Seller Sessions Amazon FBA and Private Label

Danny McMillan and Ritu Java cover AI remote control, token-saving skills and burnout resets so you can step away from the desk and keep projects moving.

Ritu Java is back for the monthly Go With The Flow show, fresh from Accelerate and a lot of conversations about how fast AI adoption is moving. Her problem will sound familiar: chat is faster than she is, so she has become the bottleneck on her own projects. This episode is about AI on the move, running your work from your phone so you can walk, hike or cook without losing control.

You'll hear how Claude remote control and Codex remote work in practice, what the catches are, and where Gemini Spark fits in for anything that lives in the Google ecosystem. Danny shares a plan-reading tip that cuts cognitive load, then the pair dig into where agency token spend really goes, why deterministic Python and SQL beat AI judgment on cost, and how to keep a stack of 90 skills clean as models change.

They finish on the human side: Ritu's two past burnouts, Danny's reset habits, and why controlling your attention matters more than keeping up with every new release.

• AI on the move - running Claude and Codex sessions from your phone while away from the desk
• Claude remote control vs Codex remote - one-time setup, per-project setup, and the "laptop must be open" catch
• Gemini Spark - an always-on assistant for Gmail, Calendar, Tasks and BigQuery
• Plan-reading tip - ask for a natural language plan on top and the technical plan underneath
• Where tokens really burn - judgment work, scraping, images, video, browser work and MCPs versus leaner CLI and scripts
• Skill hygiene - using /insights and /doctor, merging duplicates and building a skill map
• Burnout and resets - breaks, walks, meditation and protecting your attention

• 00:00 - Danny welcomes Ritu back for the monthly show
• 00:14 - Ritu on Accelerate and the AI adoption shift
• 01:01 - The foundation problem: chat is faster than the human
• 03:15 - Claude remote control: how it works
• 04:43 - The terminal quirk for activating remote control
• 06:23 - Answering Claude from the car (and why not to)
• 06:43 - Danny spots the new remote control toggle in Claude Desktop
• 07:56 - The catches: laptop must be open, set up per project
• 08:22 - Codex remote: desktop and mobile mirror each other
• 09:21 - Sharing one GitHub between Claude and Codex
• 10:02 - The protocol: plan at the desk, follow up on the move
• 11:05 - Danny's plan tip: reject early plans, ask for a plain-English top half
• 12:40 - Gemini Spark for the Google ecosystem
• 13:58 - How steep is the Claude to Codex learning curve?
• 15:06 - Sonnet 5.5 efficiency versus Opus 5.5 cost
• 15:49 - Running 86 to 90 skills and watching token usage
• 16:41 - Left brain versus right brain: where tokens skyrocket
• 18:15 - MCP versus CLI token cost
• 19:10 - Running /insights and /doctor over your skills
• 21:38 - Maintenance: old scaffolding can slow newer models
• 22:23 - What Ritu actually does on the road
• 23:18 - Notepads and breadcrumbs: Apps Script on Gmail
• 24:14 - Client sentiment analysis from email
• 25:10 - Staying fresh and Ritu's two burnouts
• 26:52 - Danny's resets: walks, meditation and breaks
• 28:31 - Wrap-up: the luxury of experimentation
• 30:15 - Danny: control your time and attention
• 31:12 - Where to find Ritu

• Plan at the desk, steer on the move - do the heavy work in one sitting, then answer questions and corrections from your phone.
• Know the catches before you rely on remote control - the laptop has to stay open, and Claude needs setup project by project while Codex is enable-once.
• Ask for a plain-English plan - a natural language top half with the technical plan underneath makes plan review far easier on your brain.
• Push repeatable work into scripts - Python and SQL cost nothing once built, while judgment, scraping, images, video and browser work eat tokens.
• Maintain your skills - merge duplicates, add a skill map, and retire guard rails that newer models no longer need.
• Protect your attention - pick a handful of things to follow, set boundaries and take real breaks before burnout does it for you.

"Chat is faster than me, and I'm seeing that I am becoming the bottleneck." - Ritu Java

"We thought AI could make us freer than before. No. I feel like a slave. But it's fun." - Ritu Java

"Scaffolding or guard rails you put in eight months ago can actually slow the model down." - Danny McMillan

"Control your time and attention, because AI is going to drop something new every single day." - Danny McMillan

• Claude remote control - lets you answer a running Claude Code session from the Claude app on your phone
• Codex remote (ChatGPT Codex) - mirrors desktop and mobile, enabled once for every project, Mac only
• Gemini Spark - always-on assistant in enterprise Google Workspace for Gmail, Calendar, Tasks and BigQuery
• /insights and /doctor - built-in commands for reviewing and tidying your skills
• Google Apps Script - used to mine email for notes, ideas and client sentiment
• Notion and Freeform - Danny's breadcrumb tools outside Claude

Ritu Java - find her on LinkedIn under her full name

Seller Sessions is the leading podcast for advanced Amazon sellers, hosted by Danny McMillan.

Danny McMillan and Shubhash unpack the Fable 5.1 vs Astra debate, the six-stage AI harness, and why your folder structure is the real cost lever.

Shubhash joins from his new home in Dubai to dig into the two biggest AI releases of the fortnight, Fable 5.1 and Astra, dropped within 72 hours of each other. Instead of relitigating which model wins, he makes the case that "which model is better" is the wrong question entirely, and spends the episode showing why.

You'll hear the real cost story behind cached tokens, why a shiny 3D render says nothing about which model is actually smarter at your business's real work, and Shubhash's six-stage "harness" framework for judging any AI tool. Danny closes with a teaser: an enterprise AI consultant's folder-as-operating-system approach that could cut token burn without touching the model at all.

• Fable 5.1 vs Astra - what a codebase-drift benchmark actually revealed, beyond the marketing screenshots
• The cached-token price trap - why identical list prices don't mean identical bills
• The six-stage harness - job, prompt, tools, model, failure handling, pass mark
• Model-switching without the cost trap - avoiding preloaded tools when routing to third-party APIs
• Claude Desktop as a single workspace - Danny's parallel-conversation, no-VS-Code setup
• Folders as the AI operating system - a teased framework for scoping context with markdown files

• [00:01] Shubhash joins from his new home - relocated to Dubai
• [00:57] Agenda: Fable 5.1 and Astra, launched 72 hours apart
• [01:24] Danny's pushback - "are they building anything?"
• [01:50] Shubhash: "which model is better" is the wrong question
• [02:06] Ellis's LinkedIn benchmark - Astra similar quality to Fable 5.1, lower cost
• [03:13] Where Astra broke - drifting from existing codebase conventions on the hardest tasks
• [04:29] Why comparison screenshots are confirmation bias - published by the model's own maker
• [05:35] Shubhash's five-point checklist before adopting any new AI tool
• [06:59] "A model is just an engine" - the car and harness analogy
• [08:28] The real price difference - cached token reads, 25c vs $1 per million
• [09:35] Season ticket vs pay-on-the-gate pricing
• [09:54] How few sellers actually examine their AI bill
• [11:41] Avoiding the third-party API cost trap - tool preloading
• [12:20] Real example - a $4.50 job cut to 35p once preloading was stripped out
• [12:40] Where Astra genuinely wins - 3D renders, exploded views, web design
• [13:46] Splitting by job type - Astra on design, Claude on knowledge work and recovery
• [14:30] The six-stage harness framework introduced
• [17:12] "The model is the sex and sizzle" - Danny's framing
• [18:21] Shubhash's VS Code setup - Claude and Codex extensions handing off work
• [19:52] Danny's Claude Desktop-only workflow, no VS Code
• [20:22] Finder and Spotlight optimisation, Kimi K3 kept to the terminal only
• [23:39] Widgets over walls of text - "like a kid's colouring book"
• [24:24] Natural-language plan on top, technical plan underneath, on request
• [24:45] Freeform and stylus for complex problem-solving
• [25:50] Raycast as a free Spotlight replacement
• [27:08] Why "you don't need instruction files anymore" ignores who's paying for the tokens
• [27:56] Teaser - an enterprise AI consultant's file-structure system
• [29:15] The folder-as-AI-operating-system concept
• [31:27] Three-layer breakdown - the map, context rules, work tools
• [33:45] Wrap-up - Shubhash's three-question pre-switch checklist

