In my day-to-day building AI products, I’ve learned a simple truth: a single model can be brilliant, but a coordinated team of specialized agents is what consistently ships outcomes customers trust. That’s the promise of multi-agent systems—multiple AIs with distinct roles collaborating inside robust AI workflows to deliver accuracy, speed, and resilience you can’t get from a lone model.
Think of a multi-agent system as a well-run product trio for machines: a planner decomposes the job, specialists execute focused tasks, a reviewer checks quality, and an orchestrator keeps everyone aligned. This agentic AI approach mirrors how high-performing teams work—divide complex problems, play to strengths, and create tight feedback loops.
When does one AI stop being enough? Whenever tasks require tool use, domain retrieval, multi-step reasoning, or policy adherence under real-world constraints. In those moments, specialized agents shine—one for search using a retrieval-first pipeline, another for reasoning, another for action execution, and a final one for validation. The result is better accuracy with manageable latency and cost.
The core architecture I rely on starts with a planner that breaks a goal into steps, followed by execution agents equipped with tools and grounded context. I pair this with context window management to keep prompts lean and relevant, and I insert a verifier (or critic) to catch logic slips and policy violations before results reach customers. A lightweight orchestrator coordinates handoffs and retries to keep the whole flow resilient.
To make this production-grade, I treat observability as non-negotiable. Agent Analytics helps me see which agents are adding value versus adding latency, where failures cluster, and how prompts drift over time. From there, eval-driven development gives me measurable confidence: I codify representative tasks, run offline and shadow evaluations, and only promote changes that move accuracy and safety in the right direction.
Governance is equally critical. I design privacy-by-design from the start, restrict data movement with strong data governance, and enforce policy constraints inside the workflow rather than after the fact. This includes red-teaming failure modes, rate-limiting tools, and capturing immutable traces for audits and post-incident reviews—habits borrowed from SRE culture that map well to AI systems.
On the practical side, prompt engineering remains foundational, but it’s the system design that converts clever prompts into reliable outcomes. Tool access, retrieval quality, memory strategy, and error handling matter more than wordsmithing alone. I’ve found that small prompt improvements are amplified when the surrounding workflow is sound—and are overwhelmed when it isn’t.
If you’re just starting, begin with a narrow use case and a minimal set of agents—planner, executor, and verifier—then expand. Use continuous discovery with real users to learn where the workflow fails in the wild, and iterate with tight release cycles. Treat every agent like a microservice with clear contracts, test coverage, and metrics, and you’ll unlock compounding gains without losing control.
The payoff is tangible: faster shipping cycles, fewer regressions, and outcomes customers can actually rely on. When stakes are high and ambiguity is real, one AI is often a talented soloist—but a disciplined ensemble of agents is how I deliver dependable, scalable value at product velocity.
Over the last year, I’ve had the same conversation with a lot of support leaders.
They’ve deployed AI and are seeing initial efficiency gains, but want to push beyond these early results and achieve meaningful transformation.
When AI is first introduced, the gains show up quickly. Teams resolve higher volumes of queries, free up capacity, and deliver faster responses. But the real opportunity for impact extends well beyond those initial wins. As AI becomes more deeply integrated into support operations, taking on harder, more complex work, those results compound, new ways to create and measure value open up, and the economics of support change entirely. That shift is where I spend most of my time with leaders—turning early efficiency into durable business value.
This sits at the heart of “The 2026 Customer Service Transformation Report.” In this reflection, I explore how deeper integration compounds impact and why that makes business value easier to articulate across the organization—especially to finance and product peers who need to see outcomes, not just output.
The teams going deeper are seeing higher returns. The research shows that 62% of support teams have seen their customer service metrics improve since implementing AI, with early wins showing up most clearly in speed and efficiency. But for teams that have reached mature deployment (where AI is fully integrated into operations) that number jumps to 87%.
As AI programs advance, measurement confidence surges. This chart shows how ROI tracking rises from 35% in exploring to 70% in mature deployments—evidence of a widening execution gap in customer service.
The same pattern holds for the ability to measure ROI. Among teams in early exploration, just 35% say they can measure their return on AI investment, but for teams at the mature deployment stage, that rises to 70%. In my experience, this is the moment the conversation shifts from “is AI working?” to “how much leverage are we creating?”
As AI becomes more embedded in support workflows, what teams choose to measure starts to change. In the early stages of deployment, ROI is typically understood through improved customer response times, lower cost to serve, and freeing up capacity. Teams focus on how much time AI creates and whether it’s relieving pressure on the support organization. These signals help validate that the system is working, but they say little about how that capacity is ultimately used.
As deployments mature, measurement starts to reflect a different intent. Instead of stopping at time saved, teams look at where that capacity is reinvested—into higher value customer work and revenue-generating activities. ROI becomes less about relief and more about leverage. I encourage teams to set targets for capacity redeployment and tie them directly to activation, retention, and expansion outcomes.
The report data shows this clearly. Across all maturity stages, the most commonly cited measure of ROI is "time freed up that the support team can use to focus on value-adding activities for customers." But at mature deployment, that signal intensifies, with 73% of teams citing it, compared to 56% at early exploration.
Mature AI deployments reveal clearer ROI: teams report more time freed for value-adding customer work (73% vs 59%) and more hours redirected to revenue-generating tasks (56% vs 34%) than initial rollouts.
What’s also interesting is that 56% of mature teams say freed capacity is being directed toward revenue-generating activities, up from 34% at initial deployment. That’s a powerful indicator that AI is shifting from a cost narrative to a growth narrative.
The result is a shift in economic intent: from measuring what AI saves to demonstrating how the capacity it creates is reinvested to drive growth. As a product leader, I anchor this conversation in outcome-based metrics and clear counterfactuals: what would it have cost to deliver the same experience without AI?
As AI takes on more work, the question moves from “does it save money?” to “how does it change the economics of support?” Legacy support economics were built for linear growth: more customer tickets meant more headcount, more outsourcing, and more software costs. Success was measured through containment—the number of queries that didn’t reach human agents. These models worked when volume and effort were tightly linked, but AI doesn’t scale linearly, and it needs to be evaluated differently.
