Tag: LLMs for product managers

Eliminating the Last Bottleneck: Agentic AI in Amplitude That Builds What Matters Faster

For years, I’ve watched high-performing product teams run into the same wall: the gap between insight and action. Dashboards multiply, yet decisions stall. That final mile—where we interpret trends, prioritize tradeoffs, and ship changes—remains the last bottleneck. It’s not a data problem; it’s a bandwidth and focus problem.

Amplitude's AI Analytics Platform takes the next step: agents that investigate, monitor, and act so your team can build what actually matters.

From my seat leading product at HighLevel, I see “agentic AI” as a structural upgrade to the product operating system. Instead of waiting on human cycles to discover anomalies, craft hypotheses, and trigger the next experiment, Agent Analytics can continuously investigate user behavior, monitor mission-critical metrics, and initiate actions—closing the loop from observation to outcome. That shift transforms analytics from a passive reference layer into an active, decision-making teammate.

Practically, this matters because empowered product teams win on speed and focus, not on the volume of reports. When agents surface the most material opportunities—say, a sudden drop in activation for a high-value cohort or a retention dip tied to a recent release—we compress time-to-insight and, more importantly, time-to-action. The result is fewer context switches, fewer meetings, and more cycles invested in building meaningful value.

The most compelling use cases are those that compound: continuous discovery that highlights friction in onboarding flows, proactive retention analysis on at-risk segments, automated experiment prioritization aligned to outcomes vs output OKRs, and closed-loop alerts that trigger workflows in your CRM or in-app guides to accelerate product-led growth. With a unified analytics platform feeding these agents, we can move from reactive analytics to anticipatory product strategy.

Of course, leverage requires guardrails. I anchor adoption in three pillars: clear decision rights for agents (what they can autonomously act on vs. recommend), transparency in reasoning (so PMs can audit how conclusions were reached), and explicit alignment to key outcomes (activation, retention, expansion). Done right, this is not a replacement for product judgment—it’s an amplifier for it.

If I were rolling this out today, I’d set a success dashboard that tracks: time-to-insight, time-to-action, percentage of initiatives initiated by agents, impact on North Star metrics, and the reduction in manual analysis hours. I’d also implement lightweight prompts and playbooks—LLMs for product managers—that standardize how we ask better questions and interpret agent outputs.

The promise here is simple but profound: eliminate the last bottleneck by giving your teams a partner that never sleeps, never tires, and never loses the plot. When agents investigate, monitor, and act, we spend less time arguing about the data and more time building the right things, faster.

Inspired by this post on Amplitude – Best Practices.

February 19, 2026
Inside ShowMe’s Playbook: Orchestrating Voice, Video & Multi‑Agent AI Sales Reps that Close

What happens when you treat an AI agent not as a chatbot, but as a full teammate on your sales team – one that can jump on video calls, demo your product, make phone calls, and follow up over days?

I recently dug into this question with the team behind ShowMe, an AI-native startup building digital sales reps for inbound teams. Founded in April 2025, ShowMe has engineered a multi‑agent system that combines conversation agents for live voice and video interactions, evaluator agents that score every call for quality and sentiment, and creator agents that ingest customer documentation to build tailored playbooks. A workflow layer orchestrates the entire lead‑to‑close journey across days, not minutes—exactly the kind of agentic AI approach I expect to see become standard in revenue workflows.

What stood out to me first was the origin story: a glaring conversion gap on a previous website, and the realization that a purpose‑built AI could fill it. The initial MVP was refreshingly pragmatic—start with a voice agent, pair it with product videos, and back it with a simple RAG knowledge base. That retrieval‑first pipeline let the team ship quickly, validate real user behavior, and then scale sophistication where it mattered.

Then came a pivotal affordance shift: adding a realistic avatar via HeyGen. It wasn’t just eye candy; it changed how prospects engaged. The video-call UX established trust and made the AI’s capabilities legible at a glance. Prospects behaved as if they were with a human rep—interrupting, probing, and asking for demos—because the surface area invited that behavior.