• "Which model is better" is the wrong question - the harness around the model decides the outcome far more than the model itself.
• List prices hide the real cost - cached-token rates can be 4x apart even when headline pricing looks identical.
• Split tasks by strength, not loyalty - Astra ahead on visual and web design work, Claude ahead on knowledge work, long documents and error recovery.
• Tool preloading is the hidden API cost - stripping it out cut one job from $4.50 to 35p.
• Your folder structure is your harness - scoping Claude to only the context a task needs cuts token waste before any model swap is needed.

"A model is just an engine. If you haven't built the car, the chassis, the tyres, everything else around it, a faster engine isn't getting you anywhere." - Shubhash "You don't pay your goalkeeper up front just because he's the best athlete in the squad." - Shubhash "The model is the sex and sizzle, not the bit underneath it." - Danny McMillan "Before you chase the next model, write down only what you know... get that right and we are good." - Shubhash

• Fable 5.1 - the latest release under discussion, benchmarked against Astra on real codebase tasks
• Astra (GPT-6) - OpenAI's release, strong on visual/web design work, weaker on holding existing coding conventions
• Raycast - free Spotlight replacement Shubhash uses for local search
• VS Code (Claude + Codex extensions) - Shubhash's multi-agent handoff setup
• Claude Desktop - Danny's single-workspace setup: parallel conversations, in-app browser and file viewer
• Freeform (iPad + stylus) - Danny's tool for mapping out complex problems before handing them to Claude

Shubhash - Not a Square, now based in Dubai (relocated from London)

Seller Sessions is the leading podcast for advanced Amazon sellers, hosted by Danny McMillan. Ritu returns next week for Go With The Flow; Shubhash is back next month.

Danny McMillan and Sim on model switching, OpenRouter cost hacks and whether AI spend for Amazon teams is actually worth it.

A quick solo show this week — Dorian's out sick, Matt's unavailable, so it's just Danny and Sim covering how to control AI spend without gutting output.

Sim walks through the real cost pressure of a 25-person team on Claude: five figures a year, uncapped Fable usage, and no way to see per-person burn. Danny counters with the setup he's built to fix exactly that — routing grunt work through OpenRouter and Kimi K3 without preloading tools, which took one job from £4-5 down to 35p. They land on a practical split: Fable 5 for planning, a cheaper model for the build, staged "cascade" plans to keep context windows under control. Sim also shares a genuinely wild same-day case study — a 100-video yoga app build for about £300 — and Danny pushes back on the whole framing: stop looking at AI as a cost line and start looking at what it's generating.

Key Topics Picking one AI provider and sticking with it - the cost of switching a trained team, and why Astra being better than Fable isn't reason enough to move Why teams actually burn tokens - heavy browser automation, parallel video work, and vibe-coders scaling far past their job description The OpenRouter cost hack - Kimi K3 without preloaded tools, cutting one job's cost by roughly 90% Cascade planning - staging big builds across multiple sessions to control context window burn Chinese model options - GLM 5.3 and LM Studio AI as free-to-cheap alternatives Grok as a low-friction accessory - personal automation for AI-hesitant team members ROI framing - weighing AI spend against what it actually produces, not just what it costs Timestamps [00:01] Quick solo show - Dorian ill, Matt unavailable, flight to Mallorca later [01:02] Wishing Dorian a speedy recovery, back next month [01:17] Kicking off: token costs, Astra's release [01:42] Why constant provider-switching burns team trust and training [02:10] History: Google/Gemini 18 months ago, Claude masterclass in December, full team switch [02:29] Sim's Opus 5 complaint - unclear responses, had to cross-check with Sonnet [02:58] Fable's cost problem - no way to cap runaway usage [03:28] Costs into five figures a year; splitting power users vs Chinese-model users [03:54] The NVIDIA DGX Spark purchase for local model runs [04:32] Danny's setup: Kimi in the terminal, Claude Desktop for daily work [04:59] The two real causes of heavy token burn: browser automation, parallel video editing [05:58] The "I've got ADHD" repo - controlling how Claude communicates [06:25] Claude Desktop's concise-response setting, plus widgets vs terminal mind-mapping [07:27] Auditing what each team member actually uses AI for before cutting costs [07:56] Why max-plan tool loading is free but third-party API tool loading isn't [08:26] "OpenClaude" - a terminal alias that loads Kimi without preloading tools [09:24] Sim's example: a warehouse dispatcher now vibe-coding time-tracking apps [09:54] The $20-to-Max "purgatory" middle ground [10:44] Danny's recommendation: Kimi K3 for the team, Claude Desktop kept for flexibility [11:12] Splitting by task: Fable 5 for planning, K3 for the build [11:40] Cascade plans - staging big jobs across sessions to control context [13:04] Real numbers: four parallel video edits, £4-5 down to 35p after removing tool preload [14:07] LM Studio AI and the free-credit-then-continue usage hack [14:43] GLM 5.3 - "Opus 5 good," and it speaks plain English [15:14] Grok/Grokbot - zero-friction agent automation from a phone [16:21] Building a review-flagging SOP from a LinkedIn post in one sitting [16:38] API scraper tip: Apify or Monid for cheap review scraping [19:00] Team breakdown: 5 on Max plans, ~18 on $20 plans [19:22] The frustration of no pooled token allocation across a team [20:12] The "Claude effect" - wait 21 days before reacting to a new release [21:08] Astra vs Fable, and why a full company switch is a bigger decision than it looks [22:04] Reframing: only 3-4 people actually need heavy-lifting models [23:37] Danny's pushback: what is the AI spend actually generating? [23:59] Case study: ~£300 to edit 100 yoga app videos with real footage and AI voiceover in a day [26:13] ROI framing: AI cost against revenue and headcount value [26:45] Team-wide Max plan cost: roughly £30k/year - "just a salary" [27:08] The local GPU reality check - a 90GB model locks the RAM, breaks other flows [28:03] RunPod and HyperStack as pay-by-hour alternatives to token metering [28:34] Wrap-up - Danny off to the airport Key Takeaways Constant model-switching costs more than it saves - retraining a team and rebuilding skills outweighs chasing the newest release; wait it out, then decide. Tool preloading is where the real API cost hides - stripping it out cut one job's cost by roughly 90% with no drop in output. Split the model by the task, not the team - planning on a stronger model, execution on a cheaper one, staged across sessions to control context burn. Audit usage before cutting spend - most token burn traces back to a handful of people doing genuinely heavy work, not the whole team. Cost only means something next to output - a £300 same-day build replacing two weeks of manual work reframes what "expensive" actually means. Notable Quotes "The last thing you want to be doing is getting people affiliated with the software, get them used to it, and then suddenly taking that away." - Sim "Once you took that out of the equation, I've got it down to about 35 pence for the same work." - Danny McMillan "Have you looked at what it's adding?" - Danny McMillan "It's not even remotely comparable." - Sim

Resources Mentioned OpenRouter - model-switching gateway, used here to route to Kimi K3 without preloaded tools Kimi K3 - the cost-efficient model for day-to-day build work GLM 5.3 - Chinese model tried via LM Studio AI, described as "Opus 5 good" LM Studio AI - harness for running Chinese models, including a free-credit usage workaround Grok / Grokbot - low-friction personal AI agent with built-in scheduling Apify / Monid - API scrapers used for cheap-at-scale review data pulls NVIDIA DGX Spark - local hardware for running in-house model flows RunPod / HyperStack - pay-by-hour GPU rental as an alternative to token-based pricing Connect Sim - Amazon seller and co-host

Seller Sessions is the leading podcast for advanced Amazon sellers, hosted by Danny McMillan.

