Phil Rivers is using AI to scale his agency by automating approvals, task creation, onboarding, and shared workflows across his team.Drew and Rory spend an embarrassing amount of time obsessing over AI visuals. Phil Rivers shows up with 40 clients, 16 employees, and an entirely different obsession: automating all the boring stuff nobody wants to do.And it turns out the boring stuff might be where the biggest opportunities are hiding.Phil has rebuilt his agency around an AI-powered operating system that handles client approvals, project management, task creation, onboarding, and internal knowledge sharing.His goal? Double the number of clients his existing team can handle without hiring another employee.And he's already built much of the infrastructure to pursue it.Phil Rivers breaks down an AI-powered agency operating system built with Claude Code, Model Context Protocol (MCP), Supabase, GitHub, Slack, Asana, and Figma. Automated client approvals create campaign tasks and deadlines. A Slack agent named Tim drafts Asana tasks with dependencies. Klaviyo data, onboarding automation, permissions, and shared knowledge help teams handle more clients.#AIAutomation #ClaudeCode #AgencyOperations #FastHours

---

⏱️ Fast Hour

00:00 Who is Phil Rivers?

08:16 Why rebuild an agency with AI?

11:15 How an email agency first used Midjourney

14:24 How do you adopt AI without slowing down?

24:35 How to build an agency on AI from day one

27:03 How can Asana automate campaign planning?

34:36 Why service keeps clients longer than results

37:30 How do you build client context into AI?

43:20 Who decides what the AI remembers

47:38 How AI unblocks account leads to just serve

49:52 How can teams share AI skills?

54:11 How does one MCP support an entire team?

58:17 Why one-off tasks break agency teams

1:00:13 Meet Tim, the Slack agent that writes tasks

1:05:41 How many clients can AI add with zero new hires

1:09:19 Can AI shorten employee onboarding?

1:14:27 Which AI projects aren't worth building?

1:18:20 How do you keep AI workflows current?

1:19:13 How to prove AI ROI to your boss

1:24:50 How do you secure shared AI infrastructure?

1:30:11 What can Obello automate for brands?

1:34:42 How many clients can the team handle?

1:35:42 How does AI automate client onboarding?

1:38:33 What's Phil's biggest AI operations lesson?

1:41:24 Who should viewers tell about Fast Hours?

Claude Opus feels like Midjourney because it can take minimal direction and produce imaginative visual work.Drew Brucker and Rory Flynn gave Claude Opus room to create, then watched the to-do list get ambitious (their neglected websites finally got some attention). A promo’s visual style carries into animated podcast clips, while a handwriting experiment reshapes Drew’s site.Claude Opus powers motion graphics, podcast clipping, and website builds from creative references. Midjourney supplies the creative comparison and visual references for animation. Riverside Model Context Protocol connects recordings and transcripts. ChatGPT image generation builds animation assets. Magnific and ElevenLabs support sound effects and narration.#ClaudeOpus #Midjourney #MotionDesign #FastHours---⏱️ Fast Hour00:00 What's coming in Fast Hours 85?04:20 Why does context improve creative quality?05:35 Why does Claude Opus 5.5 feel like Midjourney?06:07 One design system, a creative domino effect09:07 We built a custom AI clipping workflow10:01 A blind grader judging clip hooks?13:35 Why does Riverside MCP matter for clipping?14:26 How do reference clips train an AI editor?16:37 How do you build clips around out-of-order hooks?19:32 Podcast clips get branded motion graphics23:52 Motion designers losing their sh*t over AI democratization29:58 How precise are code-based motion graphics edits?32:14 Domain expertise raises the ceiling for AI motion design39:17 Drew let his daughters' handwriting shape his brand website44:52 How do you prompt a cohesive website redesign?49:56 Fast Hours builds a website from its creative DNA52:05 Can transcripts power a searchable website?58:28 Music-reactive web design with a face1:00:20 Code-based animation gets a story to tell1:04:00 How does one image become an animation asset library?1:05:48 How do AI tools add animation and narration?1:11:24 How does ElevenLabs find a voice from a description?1:16:15 How real does a Tavus conversation feel?1:21:41 What will Phil Rivers teach about AI operations?