On the architecture side, the team decomposed a single sales conversation into multiple specialized sub‑agents—greeting, qualifying, pitching—to manage latency, memory constraints, and model limitations. Deterministic workflows handle the happy paths reliably, while a smart orchestrator is emerging to break out of rigid paths when context demands it. Confidence scoring and frustration detection kick in for real‑time human handoff decisions, a must for revenue‑critical moments where a missed nuance can cost pipeline.

Training the system to sell like your team is where it gets powerful. ShowMe ingests sales transcripts and training materials to teach company‑specific sales skills, then uses creator agents to assemble tailored playbooks. Conversation agents stay focused on live interactions, while evaluator agents continuously score calls for quality and sentiment. The result: repeatable, compliant, and brand‑consistent selling—without flattening personalization.

Quality isn’t an afterthought—it’s operationalized. Early deployments run with customer-driven evaluation loops where 100% of conversations are reviewed, tapering to about 5% over time as confidence increases. Feedback becomes automated tests to prevent prompt regression, and production quality is proven with POCs, A/B rollouts, dashboards, and CRM logging. This is eval-driven development applied to go‑to‑market: measurable, auditable, and continuously improving.

I also appreciate how they treat the agent as a coworker, not a widget. Onboarding happens via Slack, weekly reporting aligns with sales leadership rhythms, and tight CRM integration keeps data flowing both ways. That mindset unlocks adoption because it fits how sales teams actually operate—and it creates real Agent Analytics you can manage.

From a product perspective, several pragmatic details matter. Real‑time voice and avatar demos rely on latency tricks and a library of video clips to keep interactions snappy. The conversation agent evolved from a basic Q&A bot into guided sales discovery, balancing personalization with the ever-present risks of hallucination. Guardrails, human‑in‑the‑loop, and clearly defined handoff rules are non‑negotiables in high‑stakes sales workflows.

Looking ahead, the roadmap makes sense: move toward self‑serve PLG setup, add smarter orchestration that adapts beyond deterministic flows, and expand into adjacent roles like customer success. For product leaders building in gen ai, the pattern here is instructive: start with inbound value, design AI workflows that align to proven sales motions, and use rigorous evals to earn the right to automate more.

If you want to go deeper into the build, the live demos, and the full multi‑agent orchestration, listen to this episode on: Spotify | Apple Podcasts. For more on the stack, explore ShowMe and the avatar platform HeyGen.

Inspired by this post on Product Talk.

February 19, 2026
Implementing AI Agents That Scale: My Playbook for One‑Person Departments with Amplitude

Over the past few years, I’ve led cross-functional teams to deploy agentic AI in production, and I’ve learned that success rarely hinges on the model alone. It comes from methodically designing the right workflows, instrumenting every step, and building a feedback loop that compounds. Learn how companies like Replit are consolidating workflows, creating one-person departments, and building systems for scale with Amplitude.

When I talk about AI agents, I’m describing software that behaves like a focused teammate—owning a clear job to be done end-to-end. In practice, that means consolidating fragmented tasks into a single accountable “one-person department,” then giving it the context, tools, and analytics to perform reliably. This is how agentic AI moves beyond demos into durable business impact.

I start with outcomes, not algorithms. I map a driver tree from business goals (e.g., lower response time, higher activation, better retention) to the specific moments an agent can influence. This outcome-first alignment keeps scope tight, informs guardrails, and grounds the value proposition in measurable change instead of vanity metrics.

Next, I define the workflow the agent will fully own. I look for high-volume, rules-adjacent processes—think lead qualification, support triage, or billing inquiries—where clear decision criteria already exist but human time is the bottleneck. I document triggers, inputs, decision points, and handoffs, then design the ideal-state flow the agent will run autonomously, with transparent escalation paths to humans.