Description: Danny McMillan and Ritu Java on AI-built email triage, pest control and client sentiment analysis for busy Amazon agencies and sellers.

Ritu Java returns after recovering from a serious ankle injury, and dives straight into the theme of the episode: managing cognitive load as AI accelerates faster than we can adjust to it. You'll hear how Danny and Ritu are each solving the same problem from different angles — building systems that manage the noise so the signal gets through.

Ritu walks through two Claude-built systems running on her Google ecosystem: a "pest control" routine that reads her inbox twice daily and files unsolicited pitches before she ever sees them, and a client sentiment analysis system that reads years of email history to flag which client relationships are improving or deteriorating. Danny shares his own zero-inbox protocol — a labelled morning triage that clears by 8:33am UK time — and both agree the real skill now is boundaries, not more automation.

• AI acceleration and cognitive load - why keeping pace with AI now outstrips our own working speed
• Pest control inbox routine - a Claude + Gemini API system that filters unsolicited email using "left brain, right brain" logic
• Reply radar - surfacing the emails that genuinely need a response, out of tens of thousands
• Zero inbox protocol - Danny's labelled, time-boxed morning triage system
• Client sentiment analysis - mining historical email threads to score relationship health
• Cascading plans - reviewing AI-generated plans in stages instead of all at once, to protect decision quality

• [00:00] Ritu returns after an ankle injury, catches up on the last few months
• [01:34] The acceleration of acceleration - falling behind AI's own pace
• [02:29] Danny's all-in-Claude mandate for his team
• [05:36] Cognitive load and the need for "a skill to manage the other skills"
• [06:39] Danny on verification systems, sign-off protocol and decision fatigue
• [07:19] Cascading plans: reviewing complex work in stages, not all at once
• [08:05] Why a shorter, higher-quality working day beats a fixed nine-to-five
• [10:03] Ritu's two access routes into Google: MCP connector vs CLI
• [10:56] Claude routines explained - the "cron job" for your inbox
• [11:55] The pest control system: left brain keyword matching, right brain Gemini analysis
• [16:04] Reply radar - catching the emails that were missed
• [18:07] Danny's zero inbox protocol: labels, triage timing, draft handling
• [20:39] The "sixth follow-up email" rant - boundaries with cold outreach
• [23:13] Why fuzzy logic beats simple Gmail filters
• [24:17] The CLI route: BigQuery access for agency-wide ad and rank data
• [24:59] Client sentiment analysis: reading 500+ emails to score relationship trust
• [27:17] Danny on spotting relationship drift before the client raises it
• [30:12] Wrap-up: signal to noise as the theme of the episode

• AI is accelerating faster than we can adapt - the gap between AI's pace and our own decision-making speed is the new operating reality.
• Fuzzy logic beats static rules - Ritu's pest control system combines keyword detection with AI judgement, catching what a plain Gmail filter would miss.
• A time-boxed triage beats an always-on inbox - Danny's zero inbox protocol proves structure, not more tools, is what protects focus.
• Sentiment analysis surfaces relationship drift early - mining historical email tone gives an objective signal alongside human account management.
• Cascading plans protect decision quality - reviewing AI output in stages, not all at once, avoids the fatigue that degrades judgement.

"We're slower than the AI now in terms of how fast things are moving." - Ritu Java "AI is not an enabler for us to think on our behalf. It's our job to verify it." - Danny McMillan "In order for us to be efficient with our productivity, we need something to manage us." - Ritu Java "Without perspective and perception, empathy can't live." - Danny McMillan

• Claude routines - scheduled, cron-style Claude tasks used to run the pest control and reply radar systems
• Gemini API - powers the "right brain" analysis layer in Ritu's pest control system
• Google Workspace MCP connector - built-in Claude access to Gmail and Drive
• CLASP - CLI tool for Google Apps Script development
• BigQuery CLI - command-line access to agency ad, organic and rank-tracking data

Ritu Java - AI for E-commerce newsletter; speaking at the Amazon booth this month

Seller Sessions is the leading podcast for advanced Amazon sellers, hosted by Danny McMillan. Adam Heist returns next week for the Broadmatch Show.

Week three of the all-things-Claude series brings Shubhash back after some time away. He walks through why sellers should build a RAG (Retrieval Augmented Generation) system: business knowledge trapped in a founder's head and a stack of spreadsheets creates a bottleneck, and RAG breaks it by answering questions from your own files with sources attached, no hallucination, no SQL required.

Danny follows with a practical rundown of the model-switching setup he's spent the last week building: a Claude Code Router (CCR) experiment that didn't work out, and the eventual fix via OpenClaude, OpenRouter and DeepSeek to save on token spend for grunt work without disturbing his main Claude Desktop workflow. He also covers running a second email address on a different domain via the Google Workspace CLI, and gives an honest verdict on OpenMontage for AI-assisted video editing: impressive, but still not a replacement for editing domain experience.

• RAG systems for Amazon sellers - chunking, embedding, indexing, retrieval and answer, built on Supabase/Postgres with pgvector
• Data drift and guardrails - how to stop a RAG system guessing, and how to version-control its answers over time
• Model switching for cost control - why and how, via OpenClaude, OpenRouter and DeepSeek
• Harnesses vs models - why a model performs differently outside its native environment
• OpenMontage - an AI video editing repo, and why domain experience still can't be replaced

• 00:00 - Danny opens week three, hands over to Shubhash
• 00:45 - Shubhash introduces today's topic: RAG (Retrieval Augmented Generation)
• 01:39 - Why sellers should build a RAG: founder-bottlenecked knowledge
• 02:53 - No model training, no GPUs required - "organising a warehouse, not building a robot"
• 03:42 - The five steps: chunk, embed, index, retrieve, answer
• 05:01 - Indexing on Postgres/Supabase, searchable by meaning and by exact keyword
• 06:08 - Retrieval and the router: number questions to tables, everything else answered with sources
• 06:54 - Danny on data drift: the chicken-and-egg problem of trusting Claude to catch its own drift
• 08:18 - Core of it simplified: chunk, guardrails, plain-English queries via Slack or Claude
• 09:15 - Building on the same Supabase project from earlier sessions, switching on pgvector
• 10:12 - Guardrail rule: don't guess, cite sources, flag when there's no answer
• 10:41 - Version control: feeding user feedback back into the system
• 11:27 - Danny's segment: model switching, why and how
• 13:22 - The CCR experiment: a gateway/pass-through that didn't preserve context or dependencies
• 15:14 - Why OpenClaude was the better route: terminal-based, dependencies not preloaded
• 16:44 - DeepSeek vs Fable 5: close, not equal, but roughly 90% cheaper for grunt work
• 17:40 - Harnesses matter as much as the model itself
• 20:38 - Budget-capping your OpenRouter API key (and the horror stories of not doing so)
• 22:52 - Why Danny moved off Claude in Chrome for email rebuilds - context window visibility problems
• 23:37 - Solving it with dual Google Workspace access via CLI (Seller Sessions + DataBrill)
• 25:17 - OpenMontage: plug in the repo, but expect to still do heavy lifting
• 27:36 - The aggregator analogy: why "done for you" video/design without domain experience is a scam
• 30:46 - Round-up: three steps to start a RAG system yourself
• 34:56 - Where to reach Shubhash

