI Product Owner translates business goals into model-backed experiences, aligns cross-functional execution, and ensures the product’s AI behavior remains safe, lawful, and on-brand under real-world constraints.
How does this differ from a traditional PM? While Product Management sets portfolio strategy, positioning, and market narratives, the AI Product Owner owns the AI experience end-to-end—data readiness, evaluation harnesses, safety guardrails, and the iterative model improvements that drive outcomes vs output OKRs. I anchor the role inside empowered product teams and product trios (PM/Design/ML Eng) to keep discovery continuous and delivery disciplined.
On responsibilities, I expect four pillars. First, discovery: continuous discovery with customers and internal experts to uncover use cases where generative AI or LLMs beat the status quo. Second, experience: define the right interaction patterns for AI UX, including retrieval-first pipeline choices, context window management, and feedback loops for human-in-the-loop correction. Third, governance: privacy-by-design, AI risk management, data governance, and regulatory compliance baked into the roadmap. Fourth, delivery: CI/CD for models and prompts, observable evaluation with A/B testing and minimum detectable effect (MDE), and SRE-grade incident management when AI behavior drifts.
Skills-wise, I look for product sense plus technical fluency. That includes LLMs for product managers (prompting, grounding, RAG), analytics mastery (Amplitude analytics, retention analysis, activation metrics), and comfort with DORA metrics and deployment frequency to keep iteration high but safe. Strong stakeholder management and clear writing are non-negotiable—AI capabilities evolve fast, and leaders must see risk, cost, and ROI with no ambiguity.
AI tools truly supercharge delivery when they eliminate bottlenecks. My practical stack: an AI product toolbox with Claude Code and a ChatGPT connector for rapid prototyping; CustomGPT workflows for support triage and internal knowledge; Pendo product tours and in-app guides to validate behavior changes; Intercom for customer support ai strategy; and tight CRM integration via HubSpot to measure revenue impact. The outcome is faster idea-to-learning cycles, sharper telemetry, and far cleaner handoffs.
For roadmapping, I prioritize thin slices that prove value early—shipping narrowly scoped assistants or copilots, then expanding with product roadmapping and sprint planning that ties capability unlocks to outcomes. A unified analytics platform helps compare human-only baselines to augmented workflows, while agentic AI patterns automate routine steps under strict guardrails.
Risk is a product surface, not a side task. I require explicit policy gates (PII handling, red-teaming, bias audits), clear escalation paths, and incident playbooks. When we treat policy and reliability as features, customers reward us with deeper adoption and higher trust.
If you’re pursuing the AI Product Owner path, build a portfolio around shipped learnings: the experiment you killed with data, the safety constraint you designed, the postmortem you led, and the business metric you moved. That story—evidence of disciplined discovery, responsible delivery, and real-world results—is exactly what teams (and boards) want to see in 2026.
I’m stepping into 2026 with a practical playbook for marketing analytics—one forged at the intersection of product management, go-to-market strategy, and AI Strategy. My lens is simple: connect data to decisions, decisions to outcomes, and outcomes to revenue. If you’re serious about product-led growth, this is the year to turn your unified analytics platform into a true competitive advantage.
Start 2026 off with a bang with exclusive insights and predictions from some of marketing analytics’ most influential voices. See what they have to say.
The biggest shift I expect is from channel-centric dashboards to journey-centric systems that stitch together product usage, CRM integration, and campaign performance. When Amplitude analytics or Pendo data sits alongside HubSpot pipeline metrics, we stop arguing about attribution models and start instrumenting the full revenue motion. That’s how marketing, product, and sales align around one truth: activation, engagement, and expansion drive sustainable growth.
I’m betting on deeper adoption of A/B testing with a rigorous minimum detectable effect (MDE) discipline and cohort-led retention analysis. Vanity metrics won’t cut it. Teams that operationalize outcomes vs output OKRs and tie experiments to LTV, CAC, and payback will outperform. The win is not more tests—it’s better tests that translate into compounding user activation and retention.
Gen AI will supercharge analysis, but not replace analytical thinking. I see LLMs for product managers accelerating root-cause analysis, surfacing anomalies, and explaining drivers behind conversion shifts. The craft moves from “pulling reports” to “asking higher-quality questions,” then validating with sound statistical methods. The highest-leverage teams will pair gen ai with strong taxonomies, clean event schemas, and clear definitions of North Star metrics.
Data governance becomes a growth enabler, not a compliance cost. With privacy-by-design, consented data, and well-documented schemas, your models become more accurate and your campaigns more resilient. When governance is strong, personalization sharpens, lookalike models improve, and executive confidence in the numbers rises—unlocking faster, bolder bets.
Product-led growth analytics will mature from “feature usage” to “value moments.” I’m focusing my teams on measuring time-to-value, depth-of-use, and expansion signals embedded in in-app guides, product tours, and contextual tooltips. The companies that make value visible earlier—and measure it precisely—will see outsized improvements in trial-to-paid and expansion.
Operationally, I expect tighter cadences between discovery and delivery. Product trios will partner with marketing to run continuous discovery on messaging, onboarding friction, and pricing signals. When insights flow directly into campaign creative and in-product experiments, learning cycles compress and the cost of delay drops.