To sustain AI investment and expand its impact, teams need to move beyond cost-cutting narratives and build a clearer case for business value. When done right, AI goes far beyond improving support efficiency. It rewires the financial model, breaking the link between support costs and revenue growth, and turning support into a contributor to customer activation, retention, and lifetime value. This means treating your AI Agent as a new workforce capability that changes how your support function creates and captures value. Here’s what value looks like in an AI-first model:
Deeper AI integration decouples growth from headcount. This split chart shows support volume surging while team size plateaus, revealing how automation unlocks scale, reduces costs, and makes ROI easier to prove.
Human productivity: Your team focuses on more strategic areas, not the queue.
System improvement: Every resolved query makes the system smarter.
Revenue influence: Support becomes a lever for activation, retention, and growth.
Organizational agility: You scale service without scaling headcount.
Leaders are racing ahead with real AI in support. Explore the 2026 Customer Service Transformation Report to see where deployment is stalling, benchmark your team, and get practical steps to scale automation that delights.
How does this look in practice? Intercom offers a compelling example with Fin. What started as a focused effort to improve their customer support experience has become one of the clearest illustrations of what happens when AI is fully embraced across an organization.
Since 2022, Fin has helped Intercom absorb more than a 300% increase in customer demand while improving the consistency of delivery—including supporting new routes into support for trial customers and website visitors. Today, Fin is involved in 97% of their customers' conversations. Of those, it resolves 83.5% end-to-end, putting their overall automation rate at 81%.
That depth of deployment allowed Intercom to scale service without scaling headcount. Without Fin, they would have needed at least 100 additional support teammates to meet rising demand and service standards.
As Fin took on the majority of day-to-day volume, the human support team shifted toward consultative work—helping customers adopt Fin more deeply, succeed faster, and unlock more value from the platform. Intercom now tracks metrics like “direct revenue generated” and “expansion revenue influenced” to understand the impact of these consultative support activities. This repositioned support from a cost center to an active contributor to long-term growth.
The throughline from The 2026 Customer Service Transformation Report is that deployment depth makes a significant difference. Teams that are investing in deeply integrating AI are reshaping how support scales and contributes to growth. Value becomes clearer as AI takes on more work, and support leaders can articulate that value to the rest of the business.
The gap between these teams and those still in the early stages is widening. A select group of pioneers are setting a new bar for what AI-powered customer service can deliver, and understanding what they’re doing differently is the first step toward closing that gap. If you want to dive deeper into the data and frameworks, you can download the report here: https://www.intercom.com/customer-transformation-report?utm_source=blog&utm_medium=internal&utm_campaign=20260128-report-owned-2026cstransformationreport&utm_content=chapterseries_2
I keep a simple mantra front and center: Figma is not the source of truth. The customer is. In practice, that means the only thing that truly counts is what we ship, how it performs, and whether users come back for more. Mockups are hypotheses; production usage is evidence. When my teams adopt this lens, velocity improves, judgment sharpens, and quality rises where it matters most.
So what does design actually do in a software company? At its best, design builds leverage for the whole system—engineering, product, and marketing—by clarifying problems, raising the quality bar, and making complex decisions legible. The standard I hold is ancient and still essential: products must be useful, usable, and desirable — and above all, used. When we calibrate around “used,” debates about pixels give way to outcomes, and cross-functional partners feel the difference.
I often trace the roots of our craft back well beyond the digital era. The lineage from industrial design to software is real; constraints, ergonomics, affordances, and systems thinking didn’t start with screens. If you’ve ever mapped delight, performance, and reliability in a Kano Model, you’ve touched this lineage. The translation to software is simple: design the full journey, not just the interface—prioritize what improves time-to-value, reduces cognitive load, and earns habitual use.
One lesson I’ve learned the hard way: why design leaders who stop designing stop leading. I still sketch flows, write UX copy, and prototype when it unblocks the team or sets a decisive quality bar. The altitude changes constantly—one hour I’m in a strategic roadmap review, the next I’m in a critique or poking at a prototype. Great design leaders jump up and down in altitude to connect vision to details without becoming a bottleneck.
Over time, I’ve come to rely on four pillars every design manager must master: craft (raising taste and execution), product strategy (clarifying choices and trade-offs), people leadership (coaching, feedback, and hiring), and systems (processes, rituals, and design ops that scale). Neglect any one of these and either quality, speed, or team health will eventually falter.
Perfectionism is a double-edged sword. Over-indexing on quality can paralyze decision-making, but lowering the bar indiscriminately is worse. I’ve seen moments where relaxing standards to “go faster” actually cost the business—rework piled up, trust eroded, and customer value stalled. The answer is principled delegation: I define what “must be true” at each milestone, delegate ownership with clear guardrails, and reserve my veto power for moments where product integrity is genuinely at risk.
Measuring success as a design leader starts with outcomes vs output OKRs. I care about activation, retention, time-to-first-value, NPS verbatims tied to key journeys, and the operational metrics that earn the right to build the next thing. Design output is visible; design outcomes are durable. When trade-offs are needed, I optimize for the smallest shippable surface that still proves the core value proposition, then expand with data.
Scaling judgment is the multiplier. I build it through pattern matching—studying enduring product systems from companies like Airbnb, Amazon, Apple, Asana, Notion, Stripe, Nest, and others—to distinguish where polish compels usage versus where it’s ornamental. Strong opinions matter, but so does being easy to convince with new evidence. I encourage designers to articulate the pattern they’re invoking, why it fits the job-to-be-done, and how we’ll know it worked.
Operating cadence matters. My week is anchored around recruiting, crits, and staff meetings that actually make decisions. In critiques, I use the Do/Try/Consider framework to give actionable direction without micromanaging. On one-on-ones, the question isn’t “Should one-on-ones exist?” but “What are they for right now?”—coaching, performance, or clearing execution blockers. If a meeting doesn’t increase clarity or commitment, it gets redesigned or removed.
Execution-wise, I’ve taken inspiration from Rippling’s operating system—especially its emphasis on speed, precise ownership, and hard commitments. The lesson is timeless: go fast on the right things, make clear promises, and instrument your work so you can see reality quickly. When speed is paired with crisp decision rights and observable outcomes, momentum compounds rather than frays trust.
Hiring your first design leader? Look for someone who can set standards, scale judgment, and ship. They should be able to zoom from company narrative to interaction copy in a single afternoon, coach product trios, and build rituals that make taste and trade-offs explicit. Above all, they should have a point of view on where quality moves the business and where speed is the quality.