• RAG breaks the founder bottleneck - your spreadsheets and documents become queryable with sources attached, cutting out the "ask the founder" loop.
• RAG is simpler than it sounds - five steps (chunk, embed, index, retrieve, answer), no model training, no GPUs, built on Postgres/Supabase you likely already have.
• Guardrails beat guessing - if there's no answer in the data, say so rather than fabricate one.
• Model switching only pays off with the right setup - a terminal-based OpenClaude + OpenRouter + DeepSeek combo saved roughly 90% on grunt-work token spend.
• AI video editing still needs domain experience - OpenMontage is a genuine leap forward, but a done-for-you button-press is the same mistake the Amazon aggregators made.

"The business knowledge lives in the founder's head and a stack of spreadsheets that only they can navigate." - Shubhash

"It's easier or better to say, I don't have enough data to make a conclusion to this, than to guess." - Shubhash

"Harnesses are just as important, to a point, as the model itself." - Danny McMillan

"If you said to a video editor, I'll just press a button and it makes me a video - they'd say that sounds like a scam to me." - Danny McMillan

• Supabase / Postgres + pgvector - the database layer for storing and searching RAG "cards" by meaning and keyword
• OpenRouter - model-switching gateway used to route to DeepSeek; supports API key budget caps
• DeepSeek (v4 Pro) - the model Danny settled on for cost-saving grunt work, roughly 90% cheaper than Fable 5
• OpenClaude - terminal-based alternative to a full CCR gateway, dependencies loaded on demand
• Google Workspace CLI - used to run two email accounts through Claude without a browser context-window problem
• OpenMontage - GitHub repo for AI-assisted video editing, works alongside a Claude video/Remotion flow

Shubhash - Not a Square Email: shubhash [at] notasquare.io

Seller Sessions is the leading podcast for advanced Amazon sellers, hosted by Danny McMillan. Week four returns with Ritu for Go With The Flow.

Danny McMillan returns after his longest break in almost ten years, with Seller Sessions approaching its tenth anniversary and roughly 1,300 episodes. This is the pilot of a new monthly roundtable with Sim and Matt (Dorian returns next month), moving away from the conversion show format towards raw conversation.

You'll hear how Sim's team runs product development end to end with AI: keyword-scored idea validation, brand director sign-off, Claude-generated product concepts rendered through Codex, and a launch pipeline already booked out to 2027. Matt shares how Productpinion prioritises features from customer feedback, and why prioritisation is the most undervalued skill in the AI era.

The back half tackles the big theme: cognitive load. Danny breaks down verification fatigue, context switching and AI maxing, and why the scarce resource is no longer time but attention and decision quality.

• AI-driven product development - from keyword scoring to Claude SVG concepts and Codex-generated product renders
• Team structure at scale - how ideas route through brand directors to sourcing across UK and Philippines teams
• Hiring in the AI era - why refusing to use AI is now a dealbreaker, and why gutting teams for AI is commercial suicide
• Free local AI tools - Fluid Voice (Whisper Flow alternative) and Meetily (Granola alternative)
• Cognitive load and verification fatigue - the hidden tax of moving from doer to overseer

• 00:00 - Danny returns: ten years of Seller Sessions, new pilot format
• 01:50 - Sim's update: ditching ClickUp for a bespoke operating system
• 03:55 - Matt's update: closing the research loop in Productpinion, Florence CRO brain, MCP
• 05:39 - Sim's product pipeline: AI keyword scoring, brand director approval, deep research
• 07:07 - AI product development: Claude concepts, Codex renders, 3-in-1 product mashups
• 09:07 - Packaging designed for the main image, and how far you can push it
• 10:46 - Team workflow: brand directors owning P&L, sourcing handoffs
• 14:21 - Danny on gutting teams for AI: who maintains the machines?
• 15:56 - The hiring line: refuse to use AI, you haven't got a job
• 17:48 - Claude across every department: projects, Claude Code vs Cowork
• 20:10 - Free local tools: Fluid Voice for dictation, Meetily for meeting notes
• 21:57 - Marketplace arbitrage: moving proven products between Amazon marketplaces
• 23:21 - Matt on signal to noise: wasting tokens instead of wasting time
• 24:57 - Time blocking and prioritising features by customer impact
• 26:54 - Danny's segment: cognitive load, oversight duty and verification fatigue
• 31:46 - Asking the right question: the Claude Science deep-dive example
• 36:41 - AI maxing, context switching and high-stakes decision quality
• 42:07 - Claude telling you to go to sleep
• 45:16 - Danny's framework: reject the first plan, decision sprints, deliberate decompression
• 50:47 - Where to reach Sim and Matt

• AI has made product development fun again - unique product concepts generated with Claude and Codex, feeding a pipeline mapped to 2027.
• Augment, don't replace - if someone was worth hiring, AI should multiply their output, not justify cutting them.
• Prioritisation is the undervalued AI skill - just because you can do everything doesn't mean you should.
• Verification fatigue is real - build in decision sprints and deliberate decompression, and reject Claude's first plan on sight.
• The scarce resource is attention, not time - your night schedule and recovery feed the next day's output.

"AI is enabling the boring to get released and the fun stuff to happen." - Sim

"Instead of people wasting time, now they're just wasting tokens." - Matt

"Prompts don't matter, but asking the right question unlocks everything." - Danny McMillan

"AI doesn't just speed you up. It puts you on permanent oversight duty, and the cost of that duty is your attention and your judgment, not time." - Danny McMillan

• Fluid Voice - free, open source local dictation with on-device models; a Whisper Flow alternative
• Meetily - free, open source meeting summariser that runs privately on your machine; a Granola alternative
• Claude / Claude Code - the AI platform used across both Danny's and Sim's teams
• Codex - used alongside Claude to generate product concept images
• Productpinion - Matt's shopper testing platform, now with MCP support and draft polls

Sim - on LinkedIn (genuine reach-outs answered) Matt - on LinkedIn or via productpinion.com

Seller Sessions is the leading podcast for advanced Amazon sellers, hosted by Danny McMillan. Dorian returns next month.

Claude Skills, CLI vs MCP and Token Discipline with Ritu Java | Seller Sessions

Ritu Java and Danny McMillan on building agentic skills, choosing CLI over MCP, plan mode discipline and the short window to ship before token costs reset.

Week 4 of the month, Go With The Flow, and Ritu Java is back from her travels. The world has shipped fast since the last episode: Codex 5.5, Claude 4.7, an Amazon Ads MCP and a fresh round of panic over the rumoured removal of Claude Code from the $20 plan (it was a 2% AB test, not a rollout). Ritu and Danny use the noise to make a sharper point: this is the moment to stop chasing models and start building repeatable systems on the platform you have already chosen.