If you’re building your 2026 roadmap, here’s my short list: consolidate tools into a unified analytics platform, standardize event taxonomies across web, product, and CRM, formalize MDE for every A/B test, and align OKRs to activation and retention milestones. Do this, and you’ll turn fragmented data into a durable growth engine—one that compounds every quarter.
Inspired by this post on Amplitude – Perspectives.
Customer expectations have never been higher. People expect fast, accurate, and effortless support, every time—and across industries, from ecommerce to financial services to healthcare, customer experience has become one of the most strategic levers for achieving durable competitive advantage.
Here’s the challenge I’ve seen again and again: you can’t improve what you can’t see. For years, most support organizations have been making decisions based on only a tiny slice of their customer interactions, captured through surveys that reach only the most motivated (or frustrated) voices. In my own program reviews, the most revealing insights often hid in the conversations that never made it into CSAT or NPS.
We created CX Score to change that. CX Score gives teams a complete view of the customer experience across every meaningful conversation—no CSAT or NPS surveys required. I wanted a signal that reflected reality, not just a vocal minority.
After launching CX Score, we saw many teams immediately use it to understand performance trends, highlight experience issues, and surface gaps across support operations. That early momentum validated the approach and showed us where to go deeper.
As adoption grew, new opportunities emerged. CX leaders found value from CX Score—but they also wanted the model to capture more nuance and identify the specific drivers leading to negative or positive scores, giving them clearer direction on where to focus. I heard the same ask from my own leadership peers: make it explainable and actionable.
That’s what we’ve built into the latest iteration of CX Score. If you’ve been using CX Score for a while and have noticed it shift recently, that’s an expected evolution. A recent shift in scores does not mean your support quality has dipped or that Fin or your team is performing worse than before—this one-time shift reflects a more advanced, more complete model that understands customer experience more deeply with even greater coverage.
Why CX Score needed to evolve
In the initial release, CX Score evaluated each conversation using a combination of sentiment, resolution, and support quality signals. It provided strong early insight and surfaced experience trends that were previously invisible. But as we analyzed real-world conversations across thousands of companies, it became clear that even these combined signals didn’t fully capture the nuance of how customers actually experience support—especially in moments where the outcome was technically correct, but the path to get there involved unnecessary friction, repeated explanations, or unresolved product limitations.
This evolution of CX Score builds on that foundation. It incorporates deeper contextual understanding of the entire interaction, creating a more complete and accurate reflection of the customer experience. As a product leader, that depth matters because it turns a lagging metric into a coaching and prioritization system.
How CX Score has evolved: deeper, more actionable insights
We expanded the CX Score evaluation criteria. CX Score now looks beyond just how your team replied, and into the broader context of the customer’s experience—including reasons that may be outside your support team’s direct control but still influence how your customers feel.
Alongside core support quality signals, we’ve introduced several new dimensions that capture what customers are actually reacting to:
Answer quality (Fin): How well Fin answered the customer’s queries—were responses clear, accurate, and able to resolve the issue without contradiction or repeated clarification?
Answer quality (Teammate): How well a human teammate answered the customer’s queries, using the same criteria: clarity, accuracy, and resolution without contradiction or repeated clarification.
Customer effort: How much effort the customer had to put in to get help (e.g. repeating themselves, multiple handovers, chasing follow-ups).
Strong emotion: Whether the customer expressed strong positive or negative emotions (e.g. joy, gratitude, frustration, anger).
The new CX Score adds context to every conversation: a donut chart surfaces drivers like policy feedback and effort, while a side panel explains why this interaction earned a 3 based on signals from an AI agent chat.
Product/Service feedback: Whether the customer praised or criticized the product (e.g. features, bugs, design gaps, etc.) or the service (e.g. delivery, reliability, onboarding, performance, etc.).
Policy feedback: Whether the customer praised or criticized a company policy (e.g. refunds, returns, account rules, limits, eligibility, etc.).
Broader coverage: more of your support volume now contributes to CX Score
Previously, some conversations couldn’t be scored reliably, especially short, simple, or low-context exchanges—which meant your CX Score was based on only a subset of your total support volume. With this update, CX Score now uses a wider set of criteria to evaluate each interaction. The result: more conversations qualify for scoring, fewer gaps in coverage, and a CX Score that reflects your true support mix—not just the longest or most detailed threads.
Greater transparency with richer, more informative summaries
We’ve made it much clearer why each conversation received the score it did. Right inside the product, every scored conversation now surfaces the specific reasons that influenced its rating—things like high customer effort, strong negative emotion, or product feedback. This added visibility makes it much easier to understand what’s driving your CX Scores, build trust in how they’re calculated, and confidently use them in reporting, coaching, and decision-making.
On top of that, conversation summaries now weave these reasons together with context from the customer’s original query. Instead of scanning the full thread, you can quickly see what happened (the core issue and how it was handled) and why it was scored that way (the key signals that impacted the rating). In my workflow, this shift lets me move from reading transcripts to taking action much more quickly.