Here’s how my team’s approach differs from many: Figma is not the source of truth. We design in Figma, but we learn from production. We pair designers with engineering early, prototype in code when it reduces risk, and wire telemetry into every critical path. Product trios use discovery to validate “useful, usable, desirable — and used,” then commit to outcomes with clear, testable definitions of success. The result is faster iteration, fewer surprises, and experiences customers actually adopt.
The throughline is simple and demanding: design for reality, not for the board. Keep your standards where they create business value, scale judgment with explicit patterns, and instrument everything so learning never stops. When teams embrace that, the work gets better, customers feel it, and the roadmap starts to pull you forward.
I've been getting a lot of questions about why I'm diving so deep into Claude Code, so I want to take a step back and provide some context.
Last March, when I started building my first AI product—the Interview Coach—I felt like I had to figure it all out on my own. I had never built an AI product before, and I didn't have a team I could lean on. It was equal parts energizing and intimidating.
I had a blast digging in, experimenting, and learning what I needed to learn to ship that first AI product. But I also started to wonder, "How are product teams going to learn this stuff?"
As an industry, we are being asked to leverage a new technology that is foreign to us. We are all experimenting and learning what's just now possible. It's moving so fast, it's exhausting just following the news, let alone trying to learn and develop new skills.
My mission has always been to help teams make better product decisions. That still drives me today.
After releasing the Interview Coach, I asked myself two questions: "How am I going to rapidly develop my skill set?" and "How can I help others do the same?" I landed on a three-part plan: First, I'm going to collect and share stories about how other teams are learning and building AI products—that's why I launched Just Now Possible. Second, I'm going to push the boundaries on how I can use AI in my day-to-day life, and I'm going to write about it. Third, I'm going to keep building AI products—and I'm going to write about that, too.
The Claude Code series was born out of number two. It’s had an interesting side effect: it’s also helping me build better AI products.
The more I push the boundaries of what's possible with Claude Code, the more I understand how to build more robust AI products. That’s reinforced my belief that product teams need to get hands-on with this stuff in their day-to-day lives. It’s how we’re going to develop the skillsets we need to build tomorrow’s products.
In my context rot article—where we learned how to manage the context window in Claude Code—I showed just how much day-to-day practice compounds. Today, I want to show how learning about context window management in our day-to-day lives directly maps to managing the context window in the AI products we might build. My hope is to make it crystal clear how experience in one area develops expertise in the other. Let’s dive in.
Discover how product teams engineer context in generative AI: compact prompts, curated turns, external memory, repetition, and sub-agents, all feeding a shared context window to deliver clearer, faster outcomes.
A quick refresher on context window management. In the context rot article, we learned: "what the context window is and what goes into it"; "how to offload conversational context to the file system"; "about the /compact and /clear tools"; "to repeat critical information as the context window fills up to overcome tokens "lost in the middle" or at the beginning of the input"; and "how to use agents to get access to more context windows."
It turns out these exact same skills are being used by developers to manage the context window in production products. If you haven't read the context rot article, start there: "Context Rot: Why AI Gets Worse the Longer You Talk (And How to Fix It)."
What is Context Engineering? Context engineering is the work that we do to manage the context window in the AI products and services that we build. It's how we give the large language model the context it needs to do the job well. It's also how we manage and mitigate context rot in our product and services, so that we can get the highest performance from the underlying model.
Today, we are going to look at five different strategies that product teams are currently using in their context engineering efforts. You are going to see that each of these strategies ties back to a strategy you might already be using in your day-to-day AI usage (especially if you followed the advice in the context rot article).
Here's how product teams are putting this into practice right now: designing compact system prompts by breaking big tasks into smaller tasks; building external memory/state structures to keep the context window clean; curating what goes into each turn; repeating critical information as context grows; and using sub-agents to grow the context window.
I'll connect each tactic back to patterns you're likely already using in your daily AI workflows, especially if you followed the advice in the context rot article. Along the way, I’ll share practical guardrails and instrumentation ideas so you can track quality with eval-driven development, reduce context rot, and scale performance predictably.
Why this matters for product trios: these strategies clarify the handoffs between prompt engineering, external memory design, and orchestration, which strengthens collaboration across PM, design, and engineering. Whether you’re exploring gen ai prototypes, hardening a retrieval-first pipeline, or evolving toward agentic AI, context engineering is the backbone of reliable, high-performing experiences.
If you build or lead LLMs for product managers initiatives, consider this your field guide. In upcoming posts, I’ll break down each strategy with concrete examples and templates you can adapt to your stack, so your team can move from experiments to durable, scalable AI workflows with confidence.
The most valuable upgrade I’ve made to my product management workflow isn’t a new framework or a shiny dashboard—it’s an AI-first operating model that compresses discovery-to-delivery cycles while increasing confidence in every decision. I built this approach to reduce context switching, remove toil, and keep the team relentlessly focused on outcomes over output. The result is a faster, clearer, and more reliable path from insight to shipped value.
Here’s how I run an AI-powered product workflow end to end: continuous discovery, opportunity sizing, solution shaping, planning, execution, and iteration—each step instrumented with automation, retrieval, and evaluation so we learn faster without compromising rigor.
Intake and triage start with a retrieval-first pipeline that unifies customer feedback, support tickets, sales notes, research transcripts, and usage analytics. I use embeddings to cluster themes, de-duplicate signals, and surface the most representative examples. This gives me an instant, always-fresh view of customer jobs, pains, and opportunities without manually combing through noise.
For discovery, I rely on “LLMs for product managers” to accelerate the hard parts without replacing judgment. I generate interview guides, summarize transcripts, extract entities, and tag moments of friction. Prompt engineering and context window management ensure the model sees the right evidence at the right time. I keep all sensitive data governed by privacy-by-design and data governance controls.
Opportunity sizing is where I connect insights to business impact. I map problems to a driver tree, quantify potential lift, and align to outcomes vs output OKRs. When relevant, I apply the Kano Model to balance performance, basic, and excitement attributes. To maintain rigor, I use eval-driven development on my prompts and heuristics so prioritization is repeatable, not anecdotal.
