Paras Doshi

Head of Data (Amazon, Opendoor)

Build 3 AI Harnesses for Trustworthy Analytics

Amazon

Opendoor

Give AI the approved metric definition, source, grain, owner, caveats, and freshness rules before it answers

Build a context harness

Catch stale data, wrong denominators, suspicious ranges, and answers that need review before a stakeholder sees them

Build a validation harness

Create a receipt and reusable answer path so the next teammate, agent, or workflow can inherit the reviewed answer.

Build a proof harness

Gain hands-on mastery of AI research tools and frameworks to deliver trusted insights faster while maintaining the rigor that matters.

AI Research Expert | Johns Hopkins PhD

Google

Capital One

Bloomberg

Pinterest

John Whalen, PhD

PhD. O'Reilly author. Host of AI for UX, where I interview AI tool founders.

June 2026

July 2026

The researchers I talk to feel two things at once: overwhelmed by the pace of AI, and watching real possibilities open up that didn't exist two years ago.Both are true. AI lets you run 500 interviews across 12 countries in a week. It surfaces patterns across thousands of sessions. It opens research to teams who never had budget for it. Synthetic users let you pressure-test ideas in hours. These are new ways of working.But how do you trust the output? Which tools deliver, and which produce confident nonsense?That's the shift this course is built around: from doing research one study at a time to orchestrating systems that scale. You'll get hands-on with the platforms researchers actually use (Listen Labs, Coloop, Marvin, Synthetic Users), hear from the founders building them, and build the judgment to know what holds up.This is Course 1 of 2 in the Certified Agentic Research Specialist program — your foundation. Course 2, Agentic AI for Research, builds on it. The researchers pulling ahead are orchestrators — conducting research with more reach, impact, and confidence than before.No hype. Just what works.

Create Customer Insights with AI You Can Actually Trust

Conduct AI-moderated customer interviews confidently

Extract insights from 50+ interviews using AI-powered analysis tools

Develop frameworks to assess new AI tools and know when they actually work

Use synthetic users for rapid testing and validation of ideas before launch

Guide your team or organization in adopting AI research tools and best practices

Connect with practitioners navigating AI research together and sharing insights

You've worked with customer insights in some capacity—whether you've conducted research yourself, collaborated with researchers on your team

Experience with customer research or user feedback

This is a practical course with weekly exercises using AI platforms. You'll need time to experiment and apply what you learn.

Willingness to try new tools hands-on

We use tools and prompting techniques that don't require any coding knowledge. If you can write clear instructions, you're ready.

No technical background required

Researchers seeking to deliver insights faster at scale using AI—while maintaining the quality and rigor that makes their work trustworthy.

PMs and research leaders balancing the need for rapid customer insights with concerns about maintaining quality, rigor, and team standards.

Designers seeking practical AI tools to understand users, test concepts, and make evidence-based design decisions with confidence and speed.

Transform from consumer of analytics to independent operator - asking sharp questions, validating answers, shipping decisions.

Cohort 2

Principal Data Scientist @ Ontra 

Stripe

Nextdoor

PwC India

Ontra

AppFolio

Shane Butler

Principal Data Scientist @ Ontra | Ex-Stripe, Nextdoor, PwC, Appfolio

Data Science Leader |Ex-Microsoft

Microsoft

eBay

Grammarly

Superhuman

Sravya Madipalli

Data Science Leader@Superhuman (Prev. Grammarly)| Ex-Microsoft, eBay, Nextdoor

Head of Data @ Ontra AI | Ex-LinkedIn

LinkedIn

Hai Guan

Head of Data @ Ontra | Ex-Nextdoor, LinkedIn, Pinterest, Meta

Cohort 1

Cohort 3

As AI reduces the value of deep domain silos, the people who thrive will be the ones who can work across disciplines and ship. Analytical independence - the ability to validate your own ideas and make data-informed decisions - remains the missing skill in most builders' toolkits.AI can conduct the analysis, but it can't tell you what to ask or whether the answer makes sense. That requires analytical judgment.This course teaches you to think like a senior Product Data Scientist. You'll learn the frameworks used at FAANG companies to frame problems, choose the right metrics, diagnose root causes, execute the analysis, and turn insights into decisions.-&gt; <a target="_blank" rel="noopener noreferrer nofollow" href="https://join.slack.com/t/dataneighbor/shared_invite/zt-3ox4drc3r-3g0ptSthytkgv0sD6ovvqg">Join AI Builders Slack Community!!</a> &lt;-What makes this different: No SQL. No stats lectures. Five weeks of hands-on real scenarios. You'll build end-to-end, metric specs, deep dives, experiment plans, stakeholder readouts.The result: You become analytically self-sufficient. The last dependency removed from your toolkit. Make data-informed decisions in hours, not weeks.