From visibility to taking action
As customer experience becomes one of the clearest ways businesses can differentiate, teams need more than visibility—they need clarity on where to invest their time and how to improve. With deeper context and clearer reasoning behind every score, CX leaders can quickly identify what’s working, what needs fixing, and what to prioritize. CX Score moves from being a measurement tool to a system for continuous improvement.
What this unlocks for CX teams: Automatically flag conversations for review. Route threads with high customer effort, strong negative emotion, or low answer quality to QA, team leads, or specialists. Auto-forward product feedback to the right teams. Send conversations with product or policy criticism directly to Product, Engineering, or Ops channels, with no manual triage required. Spot operational issues such as handoff loops, unclear answers, or inconsistent workflows. Share transparent, explainable insights directly with leadership.
The future of CX measurement
CX Score isn’t just another metric. It’s becoming a new standard. Some customers have already chosen to replace CSAT entirely, using CX Score as their primary measure of experience quality because of the broader coverage, deeper context, and clearer paths to action it offers. This reflects a broader shift across the industry: as new competitors emerge and product differentiation narrows, customer experience is becoming one of the most strategic ways to stand out; measuring it accurately and understanding it deeply is now essential.
Our focus going forward is to help teams diagnose issues faster, prioritize with confidence, and improve at scale. This is the foundation we’ll continue to build on: turning every conversation into insight, and every insight into action.
The new CX Score is rolling out gradually to all customers and will be in your workspace by December 3rd.
Want to see CX Score in your workspace? Get started →
When AI Agents resolve the majority of customer conversations, the shape of your support team has to change. I’ve experienced this shift firsthand: the moment AI begins to carry the volume, your people must pivot from answering individual questions to engineering the system that consistently delivers quality outcomes.
The old tiered model built around queue management, handoffs, and volume-based productivity no longer fits. AI now handles the bulk of customer interactions, and that changes the role of your human team entirely. Responsibilities evolve, and success is measured differently. It goes beyond just adding automation to existing ways of working. You’re building an operating model that’s entirely new.
Most teams don’t hire a dedicated AI function from day one. They start by distributing a few critical responsibilities across existing team members, and formalize those responsibilities as AI becomes central to how support works. That’s exactly how I recommend getting momentum without over-hiring too early: prove value fast, name clear owners, and then scale.
Once you have executive support and a clear strategy in place, these are the four foundational roles we believe are key to getting AI off the ground in a meaningful way:
Skillset/background: Often promoted from support ops. Deep understanding of workflows, systems, and tooling. Strong analytical and cross-functional coordination skills.
Why you need this: Without clear ownership, performance drifts. This role ensures the AI Agent constantly improves.
AI isn’t replacing support—it’s opening doors. This visual highlights how GenAI is spawning roles in customer success, from digital support engineers to automation success teams, and unlocking clearer, upward career paths.
In my teams, this role becomes the heartbeat of AI performance—instrumenting quality feedback loops, triaging failure modes, and aligning fixes across product, data, and support ops.
2. Knowledge manager
Responsibilities: Owns macros, snippets, and help content. Maintains structured, accurate inputs the AI Agent depends on.
Skillset/background: Often promoted from support ops. Deep understanding of workflows, systems, and tooling. Strong analytical and cross-functional coordination skills.
Why you need this: Without clear ownership, performance drifts. This role ensures the AI Agent constantly improves.
Every generative AI system is only as good as its knowledge. I’ve learned the hard way that inconsistent or stale content erodes trust—both for customers and internal stakeholders. A rigorous knowledge manager prevents that.
3. Conversation designer
Build a winning AI support team with four core roles: an ops lead to drive quality, a knowledge manager to keep content accurate, a conversation designer for tone and flow, and an automation specialist to power customer actions.
Responsibilities: Designs how the AI Agent communicates by focusing on tone of voice, structure, handoff logic, and interaction flow. Tunes how responses feel.
Skillset/background: Background in content design, UX writing, or support enablement. Deep grasp of policy, CX standards, and conversational nuance.
Why you need this: This role ensures the AI Agent speaks like your brand – clearly, helpfully, and in line with customer expectations.
This is your brand’s voice in motion. A strong conversation designer sets the guardrails that keep interactions on-brand, compliant, and empathetic while still efficient.
4. Support automation specialist
Responsibilities: Builds workflows and backend actions the AI Agent can execute.
Skillset/background: Background in support engineering, systems, or tooling. Works closely with product and engineering teams.
AI in customer service thrives with player‑coaches—hands‑on leaders who build, mentor, and iterate with the team. This quote-driven graphic signals a move away from heavy management toward agile, coaching‑first support operations.
Why you need this: Enables the AI Agent to take action – not just respond. This role translates customer intents into business systems.
In practice, this role unlocks the jump from “answering” to “resolving.” They wire up secure actions, map intents to outcomes, and partner with engineering to keep latency low and reliability high.
Introducing new AI-first roles doesn’t mean your existing functions disappear. But they do need to evolve. For AI to scale effectively, every function in your support organization must shift its focus from managing queue-level activity to improving the system’s performance:
Enablement trains human agents to work with the AI Agent: managing handoffs, tuning responses, and understanding how to give feedback that improves the system.