Ritu walks through the three eras of PPC Ninja's automation stack. Apps Script bulk file generators three years ago, Netlify hosted UI apps last year, and now agentic skills that her team chats with in plain English to produce upload ready Amazon bulk files. The same shift applies to data: BigQuery accessed through the Google Cloud CLI rather than through MCP, because CLI is leaner on tokens and works better when the job is heavy on data rather than tool surface. Danny mirrors the move with his event-ops CLI for WordPress, WooCommerce, Stripe and FooEvents reconciliation, and his four tier ExtractFlow cascade (HTTP, headless, stealth, agentic) that bypasses the limits of any single browser tool.

The second half is a discipline talk. Plan mode every time. Push back on the first plan because Claude over engineers by default. 30% of your time on workflow scaffolding so the other 70% can be real building. The 21 day Claude rule: when a shiny new tool fires the dopamine, wait 21 days before refactoring around it. Left brain tasks (counting, SQL, deterministic logic) belong in scripts. Right brain tasks (judgment, creativity, hypotheses) belong in the model. Mix them inside a single skill. Skills are micro pieces of your workflow, not magic, and Claude can write them for you from an existing SOP.

• The three eras of PPC Ninja automation: Apps Script, Netlify UI apps, agentic skills
• CLI vs MCP: when to choose each and why CLI is more token efficient for data heavy work
• Token economics, the rumoured $20 plan change and why it was a 2% AB test
• The short window before subsidised tokens get repriced
• Plan mode discipline and the "push back on plan one" rule
• Danny's 30 / 70 framework: workflow scaffolding vs building
• The 21 day Claude rule for resisting tool churn
• Left brain vs right brain task design inside a single skill
• The PPC Ninja "5 Whys" skill: deterministic SQL plus non deterministic hypotheses
• Claude.md, Gemini.md, Skills.yaml and the emerging Agents.md standard
• Skills for beginners: let Claude write them from your SOP
• Skill cascading: research, article, LinkedIn post, tweets, slide deck in one chain

• [00:01] Welcome back, Week 4 Go With The Flow, Ritu returns from travels
• [00:17] Codex 5.5, Claude 4.7 and the "no one is writing code anymore" reality
• [02:01] Ritu on the three eras of PPC Ninja automation
• [02:42] Era 1: Apps Script bulk file generators in Google Sheets
• [03:46] Era 2: Netlify hosted UI apps with input fields
• [04:48] Era 3: Agentic skills, the bulk file skill trained on Amazon templates
• [06:22] Cloud talking to BigQuery through the Google Cloud CLI
• [07:00] Danny: what is a CLI and why it matters for token use
• [08:00] Amazon Advertising MCP vs CLI based access to the same data
• [09:33] WordPress horrible to drive via MCP, easy via CLI
• [10:00] Danny's event-ops CLI: tickets, food tickets, WooCommerce, Stripe reconciliation
• [12:13] ExtractFlow four tier cascade: soft, medium, stealth, agentic
• [13:46] Why CLI for the heavy stuff, MCP for the soft touch
• [14:13] AWS CLI: chat to Claude, push HTML blog posts live in two minutes
• [15:33] The overwhelm problem and the 5,000costbehindthe5,000costbehindthe100 plan
• [17:35] The $20 plan rumour: it was a 2% AB test, not a rollout
• [19:38] Build repeatables, not one offs
• [20:38] Danny: pick a platform and stop chasing benchmarks
• [21:16] The 21 day Claude rule for new tools
• [22:16] Plan mode every time, push back on plan one, get the second plan
• [23:02] Why am I building it, who is it for, what am I building
• [23:30] The 30 / 70 split: workflow scaffolding vs real building
• [25:13] Why long six to fourteen hour Claude runs are usually inefficiency
• [27:12] Compounding 1% a day across a year
• [27:47] "I build the things that build things"
• [28:00] Architecture vs apps: filling the gaps between A and B
• [29:06] Left brain vs right brain task design
• [30:01] Why throwing 80/20 at a sales drop diagnosis fails
• [31:33] The PPC Ninja 5 Whys skill: deterministic plus non deterministic in one flow
• [34:32] Claude.md, Gemini.md, skills.yaml and the agents.md standard
• [40:53] Beginners: let Claude write the skill from your SOP, use the interview pattern
• [42:39] Skill cascading: URL to research to article to LinkedIn post to tweets to slides
• [44:42] Mixing deterministic and non deterministic inside a single skill
• [45:39] Wrap up, signal to noise, who is it for

1. Pick a platform and stop chasing models. A new model ships every week. Time spent benchmarking is time not building. Double down on Claude (or whichever you chose), use the 21 day rule, and let the ecosystem catch up to the shiny thing in your feed.
2. CLI for heavy work, MCP for soft touch. MCP loads tools and skills into context and burns tokens. CLI uses programs already on your machine. For data heavy jobs (BigQuery, AWS, WordPress at scale), CLI wins. For light cross app workflows, MCP is fine.
3. Build repeatables, not one offs. Subsidised tokens will not last. The 100planreportedlycostsAnthropic100planreportedlycostsAnthropic5,000 to serve. Spend the window building scaffolding that compounds, not 14 hour vibe coding runs.
4. Plan mode every time, then push back. Claude over engineers by default. Generate the plan, then say "you have over engineered this, although I want it elegant, go back and review." Plan two is the one you start from.
5. 30% on workflow, 70% on building. Each new dependency, MCP, skill or repo you add to your workflow compounds across every future project. Stop building only the apps. Build the things that build the apps.
6. Left brain in scripts, right brain in the model. Counting, SQL, deterministic logic belongs in Python the moment you can offload it. Save the model for hypotheses, judgment and creativity. The PPC Ninja 5 Whys skill mixes both inside one flow.
7. Skills are micro pieces, not magic. Take an SOP, ask Claude to interview you with decision panels, and let it write the skill. Then cascade skills together: URL to research to long form article to LinkedIn post to tweets to slide deck.

"Instead of doing one offs, it is time to build repeatables. The more people can learn that skill now, the better it will be, because a year from now you may not have access to the same tokens." Ritu Java

"If you see something and it looks sexy and it has sex and sizzle and your dopamine is screaming to go after it, wait 21 days. Either Claude will have it, or someone will have a repo, and you can combine it." Danny McMillan

"Always use plan mode. Never accept plan number one. Tell Claude: you have over engineered this, although I want it elegant, go back and review. Then start from plan two." Danny McMillan

"I build the things that build things. I build the scaffolding the team needs so they can build on top of it." Danny McMillan

"Spend 30% of your time on your workflow and 70% building. The 30% compounds across every project." Danny McMillan

"If we just hand six months of ad, organic, ranking and SQP data to Claude with no structure, it is going to mess up. It will give you an 80/20 you are not satisfied with, because it is not equipped to handle that volume without scaffolding." Ritu Java

"WordPress is horrible to work with through MCP. It falls over all the time. CLI can be amazing for certain things." Danny McMillan

• PPC Ninja : Ritu's Amazon PPC software and agency, base for the BigQuery + CLI stack discussed
• Claude Code : Anthropic's CLI for Claude, the primary surface used in the episode
• Anthropic Claude : Claude 4.7 referenced as the current model
• OpenAI Codex : Codex 5.5 mentioned as the rival shipping fast
• Google Gemini CLI : Referenced as a sibling agent surface (Gemini.md)
• Google BigQuery : PPC Ninja's central data warehouse
• Google Cloud CLI (gcloud) : The CLI Claude uses to talk to BigQuery
• Amazon Advertising MCP : Amazon's official MCP server for ads data, referenced as the MCP comparison point
• AWS CLI : Used by Ritu to publish HTML blog posts to ppcninja.com from a Claude chat
• Netlify : Hosting layer for PPC Ninja's previous era of UI based apps
• WordPress and WooCommerce : Backbone of Danny's event-ops CLI
• FooEvents : Ticketing plugin that lives behind WooCommerce in the event-ops flow
• Stripe : Source of the card fee variation Danny reconciles via CLI
• ExtractFlow / CloudExtract : Danny's four tier extraction cascade (HTTP, headless, stealth, agentic). Open repo
• Playwright : The default browser automation tier inside ExtractFlow
• Agents.md : Emerging AI agnostic instruction file standard alongside Claude.md and Gemini.md
• Sequential Thinking MCP : The MCP Danny invokes when asking Claude to step through analysis

Danny McMillan : Host of Seller Sessions, founder of DataBrill, building AI native tooling and CLI based workflows for Amazon sellers.