On architecture, I favor a retrieval-first pipeline to keep responses accurate and current. I scope the knowledge base, implement context window management, and standardize tools the agent can call (search, CRM actions, ticket updates). For teams new to this, I coach “LLMs for product managers” fundamentals so we make sensible trade-offs between speed and reliability rather than chasing model-of-the-week headlines.

Instrumentation is where the system becomes self-improving. I use Amplitude analytics and an Agent Analytics schema to track intent detection, tool usage, resolution rate, time-to-resolution, deflection, and escalation causes. A unified analytics platform lets me connect agent outcomes to core product metrics—activation, retention, and conversion—so we can see the real revenue and experience impact, not just local efficiency gains.

To validate impact, I run A/B testing when traffic allows, setting a minimum detectable effect (MDE) upfront to avoid inconclusive reads. In lower-volume scenarios, I lean on eval-driven development: curated test sets for edge cases, scenario-based regression suites, and error taxonomies that accelerate iteration. Feature flags let us stage capabilities safely (shadow mode, assistive, autonomous) while we monitor deltas before full rollout.

Reliability and trust are designed in from the start. I apply AI risk management practices—privacy-by-design, data governance, and policy-aligned prompt templates—paired with observability to trace decisions. Clear escalation policies, incident management runbooks, and human-in-the-loop checkpoints ensure the agent fails safe, not silently.

Shipping cadence matters. I use CI/CD to increase deployment frequency, keep prompts and tools versioned, and gate risky changes with targeted rollouts. As patterns stabilize, we scale horizontally to new use cases, sharing core capabilities (retrieval, analytics, guardrails) as a platform. This is how “one-person departments” multiply without multiplying overhead.

Change management closes the loop. I partner with product trios and frontline teams to co-design prompts, set acceptance criteria, and define what “good” looks like in plain language. In-app guides and product tours introduce the agent’s role and limits, and structured feedback channels feed directly into our discovery and iteration rhythm.

The throughline of this playbook is simple: treat agents like real teammates with a job description, operating procedures, and performance reviews. With disciplined workflow design, a retrieval-first pipeline, and outcome-level instrumentation in Amplitude, agentic AI stops being a science project and starts compounding into durable product-led growth.

Inspired by this post on Amplitude – Perspectives.

February 18, 2026
Go From 3 Customer Interviews to a High-Quality Opportunity Solution Tree—In Minutes

Most product teams—and especially well-run product trios—know they should be interviewing customers. More teams than ever are actually doing it. That’s the good news.

The bad news? Many teams still struggle with what comes next. Turning raw recordings into a structured opportunity space that truly guides product discovery can feel overwhelming.

In my experience, interview synthesis is cognitively demanding work. You have to extract the key moments from each conversation, translate those moments into clear opportunities, and then organize those opportunities into a coherent view of your opportunity space. It’s no surprise I hear teams say, "We need to stop interviewing so we can catch up on what we’ve already learned." Too often, they pause—and never start again.

Recordings pile up. Maybe there are scattered notes. But nothing gets turned into an opportunity solution tree. The team hasn’t synthesized what they’ve learned, so the research isn’t actionable. That’s the gap I want to help close.

What if you could go from 3 interviews to a draft OST in minutes?

My AI goals are straightforward: 1) build tools that help you learn discovery and 2) build tools that help you do discovery. The learning tools are coming through on-demand courses. Today, I’m excited to share the first big step on the "do" side.

I’m excited to see an expanded partnership with Vistaly—the opportunity solution tree tool many of you already use—to bring AI-powered discovery tools directly into their platform.

Great synthesis happens in two steps: first, you synthesize each interview separately; then you synthesize across interviews. Most AI tools skip the first step and jump straight to cross-interview analysis—exactly how teams lose the nuance and context that make research actionable.

This approach does both. You upload three interviews for the same product outcome. The AI extracts the key moments and opportunities from each one separately. Then it synthesizes across those interviews and generates a first draft of your opportunity solution tree for you. Three interviews in. A draft OST out.