QA evolves from reviewing conversations to reviewing the quality of the customer experience and behavior of the AI Agent: where the AI succeeds, where it falls short, and how the system as a whole performs.
Workforce management plans capacity based on automation coverage, not just inbound volume.
You’ll also need a new kind of leadership to make this model work. The traditional support leader doesn’t map cleanly to an AI-first organization. You need a new layer: leaders who are part strategist, part operator. They roll up their sleeves to analyze the AI Agent’s performance, refine content, and debug handoffs, but they also coach the team through a new way of working.
Customer service is reorganized for the AI era: a VP of Support leads human support, ops and optimization, and a new AI support function—adding conversation design, knowledge management, and systems analysis alongside agents, insights, and WFM.
This is the “player-coach model” – leaders who actively shape both the system and the people within it.
These leaders see the AI Agent as a teammate to manage, not just a tool to monitor. They can’t be purely people leaders or purely systems thinkers. They need to be both, and they’re emerging as a critical hire in support right now.
Some teams are restructuring their organizations around the AI Agent as a core product, not just a support tool. Here are some real-world examples:
At Dotdigital, a dedicated “Fin Ops” specialist role was created to refine content and improve AI performance.
At Clay, a dedicated GTM engineer role has been established as part of the ops team with a focus on making support more efficient at scale using Fin. Additionally, a support engineering function has been embedded directly in the CX organization to help reduce volume by fixing bugs and building internal tools.
Lightspeed created a dedicated Digital Engagement team to manage Fin’s optimization, and formalized a triangular model that brings together technical teams, frontline experts, and content specialists.
In my experience, the most resilient org designs align around three pillars: Human Support, AI Support, and Support Operations and Optimization. Each pillar carries distinct ownership yet shares accountability for AI performance. That structure keeps the team focused on outcomes over output and makes continuous improvement everyone’s job.
AI shouldn’t replace your agents—it should elevate them. This Rocket Money quote highlights a modern support model where automation handles the busywork and people concentrate on high‑value, human moments.
Once AI Agents handle most conversations, your team’s work moves from “answering questions” to “designing and improving the system that answers questions.” They become the force that steers quality, rather than the one that carries the volume.
This is why new roles are important. It’s not because they’re trendy, but because the performance of your support organization now depends on the performance of AI, and no AI Agent succeeds without clear ownership of content, behavior, workflows, and improvement cycles.
That’s the pattern we’ve seen from working with so many teams:
They name owners early.
They distribute responsibilities before they formalize them.
They anchor teams around AI outcomes, not ticket outcomes.
And they hire leaders who can manage both the system and the people.
If you take one thing away from this week’s article, let it be this: if AI is going to handle the majority of your customer conversations, your team needs to be designed to help it do that well.
Your roles, responsibilities, and leadership approach are now part of the architecture of AI performance.
Next week, we’ll go deeper into how these roles actually operate day-to-day – the workflows, responsibilities, rhythms, and collaboration patterns that make an AI-first support organization run.
Every week, I’m in conversations with product leaders, engineers, and security teams who are trying to ship AI features faster without compromising trust. The tension is real: stakeholders want velocity, customers want transparency, and regulators want accountability. That’s exactly where modern data governance earns its keep.
New AI pressures are redefining what good governance takes. Learn how to build better frameworks, move fast with confidence, and keep your data from being a black box.
In my role leading product management, I’ve learned that robust data governance isn’t a compliance checkbox—it’s a strategic capability. When we treat governance as a product, we architect for clarity, safety, and speed. That means aligning AI Strategy with day-to-day delivery so teams know what they can ship, when, and why.
Here’s the practical blueprint I rely on. First, establish ownership and a shared language. Create a living data catalog, lineage maps, and clear data classifications so teams know which assets are sensitive, regulated, or eligible for training LLMs. Second, harden privacy-by-design and least-privilege access. Bake PII detection, secrets management, and role-based policies directly into your workflows. Third, bring quality and observability to the forefront: instrument data contracts, monitor drift, and track model performance across environments. Finally, implement model governance end to end—dataset cards, model cards, bias testing, human-in-the-loop review, and a repeatable evaluation harness.
To move fast with confidence, make governance invisible and automated. Treat policies as code in CI/CD, gate deployments with pre-merge checks, and fail builds that violate data contracts. Log prompts and outputs responsibly, route unsafe patterns to red-teaming, and use a retrieval-first pipeline to anchor models on verified sources rather than fragile context stuffing. This is how we scale AI product development while keeping audit trails complete and costs in check.
Avoiding the black-box problem starts with transparency. Document assumptions, training data sources, and known limitations—then expose explanations where it matters in the product experience. Pair this with a unified analytics platform to tie telemetry, feature flags, and user feedback to model changes. When something goes sideways, your observability, incident management playbooks, and threat detection and response processes should make root-cause analysis fast and defensible.
If you’re building your program from scratch, use a 30-60-90 approach. In the first 30 days, inventory systems, classify data, and map high-risk use cases. By day 60, formalize RACI for governance, deploy access controls, and set up your evaluation pipeline with golden datasets and measurable acceptance thresholds. By day 90, operationalize incident response, conduct tabletop exercises, and wire governance outcomes into OKRs—think time-to-approval for high-risk changes, reduction in production incidents, and model evaluation pass rates.