• Website: https://sellersessions.com
• LinkedIn: https://www.linkedin.com/in/dannymcmillan

Ritu Java : CEO and co founder of PPC Ninja, Amazon PPC software and agency. Specialises in automation, BigQuery pipelines and agentic workflow design.

• LinkedIn: https://ca.linkedin.com/in/ritujava
• Website: https://www.ppcninja.com

• Next week: Ritu and Danny pick up routines and the new Claude scheduler.
• In 8 days: Seller Sessions Live 2026 in London on 9 May. Last week to lock in any final discounts.

Seller Sessions is the leading podcast for serious Amazon sellers, hosted by Danny McMillan since 2017. Go With The Flow is the weekly automation strand where Danny and Ritu Java work through agentic flows, MCPs, CLIs and skills, in real time, on the same stack their teams ship every week.

Episode published: 1 May 2026 Series: Go With The Flow (Week 4 of the month) Keywords: claude skills, claude code, cli vs mcp, mcp model context protocol, claude 4.7, codex 5.5, amazon ppc automation, bigquery cli, agentic workflows, plan mode, token optimisation, claude.md, agents.md, ppc ninja, ritu java, seller sessions podcast, go with the flow

Amazon Dashboard Brain, Remotion Video & ElevenLabs Voice Cloning | Claude Sessions

Shubhash Sharma on building a data brain behind your Amazon dashboard. Danny McMillan on Remotion video and ElevenLabs voice cloning realities.

Week 3 of the month means Claude Sessions, and Danny McMillan and Shubhash Sharma are back with a double feature for Amazon and TikTok Shop sellers building their own AI tooling. Shubhash picks up from last episode's SP API and Ads API walkthrough with a hard lesson learned the wrong way: a polished dashboard wired straight into Amazon is a window with no room behind it. The numbers will lie, and you will not know when a feed silently dies.

He walks through the fix: a "brain" sitting between the data sources and the dashboard. Supabase as the long term store, pgvector for unstructured stuff like contracts and reviews, n8n as the orchestration layer. Six core domains every seller shares (orders, products, analytics, ads, finance, affiliates and creators) plus an optional documents layer. He closes with a dual write migration pattern so you can flip between old and new without taking the business offline.

Then Danny turns to video and voice. Remotion looks like toy town out of the box, but with the right plugins (motion blur, transitions, captions, shapes, fonts, rendering) and Claude doing the orchestration, it becomes a serious production tool that can pull in your footage, branding and design system. On the voice side, he has tested VoiceBox and F5TTS and come back to ElevenLabs Multilingual v2 at £22 a month. The missing gap everywhere is cadence. He also names the deeper bet: as the market floods with AI generated content, authentic voice becomes the differentiator that cannot be cloned.

• Why dashboards lie when wired straight into Amazon, TikTok and Shopify
• The "brain" pattern: Supabase, pgvector and n8n as a centralised data layer
• The six core data domains every seller needs (plus a 7th for documents)
• Dual write migration so the old system and brain run in parallel
• Remotion as a code based video tool, and what it needs to stop looking toy town
• The four layer creative workflow: brief, story skeleton, treatment, scene by scene
• ElevenLabs vs VoiceBox vs F5TTS for voice cloning your own voice
• Why cadence is the last hard problem in synthetic voice
• The authenticity premium in an AI flooded market

• [00:00] Intro and welcome back to Claude Sessions
• [00:34] Shubhash kicks off: where to put the data you pulled last week
• [01:04] "Your dashboard is lying to you" and the polished dashboard pitfall
• [02:32] Dashboard is a window. The brain is the room behind it
• [04:54] Tech stack: Supabase (Postgres), pgvector, n8n
• [05:54] The six fundamental data domains
• [06:26] Orders, products, analytics, ads, finance, affiliates and creators
• [08:30] The optional 7th layer: unstructured documents via pgvector
• [09:44] Dual write pattern for safe migration
• [10:48] Three takeaways: audit, list domains, build one table at a time
• [12:28] Danny on Remotion: code based video and why it is toy town out of the box
• [13:51] What is missing: motion blur, transitions, captions, shapes, beat detection
• [14:54] The 80+ plugin packages that turn it into a real tool
• [16:56] Pulling in footage, logos, design systems and free music from Pixabay
• [18:30] The 4 layer creative workflow: brief, story skeleton, treatment, scenes
• [21:15] Voiceovers: ElevenLabs Pro setup and why the £22 is worth it
• [22:12] VoiceBox and F5TTS field test: garbage and 5 rounds of tuning later
• [23:22] Why cadence is the hardest thing for AI voice to fake
• [25:42] How much reference audio you actually need (30 min min, 2 hours ideal)
• [27:25] ElevenLabs UI parameters: speed, stability, similarity, exaggeration
• [28:52] The authenticity premium when the market floods with AI
• [30:30] Key takeaways, ElevenLabs API usage and locking in your voice once
• [34:24] Aside: "insane" and "most" as the new AI tells
• [36:31] SSL 2026 wrap, 18 days out, Ritu returns next week with Japan

1. Build a brain, not just a window. A dashboard wired straight to Amazon, TikTok or Shopify has no memory. When a feed silently fails, the dashboard happily lies. Sit a Supabase + pgvector + n8n layer in between, and your dashboard becomes a view on top of a real source of truth.
2. Six domains cover almost every seller. Orders, products, analytics, ads, finance, and affiliates / creators. Map every place each one currently lives, then consolidate one domain at a time. Start with one table (orders) and let Claude do the heavy lifting.
3. Use dual write when migrating. Write to the old store and the new brain in parallel for a week. Compare. Flip the dashboard's read side via a feature flag. If something breaks, flip back. Zero downtime, zero fear.
4. Remotion is a system, not a tool. Out of the box it is bare. Add the plugins (motion blur, transitions, captions, fonts, rendering), bring your own footage and design system, and let Claude orchestrate the four layer workflow: brief, story skeleton, treatment, scene by scene.
5. ElevenLabs Multilingual v2 still wins for voice cloning. VoiceBox and F5TTS were not close. Pay the £22, use Model 2, feed it 30 minutes minimum (2 hours ideal) of clean reference audio, and lock the setup in once.
6. Cadence is the last mile. AI can match tone and timbre. It still cannot match the rises, falls and micro pauses that make a sentence sound like you. Use scripts split into short paragraphs, generate three variants, and tune the language you use to talk to Claude until the cadence lands.
7. Authenticity becomes the moat. As written, visual and audio AI floods every channel, the brand voice that is unmistakably human becomes the differentiator. Do not give that away to save 22 dollars a month on a podcast.