Solution shaping is a collaborative exercise with product trios. I draft problem narratives and PRDs, generate acceptance criteria, and create first-pass UX flows. For speed, I use gen ai for product prototyping to explore alternatives quickly, then gate final choices through usability feedback and feasibility checks. Where uncertainty is high, I define a minimum detectable effect (MDE) and design A/B testing plans upfront.
Planning ties strategy to execution through product roadmapping and sprint planning. I break work into sequenced bets, enable feature flags for controlled exposure, and wire quality signals into CI/CD. DORA metrics—like deployment frequency and change failure rate—help me keep the system honest. Observability ensures we see the “why” behind behavior, not just the “what.”
Execution is instrumented with in-app guides, Intercom messaging, and Pendo to shape onboarding and activation. I connect Amplitude analytics to measure habit formation, retention analysis, and feature adoption. When experiments run, I monitor leading indicators in near real time while protecting against peeking and p-hacking. The point isn’t to prove we’re right; it’s to learn fast enough to get right.
Iteration closes the loop. I use a unified analytics platform to compare expected vs actual outcomes, harvest qualitative feedback, and push new evidence back into discovery. The system improves with each cycle because the retrieval-first pipeline and eval harness both get smarter as data grows.
Governance is non-negotiable. AI risk management, cybersecurity, and regulatory compliance sit alongside model evaluations to prevent drift, leakage, or bias. I document decisions, model versions, and test artifacts so we can audit how we got to a call—especially when trade-offs are nuanced.
If you’re standing up this AI workflow from scratch, I recommend a 30/60/90 rollout. In the first 30 days, audit your data sources and build a retrieval-first pipeline. In days 31–60, pilot two high-leverage workflows—continuous discovery and PRD drafting—backed by eval-driven development. By days 61–90, scale to prioritization and experiment design, then thread the outputs into your planning and CI/CD rhythms.
Common pitfalls I watch for: over-automation that blurs context, lack of evaluation frameworks, ungoverned data that undermines trust, and vanity metrics that celebrate activity over outcomes. The antidote is simple but disciplined—clear decision criteria, measurable hypotheses, and automated evaluations that run as guardrails, not bottlenecks.
This AI upgrade doesn’t replace the craft of product management; it amplifies it. By combining judgment, clear strategy, and reliable automation, we ship value faster, reduce risk, and make better calls under uncertainty. The payoff is durable: compounding learning velocity and a team that spends more time solving the right problems—and less time wrestling the process.
I’ve been pushing hard to operationalize AI for real product work, and this episode zeroes in on the moment Claude Code stops feeling like a demo and starts behaving like a dependable teammate. If you’ve ever wondered how to go from clever prompts in the browser to durable, repeatable workflows on your machine, this walkthrough is for you.
Listen on: Spotify | Apple Podcasts.
My first honest reaction to installing and configuring the desktop agent was the all-too-relatable “this tool thinks everything is a code repo” reality. That framing helped me reset expectations fast: instead of treating it like a magical universal assistant, I began designing guardrails, context, and repeatable routines—exactly how I’d onboard a new team member.
The shift from Claude-in-the-browser to Claude Code on my machine was the unlock. Locally, it can finally work with my files, folders, and workflows. That meant I could ground it in real artifacts—project docs, meeting notes, product specs, and historical decisions—so responses weren’t just plausible; they were contextual and verifiable.
On setup, I now treat /init and Claude MD files as my product requirements. I define roles, boundaries, and canonical sources up front, then run in a deliberate “walled garden.” The “treat it like an intern” model works beautifully: scope access intentionally, expand privileges as trust grows, and keep a tight audit trail of what it can touch and why.
Surprisingly, task management became my ideal on-ramp. It’s easy to validate, the feedback loops are tight, and the ROI is immediate. I export calendar windows rather than granting full calendar access, then let the agent map priorities into Trello, reconcile time blocks, and surface trade-offs. Fast wins build confidence—mine and the agent’s.
Model switching matters more than I expected. When speed is king and “good enough” will do, Haiku keeps the loop snappy. When stakes are higher—complex synthesis, nuanced product strategy, or gnarly ambiguity—I step up to Claude Opus 4.5. Being intentional about when to optimize for latency versus depth is a quiet superpower.
Web tasks can still spiral. When that happens, I pause its autonomy, toggle to fewer steps, and ask, “What are you doing?” Paired with Claude’s Web fetch tool, this makes the agent explain its chain-of-thought planning without exposing hidden reasoning, so I can spot brittle assumptions, prune distractions, and re-ground the task.
Content retrieval has become a killer workflow. I point the agent at my archives—blog posts, book drafts, transcripts, notes—and ask, “Where have I talked about this before?” It assembles a map of prior art, connects themes I’d forgotten, and prevents me from reinventing work. Over time, this evolves into a Zettelkasten-style research system that upgrades rigor and accelerates synthesis.
I’ve also turned Claude Code into a publishing engine. From a single transcript, it drafts titles, descriptions, show notes, and chapters, then routes artifacts to Ghost for formatting. Before anything ships, I run fact-checking workflows that validate claims against transcripts and research sources. The output improves, but more importantly, the scaffolding makes quality repeatable.
Reusable workflows compound. I rely on slash commands to trigger common jobs, break down larger efforts with sub-agents, and wire in hooks and plugins where external systems are needed. This is agentic AI at its most practical: fewer hero prompts, more reliable processes.
Audience analytics and content prioritization are helpful with caveats. I let the agent cluster themes and flag gaps, then I pressure-test its suggestions against first-party data and strategic goals. As with any model-driven insight, triangulation beats blind faith.
Two metaphors guide my day-to-day. First, Claude Code is like a dog—sometimes it returns with the stick, sometimes it gets lost in the woods. Second, the “intern” framing keeps me honest: don’t hand it the whole company on day one. With that mindset, my output jumped—more volume without sacrificing quality—because the workflow scaffolding got better.
In this episode, I cover what Claude Code is and why it’s useful even if you’re not an engineer, the real difference between the browser experience and running locally, how to shape behavior with /init and Claude MD files, why task management is the perfect proving ground, when to export calendar windows versus connecting directly, and when model-switching makes sense—Haiku for speed, Opus for depth.