This playbook pays off in board conversations and with customers. You can articulate your AI risk management posture, show measurable progress on regulatory compliance, and demonstrate how governance accelerates—not hinders—delivery. Most importantly, your teams gain the confidence to experiment, knowing there’s a safety net that protects users, the brand, and the business.
If your organization is wrestling with how to balance innovation and control, start small, codify what works, and scale with intent. With the right foundations in data governance, AI becomes an engine for durable advantage—not a source of sleepless nights.
Inspired by this post on Amplitude – Perspectives.
What if your morning started with a helpful check-in from a voice AI that actually improves your sleep—using the same core principles that typically cost thousands of dollars and come with year-and-a-half waitlists? That idea energizes me as a product leader, because it blends clinical-grade outcomes with consumer-grade accessibility. Recently, I dug into how the team at Rest built an AI sleep coach inspired by Cognitive Behavioral Therapy for Insomnia (CBTI), and why their method offers a repeatable blueprint for complex, personal AI products.
The origin story is a classic product discovery moment. Rest’s team noticed that a meaningful slice of users in their podcast app were using audio to fall asleep. Although it represented only about 10% of users, that group showed a high willingness to pay. That signal pushed them to explore a dedicated sleep solution, moving from a general audio app to a targeted sleep experience—and eventually toward an AI-powered coach as LLMs matured.
Through jobs-to-be-done research, they identified a clear, underserved segment: “DIY sleep hackers.” These are motivated users who want agency, structure, and results without navigating clinical systems. Choosing CBTI (a clinically proven approach with 80% efficacy) gave the product a strong evidence-based foundation while remaining accessible as a wellness tool. It’s the kind of strategic choice I look for: credible, measurable, and aligned with user motivation.
The product evolution moved in smart, incremental steps. Rest started with a basic text chatbot before graduating to a voice-first experience—using Vapi for voice and OpenAI for reasoning. Voice changed the relationship dynamic: it increased intimacy, lowered friction for daily check-ins, and made behavioral coaching feel human without pretending to be. The team built a memory system that tracks context (like traveling or having a dog) with time-based relevance, which keeps conversations fresh, respectful, and genuinely personalized.
Daily engagement is driven by dynamic agendas that adapt based on sleep data, the user’s stage in the program, and their recent compliance. I love this mechanic: it operationalizes behavior change by sequencing the right intervention at the right time. In parallel, they developed text via OpenAI Assistants while building voice with Vapi, which let them ship value while learning in two modes. They also moved from massive system prompts to RAG for general sleep knowledge, keeping personal user context in the prompt—reducing brittleness while improving scalability.
Because sleep sits close to healthcare, the team drew a firm line between wellness and medical positioning. They implemented clear guardrails: no diagnosis, no medication advice, and strong boundaries on scope. Weekly error analyses with domain experts (sleep therapists) tightened quality and tone, and they adopted LLM-powered evals to enforce safety boundaries. For observability and evaluations, they leveraged Langfuse, and they experimented with Hamming for voice testing to refine the experience end-to-end.
Under the hood, this is a great example of “one bite of the apple at a time” product building in AI. Start with a simple interface, anchor on an evidence-based method, layer personalization with memory, formalize program structure with dynamic agendas, and shift to RAG when general knowledge outgrows prompt engineering. As a product leader, I see strong echoes of agentic patterns here—goal-oriented orchestration, stateful memory, and adaptive planning—shipped in pragmatic increments rather than as a monolithic platform rewrite.
A few takeaways I’m applying with my teams: First, segment deeply and pick a high-intent niche (those “DIY sleep hackers” were the right beachhead). Second, let modality fit the job—voice is not a gimmick when it boosts compliance and empathy. Third, design safety and scope from day one if you’re anywhere near health. Finally, invest early in evals and observability so you can improve with confidence, not hope.
If you want to explore the full conversation and product decisions, you can listen here: Spotify | Apple Podcasts.
Resources & Links:
Rest – AI sleep coach app
Vapi – Voice agent platform Rest uses
Langfuse – Observability and evals platform
Hamming – Voice testing platform
AI Evals Maven Course by Hamel Husain and Shreya Shankar
Bottom line: Rest demonstrates how to take a clinically grounded method like CBTI, translate it into a daily voice-first experience, and ship it with rigor. If you’re building in AI, this is a model worth studying—practical, safe, and deeply user-centered.
Every breakthrough we ship in AI reinforces a simple truth I live by: "Companies that prioritize data quality, governance, and structure will accelerate their AI initiatives the fastest." That statement captures the difference between flashy demos and durable, scalable products. In my experience, the strongest AI Strategy starts with the discipline to treat data as a product, not an afterthought.
When teams rush to production with generative AI or LLMs, the first issues rarely come from the model itself—they come from the data. Poor lineage leads to hallucinations, inconsistent schemas inflate costs, and weak access controls erode trust. For LLMs for product managers, this is the gap between a compelling prototype and a reliable system customers depend on every day.