"Dashboard is a window. We need a room behind the window. So the brain is going to be the room behind this window." Shubhash Sharma

"If any of our SaaS went offline tomorrow, will our business still have its memory? The answer is no, because we haven't stored it. All we have is rented attention." Shubhash Sharma

"When you migrate to your brain, don't rip out your old system. Use dual write. Run them in parallel for a week. If something breaks, flip it back. Zero downtime, zero fear." Shubhash Sharma

"Remotion out of the box isn't great. It's almost like building some slides, just one step up. You have to build it as a system of what you need." Danny McMillan

"The hardest part for AI to represent is cadence. It can get the tone of your voice. That's the easy bit. But the speed and the up and down of how you talk, that's where these models still fail." Danny McMillan

"In our rush to use AI, you've got to remember the market floods with it. When everything sounds like AI, the only thing left is the authentic voice for your brand." Danny McMillan

• Supabase : Postgres backend used as the long term data store for the seller "brain"
• pgvector : Postgres extension for semantic search over unstructured data (contracts, reviews, supplier emails)
• n8n : Orchestration layer for scheduled pulls and cron jobs with a UI
• Amazon Selling Partner API (SP API) : Source for orders, inventory and finance data (covered in last episode)
• Amazon Ads API : Source for ad spend, campaign and keyword data
• Remotion : Code based, React powered video creation framework
• ElevenLabs : Voice cloning and text to speech. Model used: Multilingual v2 (Pro plan, £22 / month)
• F5 TTS : Open source text to speech model tested for voice cloning
• VoiceBox by Jamie Pine : GitHub voice cloning desktop app tested by Danny
• Pixabay : Free music and sound effects used inside the Remotion workflow
• Loom : Source of clean voice reference audio if you record team walkthroughs
• Seller Sessions Live 2026 : Conference 9 May 2026, 18 days out at recording

Danny McMillan : Host of Seller Sessions and Claude Sessions, founder of DataBrill, building AI native tooling for Amazon sellers.

• Website: https://sellersessions.com
• LinkedIn: https://www.linkedin.com/in/dannymcmillan

Shubhash Sharma : Engineer building data infrastructure for Amazon and TikTok Shop sellers. Returning Claude Sessions co host.

• Next week: Ritu returns from Japan with three subjects covered in this month's rotation.
• In 18 days: Seller Sessions Live 2026 in London on 9 May. Modular format, new venue confirmed.

Seller Sessions is the leading podcast for serious Amazon sellers, hosted by Danny McMillan since 2017. Claude Sessions is the AI focused monthly strand where Danny and rotating co hosts work through the practical wins, false starts and engineering reality of building with Claude, MCPs and the wider AI stack inside real seller businesses.

In this Conversion Monthly, Danny McMillan is joined by Dorian and Matt Kostan (no Sim this episode — he's on holiday) for a live, practical session on building brand-quality design systems fast and for free.

Dorian opens with a tight crash course in the three design fundamentals that separate professional Amazon listings from amateur ones: font pairing, grid and layout, and colour theory. He then demos Google Stitch live, building a full design system from a wooden utensil listing in real time. Danny shows a more automated route — using Perplexity to control Stitch autonomously and generate a complete brand kit from just a product title, bullet points, and a reference image. Matt rounds it off with a live Product Pinion split test of the new designs against the original listing — and the results deliver the session's sharpest lesson.

The big takeaway: pretty is not enough. Information + design working together is what converts.

• Google Stitch for brand design — Free AI design tool that generates full brand guidelines, font pairings, and mockups from reference images and prompts
• 3 design fundamentals every seller should know — Font pairing, grid and layout, colour theory with a contrasting action colour
• Perplexity + Stitch autonomous workflow — Danny demos letting Perplexity control Stitch end-to-end with zero manual input to generate a full brand kit
• Coolers.co — Free colour palette tool with a visualiser and AI colour bot (Matt)
• UX and design laws applied to Amazon — Miller's Law, Fitts' Law, Jacob's Law, Occam's Razor translated into listing and brand site decisions
• Product Pinion live split test — New designed variants vs the original listing, with real shopper results in under 10 minutes
• Live test result — The original information-heavy image outperformed the prettier redesigns early on; lesson: strip information at your peril

• [00:00] Intro — Danny opens, Sim is out, format overview
• [00:48] Dorian: Why most Amazon listings lack design consistency
• [02:00] The 3 design principles: font pairing, grid/layout, colour theory
• [04:30] Font pairing explained — serif vs sans-serif, how world-class brands use them
• [07:00] Colour theory — complementary colours plus one contrasting action colour
• [08:30] Live Google Stitch demo — wooden utensil set, design system generated from brand brief + images
• [10:00] Stitch output: colour palette, font pairings, layout mockups
• [12:17] Matt: brand guidelines used to cost $1,000+ — now free in Stitch
• [13:00] Dorian: live Figma iteration — cleaning up the infographic using new design system fonts
• [17:00] Matt: information hierarchy lesson — measurements vs benefits on infographics
• [19:30] Dorian: "mouse text" and anchoring — what to leave in, what to strip out
• [20:33] Matt: Coolers.co overview — free colour palette generator and visualiser
• [22:00] Matt: UX/UI design principles applied to Product Pinion and Amazon listings
• [25:12] Danny: Perplexity + Stitch autonomous brand kit demo — Z Kitchen brand from scratch
• [27:00] Z Kitchen outputs: design system, A+ content, infographic, lifestyle mockups, packaging concepts
• [31:00] How to iterate inside Stitch — refine vs reimagine, varying only specific elements, up to 5 variants
• [36:00] Danny: UX design laws — Miller's Law, Fitts' Law, Jacob's Law, Occam's Razor
• [40:00] Danny: Typography slides — spacing systems, layout balance, font families
• [43:32] Dorian: reveals three redesigned variants ready for split test
• [44:35] Matt: launches live Product Pinion test — 50 shoppers, cooking category targeting
• [47:33] Live results coming in — original listing leading over new designs
• [48:00] Dorian: "pretty is one thing but the information has to be there"
• [49:00] Danny: design and information are two separate layers — both are required
• [51:30] Product Pinion API + Claude integration teaser
• [52:36] Final results and wrap-up — test completed in ~10 minutes with 50 real shoppers
• [53:44] Closing thoughts and Seller Sessions Live preview (26 days out)

1. Three principles separate professional listings from amateur ones — font pairing (serif + sans-serif), grid and layout (hierarchy: 1, 2, 3), and colour (complementary base + one contrasting action colour).
2. Google Stitch is the best free tool right now for design mockups — unlike image generators (Gemini, GPT), Stitch understands design principles and generates layout-aware mockups you can iterate on.
3. Pretty does not convert on its own — the live test showed the original, information-heavy image outperforming the cleaner redesigns early. Design is a layer on top of strong product information, not a replacement for it.
4. Perplexity can run Stitch autonomously — paste a product title, bullet points, and a reference image; let it loop through Stitch without touching anything; come back to a full brand kit.
5. You can test design variations with 50 real shoppers in under 10 minutes — Product Pinion lets you run image split tests with category-targeted shoppers, get qualitative feedback, and iterate the same day.
6. Nano Banana outputs in Stitch cannot be regenerated — switch to one of the standard models if you need variation or refinement controls.
7. AI gets you to the concept stage fast — use Stitch to generate the direction, then hand to a designer for finishing. Revision cycles and meetings shrink dramatically.