Ask Better Questions, Make Faster Decisions - with AI as Your Analyst

Frame Problems Like a Senior Data Scientist

Design Metrics That Actually Drive Decisions

Diagnose Root Causes Without Guessing

Design Experiments That Ship

Turn Analysis Into Action With AI as Your Copilot

Synthesize Insights and Prioritize for Impact

Product Managers, engineers, and operators who need analytical independence and frameworks to measure success and drive decisions.

Designers and researchers stepping into strategy roles who need to quantify impact, run experiments, and influence with data-driven insights

Data professionals who want to frame better questions, delegate technical execution to AI, and drive impact with agentic analytics tools.

Eliminate uncertainty in shipping AI features

GenAI Product Builder @ Google, ex-Meta

Marily Nika, Ph.D AI/ML

Senior Data, ML and GenAI Scientist

George Zoto

Senior NLP/AI Scientist

Cohort 4

Cohort 5

“Does it work?”... “Is it good enough?”... “Can we ship it?”...How do you answer these questions for AI products? You’re responsible for “running evals” but what does that mean?How do you choose the right metrics, interpret fuzzy results, and make a confident decision?This course gives you a framework to do just that.<ul><li>Map user value to evaluation (eval) objectives so your metrics aren’t abstract. Define success then translate it into measurable criteria.</li><li>Choose metrics you can actually maintain: capability, safety, UX friction, latency, cost and “does this reduce support tickets or increase activation.”</li><li>Set ship/no-ship thresholds you can defend to leadership.</li><li>Build lightweight workflows that work in real teams: human review where it matters, automation where it lasts, documentation that drives decisions.</li><li>Consider domain constraints (e.g., healthcare safety) and know what to avoid: silent failures, misleading proxy metrics and tests that don’t reflect production.</li><li>Tie everything to ROI: impact vs unit cost, eval coverage vs reliability, and the minimum viable monitoring you need post-launch.</li></ul>Experience AI evals through a case-based approach with a real AI product that we evaluate together.

Acquire and develop a critical skill for product managers who are leading and contributing to AI products.

Make confident ship or hold decisions for AI features

Translate user value into clear evaluation goals

Choose the right metrics for capability, safety, UX, and cost

Set defensible thresholds leadership will trust

Build lightweight evaluation workflows teams can maintain

Navigate domain constraints and avoid common failures

PMs leading AI features, growth, or platform initiatives

PMs who partner with ML teams and want to set evaluation standards

PMs who need to make clear “ship or hold” calls without doing the engineering

You already build agentic analyses for yourself. Learn to make them reliable enough to stand behind in front of a team — across models, with

Co-founder @ AI Analyst Lab

PwC España

You've built an agentic analytics system that works for you. You run Claude Code in the terminal, write skills, chain agents, and ship an analysis end to end. This course is the next step: making that system reliable enough to trust at team scale.Solo, you can eyeball whether an answer looks right. Across a team, you can't. Two people run the same query and get different numbers. The model your workflow depends on gets deprecated overnight. An AI-written analysis reads beautifully and is quietly wrong. This course engineers past all three.You'll swap the brain of Claude Code between frontier and open-source models, so you're never locked in or cut off. You'll build a multi-model validation loop where one model builds, another reviews, and you judge the disagreement, plus the four eval types that catch what a single pass misses. And you'll engineer the context and semantic layers that makes any model produce consistent, audience-ready work.You leave with a complete agentic analytics system you built yourself, one repo that runs on both Claude Code and Codex, and reference guides you'll keep using.For people who already work agentically and want to do it reliably, at team scale.

Proven playbook to make your AI data analyst reliable enough to trust at team

Swap the brain of Claude Code between any model

Validate AI data analysis with confidence

Engineer context so any model stays consistent

Codex and open-source model compatible agentic analytics system

Product managers already using Claude Code for analysis. You've built skills and agents. Now build a system that validates its own output.

Data scientists who know how to work with Claude Code. Now automate the full workflow: context loading, analysis, validation, and narrative.

Analysts and engineers comfortable with skills and agents who want to go deeper in Claude Code.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Data scientists who apply statistical and ML techniques to extract insights from data.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Using data and metrics to measure performance, run experiments, and inform decisions.

Measuring and evaluating AI model performance, quality, and reliability for production use cases.

Business analysts defining requirements and bridging business and technical teams.

Automating professional workflows with AI tools — productivity, operations, and task automation.

Designing and optimizing the context window for LLM applications — prompt structure, memory, and information retrieval.

Operating and deploying large language models in production — fine-tuning, inference, monitoring, and cost optimization.