Let me clarify what I mean by data quality, governance, and structure. Quality is completeness, accuracy, freshness, and consistency across sources. Governance is policy, ownership, and accountability—privacy-by-design, regulatory compliance, and AI risk management built in from day one. Structure is the architecture: clear data contracts, standardized schemas, metadata and lineage, and role-based access that keeps sensitive signals protected while enabling speed.
Here’s the product playbook I use to operationalize this. First, map critical sources and define data contracts at the edges so producers and consumers can move independently. Second, standardize schemas and entity resolution to eliminate ambiguous joins. Third, enforce privacy-by-design with policy-as-code and automated redaction. Fourth, converge analytics into a unified analytics platform so definitions, freshness, and observability are shared. Fifth, instrument end-to-end lineage and quality SLAs with alerting. Finally, close the loop with human feedback and labeling to continuously improve model performance.
For generative AI workloads, a retrieval-first pipeline is essential. Unify trusted sources (product analytics, CRM, support, docs), embed and index them with guardrails, and focus on context window management to keep prompts lean, relevant, and cost-effective. This approach improves response quality, reduces token spend, and makes updates near-real-time—without retraining the base model every week.
Measure what matters. Tie model outcomes to product metrics through rigorous A/B testing, and size experiments with minimum detectable effect (MDE) so you can ship confidently. Use product analytics to verify that better data actually improves activation, retention, and support deflection. When teams can trace an AI improvement back to a specific data-quality fix, they invest in governance with conviction.
Culture closes the gap. Empowered product teams and product trios (PM, design, engineering) make crisper decisions when data stewards are embedded and accountable. Clear ownership, shared definitions, and transparent dashboards reduce friction with security and compliance while speeding up delivery. This is how product management leadership sustains velocity without trading away trust.
The bottom line: if we want faster, safer, and more scalable AI, we start with the data. Build strong foundations, treat governance as enablement, and structure every step so improvements compound. With that in place, Generative AI stops being a science experiment and becomes a durable competitive advantage.
Inspired by this post on Amplitude – Perspectives.
I’m thrilled to share that Intercom is now a certified Shopify Plus Partner on the Technology Track. As someone who obsesses over product quality, speed, and measurable outcomes, this milestone reflects the rigorous standards we hold ourselves to and the trust Shopify Plus merchants can place in our solution.
The Shopify Partner Program Technology Track supports the largest Shopify merchants by helping them find the apps and solutions they need to build and scale their business. The program is available specifically for Shopify Partners who provide a level of product quality, service, performance, privacy, and support that meets the advanced requirements of Shopify Plus merchants.
As a Technology Partner, Shopify has recognized Intercom as a provider trusted to help high-growth ecommerce brands scale.
“The Shopify Partner Program Technology Track is designed to meet the advanced requirements of the world’s fastest growing brands. We’re happy to welcome Intercom to the program, bringing their insight and experience in Customer Support to the Plus merchant community.”
— Jeff Kennedy, Head of Product Partnerships, Shopify
For Shopify Plus merchants, this certification means that our integration is vetted and optimized, and that our roadmap aligns with Shopify’s priorities. In practice, that translates into faster resolutions, less context switching, and more personalized conversations—without compromising privacy or performance.
Over the past year, we’ve launched a series of enhancements to our Shopify integration to give merchants more control and speed in support, including:
Data Connector templates so our AI Agent Fin can fully resolve requests from customers who want to get information about their Shopify order.
Multi-store support for merchants to manage conversations from multiple storefronts in one inbox.
Inbox order actions for merchants to take actions like editing shipping addresses, cancelling and refunding whole orders, deduplicating or creating duplicate orders based on existing ones, all without leaving the conversation.
EU workspace support to ensure merchants stay aligned with EU data residency requirements.
Launch your AI customer service faster—this hero graphic invites users to try the #1 AI agent with a bold headline and clear CTA, emphasizing practical, real‑world demos over polished Hollywood sizzle.
Updated data mapping and custom fields to keep Shopify order data and customer profiles fully in sync.
These updates make it faster and easier for merchants to resolve queries, personalize conversations, and drive loyalty, all from one platform. I’ve seen these capabilities reduce average handle time and minimize escalations—especially for complex order changes and post-purchase workflows.
We’re already seeing how our Shopify integration is helping merchants scale their support and deliver better customer experiences: teams are deflecting routine inquiries with AI while empowering agents to focus on high-value, relationship-building conversations.
Our team is continuing to invest in Shopify-specific capabilities. Here’s what we’re working on:
Expanded Fin Tasks for complex order actions with new pre-built workflows.
Enabling Model Context Protocol (MCP) support.
Smarter product search powered by Shopify data.
These additions will help merchants resolve faster, personalize at scale, and stay ahead of rising customer expectations – particularly as we approach peak season. We’ll continue to ship in tight feedback loops with Plus merchants to ensure each improvement moves the needle.
If you’re a Shopify Plus merchant, learn more about how we can help you scale your support with Fin, the best performing AI Agent for ecommerce. Ready to move fast? Get started with Fin now.
Like many support leaders right now, I’m deep in 2026 planning. The more I map scenarios and stress-test assumptions, the clearer one thing becomes: the way work gets done has fundamentally changed, and that change must reshape our customer service organization.