Here’s what this is—and what it isn’t. You’ve probably heard criticism of tools that promise "one-click opportunity solution trees." Those tools ask you to describe your market, click a button, and get a tree. The point of an opportunity solution tree is not to have one—it’s to synthesize what you’re learning from real customers so your team can align on the best path forward. A one-click tree built from made-up data is useless.

Turn interviews into insights in minutes with Vistaly. This hero screen invites you to enroll in beta and showcases an opportunity solution tree that maps outcomes to opportunities and actionable solutions.

This approach is fundamentally different. It starts with your real customer interviews. The AI does the heavy lifting of extracting key moments and opportunities from those conversations and organizing them into a draft opportunity solution tree. But it’s a draft—you review it, refine it, and reorganize it. You bring your judgment and context to the work.

My vision for AI-aided cross-interview synthesis is simple: AI identifies common opportunities across interviews, suggests a tree structure, and facilitates the team’s review. Historically, it’s been hard to give AI access to an opportunity solution tree in a way that preserves structure and context. The integration with Vistaly solves that problem by building this capability directly into the tool where your tree already lives.

In my own experiments using Claude, the AI surfaced opportunities I missed—and I caught things it missed. The highest-quality synthesis came from combining both perspectives. Research (see here and here) backs this up: Experts working with AI outperform both experts working alone and AI working alone. That’s the model we’re building toward—AI generates the draft, you bring the expertise.

I have mixed feelings about AI doing discovery work for us because there is real value in doing the synthesis yourself. But I also know that a draft OST you actually refine is better than a perfect process you never get to. This is about raising the floor—helping more teams get to a structured opportunity space, even if they aren’t doing every step manually.

We’re looking for a small group of alpha partners to help shape this product. To apply, sign up for a free Vistaly account and upload three customer interviews for the same outcome or product space.

We’ll select alpha partners from the applicants. We want a range of interview styles, experience levels, and product spaces. Selected partners will get access to the AI-powered synthesis tools and will work closely with the team to shape the product. Even if you aren’t selected for the alpha, your application puts you at the front of the line when we enter beta.

A few things to know as you apply: Your three interviews should be for the same outcome, goal, or product space, so the tool can generate a meaningful OST. You don’t need to be a Vistaly user today—the account is free. You don’t need to be an expert interviewer either; we’re looking for a range of experience levels, though we’re particularly interested in story-based customer interviews.

This is just the beginning. The vision is a full AI-powered discovery suite inside Vistaly—from interview analysis to complete interview snapshots to opportunity solution trees and beyond. We’ll learn alongside our alpha partners and share what we discover as we go.

If you’ve been looking to bridge the gap between your customer interviews and your opportunity space, this is your chance to help shape how that works. Apply for the alpha today.

Inspired by this post on Product Talk.

February 18, 2026
LLMs vs AI Agents: Hard‑Won Lessons Product Teams Need to Nail for Real‑World Impact

When people ask me about "LLM vs AI Agents: What Product Teams Must Get Right," I start with a simple truth: an LLM is a powerful prediction engine, while an AI agent is a productized workflow that plans, takes actions with tools, remembers, and closes the loop on an outcome. That difference sounds academic until you’re on the hook for reliability, cost, and customer trust.

In my role, I’ve shipped LLM copilots that delight users and piloted agents that automate complex workflows. The pattern that never fails is this: start assistive, then graduate to autonomy. Copilots accelerate people; agents own outcomes. When we respect that gradient, adoption climbs, incidents fall, and we earn the right to expand scope.

The first decision point is use-case fit. If the task benefits from human judgment, high-context nuance, or brand voice, I frame it as a copilot with strong guardrails and crisp UX. If the task is well-bounded, tool-heavy, and verify‑able, I consider an agent—but only after we can measure end‑to‑end task success with eval-driven development.