"If everything is important, nothing really is." — Dorian

"The hardest thing is to make something simple, elegant, and something that people get instantly." — Dorian

"Pretty is one thing, but the information has to be there. I didn't put the information there — and it's not doing well." — Dorian (on live split test results)

"Most people don't necessarily know good design, but they know what they like. It's more of a feel — they go, that looks a bit cheap, or that looks really good." — Danny McMillan

"It's never been easier and faster to become a world-class brand on design. Plug in your details, get a design guide going, and you can really up your brand in a very short period of time." — Matt Kostan

"The breakout brands from the Amazon community — we haven't had enough of them crossing over. Now that gap's closed." — Danny McMillan

• Google Stitch — Free AI design tool; generates brand guidelines, font pairings, mockups, A+ content concepts, and layout variations. Up to 3,000 generations per day (free)
• Figma — Design tool used by Dorian to pull Stitch outputs and refine layouts manually
• Adobe Color (color.adobe.com) — Colour palette exploration and complementary colour tool; used in the live demo for the wood/blue beach-forest palette
• Coolers.co — Free colour palette generator with AI colour bot and real-world visualiser
• Pinterest — Recommended for browsing font pairing inspiration
• Nano Banana 2 — Image generation model available inside Stitch; note: regeneration/variation controls don't work on Nano Banana outputs
• Perplexity — Used to autonomously control Google Stitch via browser automation, building a full brand kit end-to-end from a single prompt
• Product Pinion — Consumer research and split testing tool by Matt Kostan; image tests with real shoppers, category targeting, results in minutes. Product Pinion API + Claude integration in development.

Dorian — Design and conversion specialist, Seller Sessions Conversion Monthly co-host

Matt Kostan — Founder of Product Pinion, consumer research and split testing for Amazon sellers

In this Broad Match Show, Danny McMillan and Adam Heist cover two of the most practical AI frontiers for Amazon sellers right now: getting direct API access to your Seller Central data and building a fully automated design workflow from inspiration through to live assets.

Adam breaks down how he connected Amazon's SP API and Ads API to an AWS database and wired Claude Code directly to it — giving him real-time, queryable access to years of business data across any metric. No developer required. Danny walks through his 8-step system that takes a seller from a TikTok scroll to a finished, conversion-tested design with brand consistency baked in.

Both share hard-won lessons on where AI gets you (the 70–85% mark) and where the human still needs to step in — plus a candid look at what's changing at Seller Sessions Live on May 9th.

• Amazon API data pipeline — SP API + Ads API → AWS database → Claude Code for real-time analysis
• 8-step AI design workflow — Inspiration capture, memory/photo brain, brand system, mood board, asset generation, build, and quality gate
• CLI vs MCP — Why CLIs are becoming the cleaner integration path for tools like Google Workspace
• Seller Sessions Live (May 9th) — New modular format, no sponsors, £5,000 fine system for service providers pitching
• Health check-in — Adam on fitness goals; Danny on resolving a high ferritin (iron overload) diagnosis

• [00:00] Welcome and introductions
• [01:10] Adam: Getting Amazon SP API and Ads API access as an individual brand
• [05:00] Storing API data in AWS and connecting it to Claude Code
• [07:30] Building custom dashboards and software from your own data
• [09:00] How to approach it if you're not technical — think first, screenshot issues, let Claude walk you through
• [12:25] Danny: 8-step AI design workflow overview
• [13:30] Step 1 — Inspiration capture from TikTok, YouTube, social reels
• [14:20] Steps 2–3 — Memory/photo brain + design system (52 world-leading brands baked in)
• [15:30] Steps 4–5 — TLDraw mood board + asset generation (Nano Banana 2, Gemini, Remotion)
• [17:50] Steps 6–7 — Build stage (React, Tailwind, ShadCN, Netlify deploy)
• [18:30] Step 8 — Quality gate (216-feature scoring: UX heuristics, typography, psychology)
• [19:30] Google Stitch + Perplexity demo: full brand system from a product title + screenshot
• [23:12] Adam: the 70–85% rule and how to think about AI-assisted design cycles
• [27:35] Danny: Google Workspace CLI for email — running launches under 3,000 contacts
• [29:26] Health updates — Adam on fitness; Danny on ferritin/iron overload and phlebotomy sessions
• [35:45] Seller Sessions Live May 9th — format, venue (inside a church), evening networking
• [41:49] The £5,000 fine system for service providers pitching at the event
• [43:01] Wrap-up

1. You can get Amazon API access as an individual brand — no developer credentials needed. SP API goes back 720 days; Ads API covers 60 days. Approval takes 1–2 days.
2. AWS as a data warehouse for Amazon data — pipe the API into AWS, connect Claude Code to it, and query anything: anomalies, stock-outs, week-on-week comparisons, year-over-year trends.
3. The non-technical workflow is: think → verbalize → screenshot issues → let Claude solve — you don't need to understand the infrastructure, just be clear on what you want to achieve.
4. AI gets you to 70–85% fast — bring in your designer or team at stage 4, not stage 0. Cycle times drop from 6 weeks to 1 week.
5. CLIs beat MCPs for tool integrations where available — less token overhead, fewer config issues, more cohesive experience in Claude Code.
6. Google Workspace CLI can replace Mailchimp/Klaviyo for small lists — Gmail allows up to 3,000 sends per day; viable for product brand launches under that threshold.
7. Seller Sessions Live is now sponsor-free and profitable on ticket revenue alone — the event model is shifting away from conference-style sponsorship dependency.

"Getting the actual real-time API data access has been just another level completely." — Adam Heist

"The original thought is: I need to get API access and I need to connect that to Claude. That's my thinking. And then you literally just verbalize that and use screenshots as you get stuck." — Adam Heist

"AI gets you to the finish line faster across way more dimensions, so instead of doing 600 things in a year, you're doing 2,000." — Adam Heist

"We live in a time whereby execution in a way is taken care of by AI. Where we're needed is on the vision — do we build this or don't we build it?" — Danny McMillan

"Know with AI it's dumb unless you give it a brain." — Danny McMillan

• Amazon SP API — Business reports, inventory, listings, SQP data; up to 720 days historical
• Amazon Ads API — Ad performance data; 60-day lookback
• AWS (Amazon Web Services) — Cloud database for storing API data; connects to Claude Code via MCP or CLI
• Claude Code — AI coding assistant used to build the data pipeline and dashboards
• Google Stitch — Free UI design tool; used to generate brand systems from a product image + title
• Perplexity — Combined with Stitch to generate full design systems from Amazon listings
• Nano Banana 2 — Image generation tool controlled via Claude; used in Danny's asset generation step
• Gemini — Used with reference images for asset generation
• Remotion — Video generation component in Danny's design workflow
• TLDraw — Collaborative whiteboard/mood board tool; integrated with Claude for live-updating design boards
• React / Tailwind / ShadCN — Front-end stack used in the build step of Danny's workflow
• Netlify — Deployment target for the build step
• 21st Century Dev / ShadCN MCPs — Component library MCPs used in the build stage
• Google Workspace CLI — Cleaner alternative to Gmail MCP for read+write workflows in Claude Code
• Playwright / Fetch MCP — Browser automation tools; Danny built a 4-stage cascade scraper for Amazon

The Broad Match Show is a monthly format on Seller Sessions, hosted by Danny McMillan and Adam Heist. It covers the cutting edge of AI tools, Amazon strategy, and brand building — first Tuesday of every month.

Seller Sessions is one of the longest-running Amazon seller podcasts, hosted by Danny McMillan. Known for deep-dives into conversion, data, and the practical application of AI for e-commerce brands.