In 2026, you won’t get the full value of AI by keeping your org chart, systems, and operating model the same. You need to think differently about how support is structured, how performance is owned, and how your systems evolve around an AI-first model. That’s the lens I’m using across my team and our cross-functional partners.
To help you do the same, I’m launching a 2026 customer service planning series. Over the next five weeks, I’ll share how I’m approaching roles, skills, organizational design, and an operating model that makes AI the backbone of support—not a bolt-on feature.
We’ll publish each edition here and on LinkedIn. If you’d rather get them by email as soon as they go live, drop your details and I’ll send each edition straight to your inbox.
But before you can make any of those decisions, you need the right mindset and the right internal conditions for change. That’s where I’m starting this week.
Week 1: Start with a mindset shift
If you were building support from scratch today, you’d design around AI from day one. That’s the mindset to carry into 2026—and it’s the mindset I’m using to guide investment and accountability.
Too many teams still treat AI like a feature instead of infrastructure. They tack it onto existing processes, limit scope to tier-one issues, and never evolve the organization or systems around it. I’ve seen that approach stall progress and fragment the customer experience.
Those teams are thinking too small. They chase incremental efficiency, underinvest in the system change required to make AI successful, and get stuck. The result: a reactive team, a choppy customer experience, and value left on the table.
AI Agents are fully capable, end-to-end resolution engines. They fundamentally change the architecture of support.
To plan effectively and get the most value out of the technology, you need to adjust your mental model. Here are the mindset changes I’m prioritizing.
1) Move from ‘AI as a tool’ to ‘AI as infrastructure’
For the past decade, support systems have been the intermediary between customers and human support agents. AI isn’t an intermediary, it’s the first touchpoint (and often the last), the primary resolver, it manages workflows, orchestrates handoffs, and takes real actions.
Planning with the “AI is a tool” mindset leads to small optimizations that don’t move the needle. Planning with the “AI is infrastructure” mindset lets you redesign around the real sources of value creation.
Here’s what I’m designing around in 2026:
• Clear ownership of Agent performance
• A feedback loop that never shuts off
• A shared understanding of when humans step in
• Systems that evolve as AI capabilities expand
This framing sets up every decision that comes later in your planning process.
2) Look at how the work is changing
You need to plan your 2026 support organization around what the distribution of work will be—not what it is today. AI has shifted where volume goes, what humans spend time on, where judgment is needed, how performance is measured, and how the customer experience is designed.
If your planning assumes the current distribution is stable, you’ll design the wrong structure. I’m modeling for the work that’s coming, not just the work on our queue today.
3) Think like a product leader
When customers primarily interact with your AI Agent, support becomes responsible for designing the customer experience—not just managing it.
“Support is becoming a product function, and you are becoming a product leader”
Design your 2026 support org for AI from day one. This Gamma testimonial shows how an AI agent (Fin) resolves 80%+ of inbound requests, letting a small team scale customer service efficiently without increasing headcount.
Support is now a product surface, and support teams act like AI product teams. They:
• Design the customer experience
• Create and curate the knowledge layer that drives AI quality
• Maintain continuous improvement loops and tune system behavior over time
This is a big shift. Your planning—hiring, skills, rituals, and metrics—needs to reflect that evolution.
4) Redefine performance
This is a big mental leap for support leaders. Traditional performance was measured on speed and satisfaction, but AI performance is measured on resolution, impact, and system reliability.
Planning for 2026 means assuming that:
• Humans will handle a smaller % of volume.
• Customer experience will be shaped by AI’s performance, not throughput
When AI handles the bulk of your support volume, you need new metrics for how your team creates value. In practice, that means instrumenting AI and human-in-the-loop workflows with the same rigor you’d apply to a customer-facing product.
5) Understand that your value increases as AI takes on more work
You need to re-orient your team around AI’s performance to get the most value out of it. The more complex work you give it, the higher impact it will have.
Instead of routing complex, messy questions straight to your human team, shift their focus to improving the AI system so it can take on more over time.
Automating low-effort questions reduces noise, but automating complex workflows changes the economics of your entire team. It creates asymmetric returns that compound as AI absorbs the work that once demanded the most time and skill.
6) Plan for adaptability
A big difference between traditional planning and 2026 planning is simple: change will be constant.
“Change is hard, but the teams that adapt will be the ones who get the most out of this opportunity”
AI learns, evolves, and improves continuously. I’m asking, “How do we build an organization designed to adapt fast as the system evolves?” That question is informing everything from team topology to knowledge governance and experimentation cadence.
Food for thought
Heading into 2026, your org chart will look different—and that’s a good thing. Your people will play new, more meaningful roles as designers, curators, and stewards of an AI-first customer experience.
Once you accept that 2026 demands a different way of thinking, working, and planning, you can move to the next stage: designing the support organization that fits this future. I’ll share exactly what that looks like next week, including roles, skills, and ownership models that have worked well in my experience.
Want the full series delivered by email? Drop your details and I’ll send each edition to your inbox as soon as it’s published.