I also dig into debugging web tasks by asking “What are you doing?”, content retrieval workflows across personal archives, building reusable slash-command systems with sub-agents, hooks, and plugins, practical publishing stacks from transcripts, fact-checking against transcripts and research sources, and using analytics to prioritize content—with a healthy respect for uncertainty.
If you’ve been trying to make Claude Code feel less like “throwing a stick into the woods,” this is the candid, tactical tour I wish I’d had on day one. Drop your questions and experiments below—I’m eager to compare notes and refine the playbook together.
“You don’t have to trust the algorithm; you can see exactly why a conversation earned the score it did.”
We recently shared how we redesigned CX Score to deliver deeper, more actionable insights across every conversation. The most common follow-up from support leaders was simpler and incredibly important: “Can I trust it?” It’s the right question—and it’s the one I use as my own bar for whether a metric is ready for the C‑suite.
CS teams are the subject matter experts on customer experience. They understand the nuance of what customers feel, the context behind every interaction, and the difference between a technically resolved issue and a genuinely satisfied customer. I’ve learned, conversation by conversation, that any metric we ship has to capture that nuance at scale—or it doesn’t deserve to be used.
We built CX Score to give support teams a complete view of how their customers feel across every conversation. It surfaces what’s working, what’s not, and why—so leaders can communicate impact clearly and drive change across support, product, and the wider business.
A CX Score in action: repeated CSV export failures trigger a low score and customer frustration, while the AI agent clarifies next steps and gathers details—turning raw signals into actionable support insights.
Here’s exactly how I approached building a trustworthy metric that support leaders can inspect, explain, and defend.
1) It’s grounded in how support teams define quality. I started with how experienced support professionals actually evaluate conversations—collecting real examples of strong, mixed, and poor interactions across industries, identifying the specific factors that shape overall experience, and writing plain-English rules for each. The result: CX Score applies the same criteria a trained support professional would use, not generic LLM assumptions.
2) It’s aligned with human judgment. We created a dataset of thousands of real customer conversations spanning multiple industries, languages, channels, and agent types. Each was manually reviewed by experienced support professionals—with two reviewers per conversation where possible and disagreement resolution to create stable consensus labels. The result: CX Score is trained and tested to behave like an expert reviewer, not a language model making broad guesses.
A modern CX analytics view shows how conversations flow from chat, email, and mobile into AI assistance, then to resolutions and sentiment outcomes—turning messy support data into a single, defensible CX Score.
3) It’s engineered by AI specialists. CX Score isn’t a prompt attached to an LLM. It’s a production system built by Intercom’s AI Group: 37 ML scientists and 350 engineers whose full-time focus is AI for customer service. The system includes specialized handling for long transcripts, model configuration tailored for support language and subtle sentiment, prompt engineering designed to default to neutral when evidence is weak, and a multi-stage evaluation pipeline that checks for precision, consistency, and reliability. The result: A metric built by a team that understands LLM behavior in production support environments, where accuracy and consistency matter most.
4) It’s validated statistically, not qualitatively. Trust requires measurement, not vibes. We tested CX Score across standard ML metrics: Precision (when the model flags a negative experience, how often do humans agree?), recall (how many human-identified issues does it catch?), and F1 score (the balance between both). We set an explicit bar: F1 above 0.8, representing high agreement with human judgment. We reran these evaluations through every revision, checking for regressions or biases, and I focused especially on negative experiences, because a false negative hides a real problem. The result: CX Score meets a measurable standard before it ships—not a gut check, a statistical requirement.
5) It was battle-tested with real customers. Lab accuracy isn’t enough. Customer environments are messy: Varied ticket types, mixed languages, unpredictable edge cases. Before release, we ran a multi-phase field test—shadow-scoring conversations with both old and new models, validating sensible behavior across agent type and conversation length, then rolling out to a controlled customer group who confirmed the scores felt right, reasons were clear, and insights were actionable. The result: CX Score shipped because real teams told us it made sense in practice, not because it passed internal tests.
From conversation to clarity: this visual maps the drivers behind a CX Score. Explore how policy feedback, answer quality, and effort combine to produce defendable insights support leaders can act on.
The importance of explainability. One of the most critical choices I made was ensuring CX Score isn’t a black box. Every score comes with clear reasons, concrete excerpts, and a short explanation of what influenced the rating. This turns the metric into something you can inspect, audit, and explain to executives. You don’t have to trust the algorithm. You can see exactly why a conversation earned the score it did.
A metric that evolves with your business. Customer expectations shift. Products change. AI improves. A trustworthy metric can’t be static. CX Score evolves with the same commitments that shaped its redesign: Evaluate the real signals that shape customer experience, keep the logic simple and interpretable, and ensure leaders can make clear decisions from it. It’s built to be a durable source of truth across every conversation.
The takeaway. In a world where products look the same and AI can generate any interaction, customer experience is one of the few differentiators that actually matters. Support leaders have built that expertise conversation by conversation. What they’ve lacked is a measurement system that could validate it at scale—one that’s reliable enough to report to the C-suite, explainable enough to defend in strategy meetings, and rigorous enough to drive real decisions. That’s what CX Score is designed to be: A metric that reflects the reality support leaders see every day, backed by the technical rigor to make it credible everywhere else.
Want to see CX Score in your workspace? Ask your admin to enable it for your team, and start using explainable AI insights to improve customer experience and coach with confidence.
Shipping AI agents is not like shipping a typical feature. The system learns, reasons, and takes action in unpredictable environments, and when it’s customer-facing, the stakes are high. Over the past few years, I’ve refined a practical checklist that helps my teams move quickly without breaking trust. It balances speed with safety, and ambition with accountability—exactly what you need to scale agentic AI in production.
This checklist was forged in real launches—some smooth, some humbling. Early on, I watched an otherwise brilliant agent confidently offer a refund policy we didn’t have. That one incident made it clear: AI agents require a higher bar for guardrails, evals, and observability. Today, I won’t greenlight an AI rollout without these steps being explicit, owned, and testable.
Start with outcomes, not output. I define the job-to-be-done, the target users, and the measurable business impact using outcomes vs output OKRs and driver trees. Success is not “ship an agent,” it’s “reduce first-response time by 40% with no drop in CSAT,” or “increase qualified demo bookings by 20% at a lower cost per acquisition.” Clear outcomes give the agent a purpose and the team a north star.