Architecture matters. I reach for a retrieval-first pipeline to keep responses grounded in authoritative data, then add tool use for actions (search, write, schedule, transact) with deterministic scaffolding to prevent thrashing. Good prompt engineering is table stakes, but context window management and a clean memory strategy (short‑term scratchpad, long‑term facts, and policy) separate demos from durable systems.

Agents amplify both value and risk. I build safety in layers: role and scope definition, tool whitelists, unit limits, human‑in‑the‑loop checkpoints at irreversible steps, and privacy-by-design data governance. We log every decision token-for-token because auditability isn’t optional once agents touch customers, money, or data.

Measurement is non‑negotiable. For LLM features, I track time‑to‑first‑token, response latency, groundedness, and user satisfaction. For agents, I add Agent Analytics: task success rate, number of steps per task, tool error rate, loop detection, guardrail triggers, escalation to human, cost per successful task, and containment rate. If we can’t see it, we can’t ship it.

My delivery playbook mirrors modern software ops. We use feature flags, gated betas, and canary rollouts; we version prompts like code; we set incident management paths for model outages and tool drift; and we rehearse fallbacks so the experience degrades gracefully, not catastrophically. Dull operations build dazzling products.

On roadmapping, I thin‑slice value. We introduce a minimal viable copilot that handles a single, frequent job-to-be-done with high success. Only after continuous discovery confirms product‑market fit do we grant more autonomy, one capability at a time. Outcomes vs output OKRs keep us honest: if the customer’s job gets done faster, cheaper, and with fewer errors, we scale; if not, we fix fundamentals before adding scope.

Build vs buy is rarely binary. I tend to buy the undifferentiated heavy lifting—observability, prompt versioning, red‑teaming, and policy enforcement—while building the proprietary workflows, data modeling, and UX that encode our defensible advantage. The litmus test: if it’s part of our unique value proposition, we own it; if not, we integrate the best‑in‑class and move.

Go‑to‑market must be as rigorous as the tech. We position clearly (assistant vs agent), price to value with transparent consumption SaaS pricing, and communicate risk posture in plain language. Customers don’t buy models; they buy confidence that a job gets done reliably within their constraints.

Common failure modes repeat: shipping autonomy before instrumentation, treating prompts as magic instead of software, skipping data governance, and ignoring the human experience. The antidote is disciplined AI Strategy rooted in empowered product teams, tight feedback loops, and relentless evaluation.

If you take nothing else: choose the right paradigm for the job (copilot first, agent when proven), ground with a retrieval-first pipeline, instrument with eval-driven development and Agent Analytics, and operationalize like a mission‑critical system. Do that, and you’ll turn LLM capabilities into durable product outcomes.

Inspired by this post on Product School.

February 18, 2026
Can AI Agents Master Enterprise Analytics? My Proven Task Framework and Amplitude Insights

Every week, product and data leaders ask me the same question: can AI agents truly shoulder enterprise analytics without sacrificing trust, governance, or speed? I’ve spent the past year putting agentic AI through its paces in real product workflows, and I’ve distilled what works into a practical, task-driven evaluation approach you can adopt immediately.

Learn how to evaluate AI analytics agents with a task-based framework across analytics tasks. See how Amplitude’s Global Agent scores.

When I say “enterprise analytics,” I’m talking about far more than chatty dashboards. The bar includes consistent metric definitions, privacy-by-design, RBAC and data governance, audit trails, low-latency decision support, and repeatable outcomes across retention analysis, funnels, cohorts, A/B testing, instrumentation planning, and anomaly detection—ideally within a unified analytics platform.

My task-based framework evaluates eight capability pillars I expect from an enterprise-ready Agent Analytics solution: task coverage and depth across common product analytics workflows; data fidelity and governance (lineage, access controls, PII handling); instruction-following and reasoning transparency; evaluation rigor and reliability (repeatability, error modes, regressions); security and compliance posture; latency and cost efficiency; integration into existing product strategy workflows (e.g., CRM integration, CI/CD-linked instrumentation, experiment platforms); and human-in-the-loop controls for approvals and guardrails.