Walking into PendomoniumX London, I could feel the AI revolution hitting its stride. The conversations were sharper, the demos more grounded, and the outcomes more measurable—a clear signal that AI Strategy is moving from slideware to shipped value in modern product management.
PendomoniumX’s sixth stop brought 350+ software leaders together for a day of AI transformation, real-world stories, and product innovation.
What stood out to me was the shift from hype to execution. Teams compared playbooks for gen ai and Generative AI, shared lessons from LLMs for product managers, and showed how they’re threading AI into product discovery, product roadmapping and sprint planning, and go-to-market motions. The focus was pragmatic: drive adoption, accelerate time-to-value, and make better decisions with cleaner signals.
On the product-led growth front, I saw compelling examples of using Pendo’s in-app guides and product tours to increase user activation and reduce friction in key onboarding moments. When AI-enhanced experiences are paired with clear guidance and behavioral analytics, customers don’t just try features—they build habits.
What I appreciated most were the leadership narratives: empowered product teams aligning around outcomes, candid retros on where AI prototypes missed the mark, and crisp frameworks for prioritizing the highest-leverage bets. The conference networking felt purposeful, with operators trading hard-won insights on experimentation velocity, data governance, and building trust into AI-infused experiences.
My takeaway: AI is no longer a side project—it’s a core capability in product management. If we anchor our AI Strategy in clear customer problems, instrument for learning, and iterate with discipline, we can consistently turn innovation into impact. And with the right mix of PLG mechanics, in-app education, and thoughtful design, those gains compound across the product lifecycle.
I hear the same question in nearly every executive review and go-to-market strategy session: how do we get our brand to show up more often inside ChatGPT? As a product leader, I treat this as an AI Strategy problem, not a mystery. The path forward looks a lot like modern SEO, adapted to how large language models (LLMs) discover, trust, and summarize information across the web and via tools.
Understand how ChatGPT works and how to make your brand appear more often. Like SEO, but for AI chats.
First, let me set expectations. We can’t force mentions, but we can systematically raise the probability that an LLM chooses our content as a trusted source. My playbook centers on three levers: strengthen your public footprint (so you’re easy to learn from), amplify trustworthy signals (so you’re chosen), and enable high-fidelity retrieval and actions (so you’re accurate and current when the model reaches out).
Public footprint: I build topical authority around the entity that is our brand. That means canonical naming, clean information architecture, and interlinked explainers, how-tos, and case studies that answer real tasks. I use schema.org (Organization, Product, HowTo, FAQPage) to make our pages machine-readable, and I back claims with credible citations. Think of this as “entity-first content design” for gen ai and LLMs for product managers.
Content design for LLMs: I write like I’m teaching a capable assistant. I define acronyms in-line, structure pages with crisp headings, include concise summaries up top, and add Q&A sections that mirror natural prompts. I avoid heavy gating on foundational docs so models can ingest the essentials. I also optimize for context window management by keeping key facts succinct and repeated consistently across properties.
Authority and distribution: Models overweight high-credibility surfaces. I prioritize documentation, API references, GitHub repos, conference talks, reputable media, and third‑party reviews. Where appropriate, I pursue eligibility for knowledge bases (e.g., Wikidata) and ensure consistent facts across partner sites and directories. This isn’t about gaming; it’s about being verifiably useful wherever professionals already look.
Technical hygiene: I keep robots.txt and sitemaps friendly to docs, ensure semantic HTML, fast performance, and rich alt text, and use canonical tags to concentrate signals. Changelogs, release notes, and comparison pages help LLMs answer "what’s new" and "versus" questions with precision—core to product positioning and product-led growth.
Tools and connectors: Visibility isn’t only pre-training; it’s also in-session. I invest in a reliable ChatGPT connector and CustomGPT workflows so assistants can call our APIs via well-scoped actions. I publish a high-quality OpenAPI spec, implement a retrieval-first pipeline over our docs, and tune chunking and metadata so answers stay grounded. Good context window management, privacy-by-design, and clear guardrails are non-negotiable.
Intent coverage: I map the customer journey and write to the prompts users actually type: definitions, quick starts, integrations, troubleshooting, and “compare vs” pages with transparent points of parity. This doubles as strong customer support ai strategy while reinforcing our go-to-market strategy.
Measurement: I maintain a prompt panel representing priority intents and track our share of voice in model outputs over time. When we ship content improvements, I use disciplined A/B testing where possible and set a minimum detectable effect to avoid overfitting to anecdotal wins. I pair qualitative spot checks with analytics to see which pages, entities, and citations correlate with improved inclusion.
Governance and ethics: I avoid manipulative tactics, fabricated claims, or spammy link schemes. Sustainable AI visibility comes from trustworthy content, clear provenance, and user value. Treat LLMs like discerning editors: they reward clarity, credibility, and consistency.
The bottom line: you can’t control when an assistant mentions your brand, but you can earn it. Build an authoritative, structured footprint; show up on credible surfaces; enable high-quality retrieval and actions; and measure rigorously. Done well, AI visibility compounds—just like great SEO—only faster, and with outsized leverage for teams who execute with focus and integrity.
Inspired by this post on Amplitude – Perspectives.