Prepare the knowledge the agent will use. A retrieval-first pipeline beats raw prompting for most enterprise cases. I inventory sources of truth, set access controls, and enforce data governance from day one. That includes PII handling, redaction, retention policies, and privacy-by-design. If the agent can’t reliably retrieve the right fact at the right time, the rest doesn’t matter.
Choose models and prompts with discipline. I align model selection with context window management, cost, latency, and tool-use requirements. Then I build prompts and tools together, not in isolation, and I keep temperature, stop conditions, and function-calling explicit. Most importantly, I use eval-driven development: golden datasets, task-specific metrics (accuracy, helpfulness, latency, cost), and target thresholds that must be met before widening rollout.
Manage AI risk upfront. I treat jailbreaks, toxicity, and data leakage as product risks, not just security issues. I implement layered defenses—input/output filtering, policy checks, rate limits, and abuse monitoring—and define escalation paths and human-in-the-loop handoffs for ambiguous cases. Every risky capability needs an owner, a playbook, and a test.
Build the pipeline that lets you iterate safely. Prompts, tools, policies, and retrieval configs go through the same CI/CD rigor as code. I use feature flags for progressive delivery, canary cohorts to limit blast radius, and clear rollback procedures. Observability isn’t optional; I track latency, token usage, cost, failure modes, and user outcomes. I also watch DORA metrics and deployment frequency to ensure we’re improving the engine, not just the output.
Constrain autonomy intentionally. Agent behavior design matters as much as model choice. I set step limits, define tool whitelists, separate read vs write permissions, and specify decision checkpoints. When the agent is uncertain or confidence drops below a threshold, it hands off to a human or a deterministic workflow. Guardrails aren’t barriers; they’re bumpers that keep you on the track.
Instrument what users experience, not just what models produce. I track activation, task success, self-serve completion rates, and time-to-value. I pair Agent Analytics with journey analytics so I can see where the agent helps or hurts. I also invest in UX trust cues—transparent explanations, undo paths, and in-app guides—so users feel in control. When the agent changes behavior through learning, the interface should make that understandable.
If you’re shipping a voice AI agent, test in realistic conditions. I set targets for ASR accuracy, barge-in responsiveness, TTS prosody, and end-to-end latency. I predefine safe transfer logic for complex calls and ensure compliance for call recording and data retention. Voice amplifies both the magic and the mistakes; operational excellence is non-negotiable.
Plan the business rollout like a product, not a press release. I align pricing (often consumption SaaS pricing), packaging, and SLAs with actual unit economics—tokens, inference, and retrieval. I equip solutions engineering with playbooks and reference architectures, wire up CRM integration for attribution, and put feedback loops into Intercom or the support stack so we learn from every interaction.
Run operations like an SRE team. I define incident severity for AI-specific failures (e.g., harmful output, runaway cost, degraded retrieval), add alerting, and keep runbooks current. I schedule postmortems that feed directly into eval baselines and backlog priorities. Continuous discovery isn’t a ceremony; it’s the safety net that keeps improvements compounding.
Close the loop on compliance and governance. From day zero, I document data flows, vendor scopes, and audit logs. I verify regulatory compliance and adopt privacy-by-design so I’m not retrofitting later. Transparency, user consent, and opt-outs aren’t just legal checkboxes; they’re trust-building tools that differentiate your product.
The result of this checklist is speed with confidence. It gives my teams a common language to debate trade-offs, a clear path to production, and the guardrails to scale safely. If you’re preparing to deploy an agent, adapt these steps to your stack and your customers. Your future self—and your users—will thank you.
I’ve been exploring what I call the next level of vibe coding: orchestrating agentic AI to build complex product artifacts in minutes, not days. The breakthrough comes from ditching linear handoffs and embracing true parallelism—letting specialized agents tackle the work simultaneously while I steer the orchestration. In product management contexts where speed and clarity matter, this shift changes everything.
Building a KPI Driver Tree in two hours becomes possible when you stop building sequentially and start building with parallel agents.
For product leaders, a KPI Driver Tree is the fastest way to make strategy legible. It ties high-level outcomes to the levers we can actually pull—features, channels, pricing, onboarding, activation, and retention mechanics—so we can prioritize with confidence. Done well, it connects outcomes vs output OKRs, clarifies measurement, and aligns the team around a shared, testable model of growth.
Here’s how I operationalize it with agentic AI and AI workflows. I spin up a small team of specialized parallel agents: a Metrics Librarian (taxonomy and definitions), a Data Modeler (event and table design), a Research Synthesizer (voice of customer and causal hypotheses), a UX Prototyper (visualizing the tree and flows), and a QA/Evaluator (logic and consistency checks). An Orchestrator coordinates these agents, resolves conflicts, and composes outputs into a single, production-ready artifact—while I set constraints, review deltas, and decide.
In a typical two-hour sprint, all agents run at once. While the Metrics Librarian finalizes the KPI ontology, the Data Modeler validates instrumentable events and joins, and the UX Prototyper renders an interactive driver tree for a unified analytics platform. Meanwhile, the Synthesizer maps qualitative insights to quantitative levers, and the Evaluator stress-tests assumptions. Because we’re not waiting for sequential handoffs, we converge on a coherent driver tree and its initial measurement plan in one pass.
The payoff isn’t just speed—it’s higher-quality decisions. Parallel agents reduce context loss, expose trade-offs earlier, and allow me to compare multiple viable paths side-by-side. This accelerates continuous discovery, aligns with product strategy, and gives product managers and LLMs for product managers a clear, living map of how inputs roll up to outcomes. It’s the closest I’ve found to running a product trio at machine speed.
Guardrails matter. I pair this approach with strong data governance, privacy-by-design, and eval-driven development so every agent’s output is testable and auditable. Clear prompts, scoped corpora, and consistent acceptance criteria keep the Orchestrator honest, while lightweight Agent Analytics helps me see where reasoning falters and where to improve the system.
If your team is still tackling analytics artifacts sequentially—requirements, then instrumentation, then visualization—consider switching mental models. Treat the driver tree as the backbone, empower parallel agents to co-create around it, and reserve human judgment for the critical calls. This is vibe coding for product management: creative, fast, and grounded in measurable outcomes.