Operationally, I define canonical tasks that reflect day-to-day product management: codify a North Star metric; perform retention analysis by cohort; generate and explain a funnel with drop-off drivers; recommend an event taxonomy and tracking plan; analyze an A/B test with minimum detectable effect (MDE) considerations; and propose a driver tree that maps inputs to outcomes. Each task comes with ground-truth datasets, acceptance criteria, and edge cases to stress the agent—an eval-driven development practice I’ve found indispensable.

I then score maturity across four levels. L0: a pure chat UI that summarizes existing charts. L1: a retrieval-first pipeline that grounds responses in your analytics catalog and metric store. L2: a tool-using agent that is schema-aware, can write safe SQL, and reconciles results to canonical definitions. L3: a governance-aware autonomous workflow that executes analytics tasks end-to-end with approvals, audit logs, feature flags, and rollback plans. Most teams discover they’re between L1 and L2; reaching L3 requires serious investment in data governance and eval automation.

Risk management is non-negotiable. I require strict data governance and privacy-by-design controls, including scoped credentials, PII redaction, policy-aware retrieval, and comprehensive observability (query traces, prompt/response logs, lineage). Feature flags and approval gates prevent unintended metric redefinitions. Red-teaming tasks expose prompt injection, schema drift, and hallucination failure modes before they hit production stakeholders.

Where do agents shine today? Rapid exploration, SQL generation from schema context, summarizing experimentation results, and turning natural-language questions into actionable charts. Where do they struggle? Ambiguous metric semantics, under-specified experiment designs, and edge-case-heavy analyses where ground truth depends on organizational nuance. The cure is disciplined product management: codify definitions, maintain a living analytics taxonomy, and continuously harden your eval suite.

In the context of product analytics stacks, Amplitude analytics is a common anchor for product teams, and many are evaluating “Amplitude’s Global Agent” to accelerate insight generation. In my framework, I look for how well it grounds to canonical metrics, handles retention and funnel tasks, explains trade-offs, and respects governance boundaries—before I consider expanded autonomy. I share the full task matrix and scoring rubric so you can replicate the assessment in your environment.

If you’re getting started, pick your top ten high-frequency analytics tasks and define crisp success metrics for each (accuracy, explainability, latency, and reusability). Build a small eval harness with golden datasets, assertions, and regression tests. Favor a retrieval-first pipeline tied to your taxonomy and metric store, add human-in-the-loop approvals for sensitive actions, then pilot with a cross-functional tiger team. Measure time-to-insight, analyst hours saved, and stakeholder trust—then iterate.

Enterprise analytics isn’t a single feature; it’s a system of definitions, workflows, and governance. With a task-based, eval-driven approach, agentic AI can become a reliable partner—not just a novel interface. If you’re evaluating options, apply this framework first, then expand scope as reliability and trust climb.

Inspired by this post on Amplitude – Best Practices.

February 17, 2026
Multi‑Agent Systems Demystified: Why One AI Isn’t Enough—and How I Ship Faster With Many

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.

Inspired by this post on Product School.

February 16, 2026
Context Engineering Playbook: 5 Proven Ways to Slash Context Rot and Scale Smarter AI

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.

Inspired by this post on Product Talk.

February 11, 2026
Reinventing Product Management Workflow: The AI Upgrade I Use to Ship Faster, Smarter

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.

Inspired by this post on Product School.

February 11, 2026
From Chaos to Clarity with Claude Code: My Hands-On Playbook for Product Leaders

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.

Inspired by this post on Product Talk.

February 10, 2026
Build CX Scores You Can Defend: My 5-step playbook for transparent, trustworthy AI metrics

“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.

Inspired by this post on The Intercom Blog.

February 9, 2026
Vibe Coding Unleashed: How Parallel Agents Build KPI Driver Trees in Under Two Hours

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.

Inspired by this post on Pendo – Best Practices.

February 5, 2026