AI adoption is everywhere. I see more teams every quarter moving from pilots to production—and increasing their budgets accordingly. But the gap between “using AI” and truly transforming with it is widening fast. Launching an AI Agent is easy; building a mature, AI-powered support operation is where the real work—and the real value—lives.
In the new research, the "2026 Customer Service Transformation Report," the difference comes down to depth of deployment. It’s not enough to dabble. Teams that design their operations around AI are pulling away from those who treat AI like a bolt-on feature.
This article kicks off part one of my five-part deep dive into the research. I’ll unpack the data, share what I’ve learned leading product and AI strategy, and translate it into practical steps you can apply now. If you’d like to go straight to the source, you can download the report here.
First, the macro picture: 2,470 global support professionals across industries were surveyed to understand current AI usage, challenges, and the 2026 opportunities. The headline is clear—AI investment is now table stakes. Eighty-two percent of senior leaders say their teams invested in AI in the past year and 87% say they plan to invest in 2026. Those investments are already paying off: Over three-quarters of CS teams (77%) say AI is meeting or exceeding expectations, delivering faster response and resolution times, always-on coverage, cost savings, increased capacity, and multilingual support that scales globally.
And yet, only 10% of organizations say they have reached a "mature" level of deployment, where AI is fully integrated into operations and working at scale. That’s the tell: most teams are skimming the surface and leaving meaningful performance gains on the table.
Most service teams are still early in AI adoption. Only 10% report mature deployment, while 26% are scaling, 35% are in initial rollout, and 26% remain in exploration, with 3% unsure.
When I map the data to what I’ve seen in the field, the maturity difference shows up immediately in outcomes. Teams at mature deployment don’t just automate repetitive tasks; they build AI into critical workflows, give it real responsibility, and iterate continuously. Beyond automating the bulk of their manual work, they’re using AI to proactively engage customers and perform tasks on their behalf.
The results follow. Of the teams that have reached mature deployment, 43% report higher quality and consistency across support—nearly double the rate of those still in the initial deployment stage. That quality shift is how support evolves from a cost center to a value driver. Great experiences don’t just prevent churn; they create advocacy and become a reason customers choose you. The more you trust your AI Agent with meaningful work, the more it creates the conditions for higher-quality, more consistent support.
One example I point to often: Lightspeed. They operate a complex product across regions and languages, with tens of thousands of monthly requests. When they adopted Fin in early 2023, they needed a solution that could scale with that complexity—and they treated the transition like a first-class change program.
They leveraged foundational training and built custom, in-house modules aligned to their processes. They supported their team post-launch and worked closely with leadership to align on the goals and benefits of AI. In a large, distributed org, that executive alignment created ownership and momentum. Their VP of Information Systems, Yamine Gluchow, put it perfectly: "It’s not magic. If you invest in understanding, adoption, and great content, AI performance takes off."
Mature AI Agent rollouts deliver bigger gains in customer service—outperforming initial deployments in automation, proactive engagement, and task completion (63% vs 52%, 51% vs 41%, 45% vs 28%)—showing how depth drives measurable impact.
Their outcomes reflect that depth: An 88% involvement rate. 72% of Fin conversations resolved without human intervention. 43,000+ customer requests resolved monthly. Service in 12+ languages across 100+ countries. Stable CSAT—with improvement in some markets.
What impressed me most was the complexity Fin now resolves. A merchant in France asked about tax invoices—normally a long phone call to check back-end data and explain rules step by step. Instead, Fin handled the conversation in French, provided an accurate end-to-end explanation, and earned positive CSAT. That’s what mature deployment looks like: a system that absorbs complexity and delivers correct, efficient results at scale.
So how do we build toward that level of maturity? In my experience, this journey requires a mindset shift and operational rigor—not just a bigger AI budget.
Rethink how you approach support. If you were building from scratch today, you’d design around AI from day one. As Grant Lee, CEO of Gamma, puts it: "If you want to unlock the real value of AI, you have to design for it, not retrofit around it." Treat AI as infrastructure, not a feature. That shift impacts your org design, workflows, and what “good” looks like.
Leaders are racing ahead with real AI in support. Explore the 2026 Customer Service Transformation Report to see where deployment is stalling, benchmark your team, and get practical steps to scale automation that delights.
Secure executive sponsorship early. You won’t scale without C-suite backing. AI reshapes how support works, how teams are structured, how performance is measured, and how cost and value flow. Align your CFO on ROI, your CCO on journey design, and your CEO on customer experience as a strategic advantage. Early wins are great—but the compounding gains only come when leadership backs AI as infrastructure, not a one-off cost save.
Assign clear ownership for AI performance. One common failure mode: no one owns the AI. Stand up an AI operations lead or support ops specialist to review resolution trends and handoffs, tune content and configuration, coordinate on systemic issues, and drive a prioritized improvement roadmap. Without this role, feedback loops break and performance plateaus.
Treat content as critical infrastructure. Your AI Agent is only as good as the knowledge it can access. Ensure coverage for the topics it must handle, keep information accurate and current, and structure content so it’s easy for AI to consume. Make maintenance part of BAU, not a quarterly fire drill. A clean, governed, retrieval-first pipeline dramatically increases autonomous resolution.
Build a continuous improvement system. AI performance isn’t static. Train your AI Agent by expanding its knowledge, refining behavior, and connecting new data sources to handle more scenarios autonomously. Validate changes against real scenarios before they ship. Roll out updates in a controlled way across channels and segments. Use performance data to find patterns—frequent handoffs, low-resolution topics—and decide what to improve next. I often point to the Fin Flywheel (Train → Test → Deploy → Analyze) as a practical example of turning performance data into action.
The big takeaway from the "2026 Customer Service Transformation Report" is encouraging: investment is widespread, and early returns are real. The bigger opportunity is to turn those early wins into durable transformation. Teams leaning into AI as infrastructure—supported by executive alignment, clear ownership, strong content, and a continuous improvement loop—are already separating from the pack.
Next up in this series, I’ll dig into how leading teams measure success. Beyond simple cost savings, mature deployments tie AI to clear ROI and strategic impact—shifting more work into value-adding, revenue-generating territory. Follow along here, or subscribe on LinkedIn to get the next installment in your feed.
I look for analytics upgrades that meaningfully compress time-to-insight for product teams. The newest expansion of Amplitude AI Visibility stands out because it improves how we explore user behavior, automate insight creation, and translate data into action across product-led growth motions.
Explore the most recent updates to Amplitude AI Visibility, including content generation, AI chat-driven segmentation, better UI, and improved reliability.
Here’s how I’m thinking about the impact. Content generation can turn raw events into ready-to-share narratives—experiment summaries for A/B testing, cohort deep-dives for retention analysis, and executive briefs that tie outcomes to roadmap decisions. For leaders and ICs alike, this trims the manual lift in Amplitude analytics while keeping the human in the loop to verify context and nuance.
AI chat-driven segmentation is another meaningful unlock. Instead of clicking through complex filters, I can describe the cohort I want in natural language and iterate quickly. That speeds up continuous segmentation work—spotting activation bottlenecks, isolating churn precursors, or defining cohorts for product-led growth experiments—and keeps the team focused on hypotheses and decisions, not interface friction. With LLMs for product managers, the key is pairing this speed with clear guardrails and validation steps.
The updated UI matters more than aesthetic polish. A clearer, more consistent experience reduces cognitive load, improves adoption across cross-functional partners, and reinforces a unified analytics platform approach. Improved reliability, paired with strong observability, increases trust in the stack—critical when insights drive roadmap priorities and high-visibility launches.
Operationally, I’d roll this out with a simple playbook: identify 2–3 high-value use cases (e.g., activation funnel analysis, churn cohort exploration, experiment reporting), define success metrics (time-to-insight, stakeholder adoption, decision velocity), and establish basic AI risk management and data governance guardrails (prompt templates, access policies, and review steps). The goal is to turn AI workflows into a durable capability rather than a one-off novelty.
Bottom line: these enhancements remove friction between questions and answers. If your team relies on Amplitude analytics, the combination of content generation, AI chat-driven segmentation, a cleaner UI, and stronger reliability should accelerate discovery cycles and help you translate insight into action with greater confidence.
Inspired by this post on Amplitude – Best Practices.
I care about meetings only insofar as they create momentum and outcomes. What if your meetings could actually produce the artifacts you need—specs, tickets, slides—before the call even ends?
I recently listened to an episode of Just Now Possible where Teresa Torres talks with Mark Barbir (CEO) and Sanden Gocka (Co-Founder), the co-founders of Earmark, about building a productivity suite that turns unstructured conversations into finished work in real time. As a product leader, this premise hits the sweet spot of agentic AI, real-time AI workflows, and ruthless focus on outcomes over output.
Listen to this episode on: Spotify | Apple Podcasts
Unlike generic AI notetakers that produce summaries nobody reads, Earmark runs multiple agents in parallel during your meetings—translating engineering jargon, drafting product specs, even spinning up prototypes in Cursor or V0 while you're still talking. That’s the bar I want from AI in the room: finished work, not notes.
What impressed me most was the clarity of their pivot. They moved from an Apple Vision Pro presentation coaching tool to a web-based meeting assistant. I’ve made similar calls: when the distribution path and daily workflow are obvious, you follow the user’s gravity. This shift unlocked a broader surface area—PMs, engineers, design partners—and made agentic workflows useful where work actually happens.
They also turned a technical constraint into a commercial advantage. Their ephemeral (no-storage) architecture became a feature for enterprise sales. I’ve seen this repeatedly in AI risk management: privacy-by-design and clear data governance reduce friction with security reviewers and accelerate procurement. For many enterprises, “we don’t store your data” is the win condition.
Cost discipline was another standout. They tackled the hard problem of making real-time AI affordable—from $70 per meeting down to under a dollar through prompt caching. That’s not just optimization; it’s product strategy. Choices like model selection, context window management, and retrieval-first pipeline design determine whether a feature can scale to every meeting or remains a demo.
On capability design, the team leaned into templates and simulated stakeholders to ship value fast. Template-based agents: Engineering Translator, Make Me Look Smart, Acronym Explainer. Personas that simulate absent team members (security architect, legal, accessibility). This is exactly how I frame early AI workflows: remove friction for the product trio, anticipate blockers, and let the agent do the tedious, error-prone first pass.
They were refreshingly pragmatic about models. Why GPT 4.1 still beats newer models for prose quality in their use case is a reminder that “best” is contextual. When the job-to-be-done is precise prose and production-grade artifacts, consistent quality trumps leaderboard buzz. Of course, they also invest in guardrails to ensure quality and manage hallucinations—another non-negotiable for enterprise adoption.
Search and analysis across time is where many AI products stumble. They explained the limits of vector search for analysis questions across meetings and how they’re building agentic search with multiple retrieval tools (RAG, BM25, metadata queries, bespoke summaries). I couldn’t agree more: analysis requires reasoning over structure, time, and purpose—not just semantic proximity. Layered retrieval with stateful agents beats a single embedding call.
They also articulated a crisp user thesis: design for product managers as the extreme user to solve for everyone. In my experience, if you satisfy the PM’s bar for clarity, traceability, and actionability, engineers, designers, and go-to-market teams benefit immediately. That’s how you earn daily active use, not once-a-week novelty.
For builders curious about the stack and comparables, they discuss services and tools like Assembly AI for speech-to-text, OpenAI API with prompt caching support, and build integrations with Cursor and V0 by Vercel. They also reference Granola as a comparison point and nod to ProductPlan, where both founders previously worked. If you want to try the product, here’s Earmark—a productivity suite where the work completes itself.
If you're a PM drowning in follow-up work or a builder curious about real-time AI architectures, this conversation offers a detailed look at what it takes to ship an AI product that people can't imagine working without. Personally, I see this as a credible path toward an AI chief of staff—their vision goes beyond automating deliverables to orchestrating judgment, compliance signals, and cross-functional readiness.
The episode covers the founder backstory, what Earmark does, comparisons to competitors, unique features, templates and personas, technical decisions, early versions and challenges, optimizing transcript summarization, managing multiple tools and costs, challenges with context and reasoning models, innovative search and retrieval techniques, creating actionable artifacts from meetings, ensuring quality and managing hallucinations, and the future vision for an AI chief of staff. It’s a full-spectrum look at building with agentic AI, not just talking about it.
Podcast transcripts are only available to paid subscribers.