Opus 5.5 made editable AI video practical: build motion graphics in code, then revise shots, text, and variations without starting over.A cocktail graphic from Rory’s T-shirt became an animation system. Then came four more drinks, a Pokémon battle, podcast promos, and a client-style video. Drew and Rory sound like two people who’ve spent years hearing “one tiny change” and knowing exactly how much work that used to mean.Claude Opus 5.5 turns one cocktail image into a JavaScript or HTML animation system and produces four more recipe videos. Three.js lets Rory block a Pokémon battle and change camera angles for complex scenes. Riverside supplies context for Fast Hours promos. Drew tests a client-style video using a website and company context file.#Opus55 #AIVideo #MotionGraphics #claudeai ---⏱️ Fast Hour00:00 What are Drew and Rory making this week?07:31 Why is AI adding work for project managers?9:29 Why most companies are stuck at basic AI17:36 What is production debt, and why AI took off20:45 Is the $200 AI plan a different product?21:19 What changed with Claude Opus 5.525:04 How one T-shirt image became a motion graphic26:28 Why code-rendered video is infinitely editable28:19 How to turn one render into an animation pipeline31:25 Can Opus 5.5 render a 3D Pokémon battle?36:58 How can Three.js block a complex shot?41:36 How did AI make a Fast Hours promo?42:28 Do you need brand guidelines for this?45:41 Can AI pick a stronger clip hook?47:34 Cutting a promo with no instructions49:18 Why creatives aren't siloed anymore50:39 Watching a sponsor promo render live53:38 What one Opus 5.5 prompt gets you for a B2B SaaS video56:09 The exact prompt behind the one-shot video57:21 Claude Code vs Cowork for motion builds59:17 How do editing and motion graphics combine?1:03:05 How did Drew turn his kids' handwriting into a font?1:10:33 Stop sending AI output without the context1:14:17 How to share a skill that runs anywhere1:18:40 Why trading transcripts beats trading drafts1:20:40 Can you share a Claude project?1:24:18 How to get email discounts, then unsubscribe1:27:44 Where does the episode close?

After 20 years in creative, building Golden Wolf and selling it to Doodles, Ingi Erlingsson went deep on AI to start a new chapter at his company, SYSTMS.Ingi has spent two decades making work for brands including Nike, Adidas, Jordan, Disney, Netflix, Coca-Cola, and Cartoon Network. He built Golden Wolf from the ground up, sold the studio to Doodles, became Doodles’ Chief Content Officer, and now builds custom AI creative systems at SYSTMS.So naturally, Drew and Rory spend half the episode staring at his ComfyUI graphs wondering what the hell is happening.Ingi breaks down how he actually works with AI: custom ComfyUI nodes, LoRAs, agents, model fine-tuning, Wan 2.2, Krea 2, GPT 2.5, After Effects, transition models, and the reusable systems behind his visual work. The conversation also gets into creative control, originality, attention, open source, prompt hunting, and why experienced creatives may have an advantage as AI gets more capable.More importantly, Ingi explains why the goal matters more than the prompt, why rapid iteration changes the creative process, and why giving AI more capability does not automatically mean giving it more creative decisions.#GenerativeAI #ComfyUI #AICreative #creativedirector ---⏱️ Fast Hour00:00 Who is Ingi Erlingsson?02:58 How much creative freedom do top brands give?05:56 How do studios get hired for their style?10:59 What did Doodles teach Ingi about brand work?13:05 How do you turn attention into recognition?18:13 How does Ingi build his signature AI style?26:13 Why does AI make experimentation cheaper?29:01 How do AI and After Effects work together?30:20 Why did Ingi move into ComfyUI?31:42 What hardware does Ingi use for ComfyUI?34:34 What does ComfyUI let you control?38:33 How does Ingi create tracked AI graphics?42:05 How do you build custom ComfyUI nodes?47:11 How does Ingi combine fine-tuned AI models?51:09 How should you train a style LoRA?55:13 What should a video LoRA learn?58:50 How much creative control should you keep?1:01:04 Do AI videos need longer generations?1:07:28 How can open-source AI sustain itself?1:11:31 What did Doodles and Web3 teach him about AI?1:15:01 How does viral content connect to X payouts?1:17:42 AI critics keep moving the goalposts1:19:12 How do bots expose themselves in replies?1:21:48 How does AI search surface a local business?1:24:04 Why do comment-for-workflow posts spread?1:25:42 What should young creatives learn now?1:28:23 What should AI creatives get good at?1:32:15 Do creatives still need to collect prompts?1:32:54 How did Ingi end up working on DuckTales?1:36:12 Who gets the Fast Hours sign-off?---🔗 Links Ingi's X: https://x.com/ingi_erlingssonIngi's Instagram: https://www.instagram.com/ingi.ai/Ingi's company (SYSTMS): https://www.systms.ai/

So, what can OpenAI’s Astra and GPT Image 2.5 actually do?

Drew Brucker and Rory Flynn put OpenAI’s Astra and GPT Image 2.5 models through a golf course build, a vintage typewriter animation, and a round of image edits. Rory’s golf course experiment burns 70% of his weekly allowance. Drew spends three hours getting a typewriter to type. Their gift for turning a quick test into a side project remains undefeated.

The pro-AI half of the show. The other half: a viral AI resignation that looks planned to the minute, Anthropic's 154-page report on how people misused Claude, and GPT Image 2.5 quietly fixing the reasons everyone kept running back to Nano Banana.

This episode covers OpenAI Astra with computer use, two ChatGPT chats collaborating inside one project, Three.js and Blender renders, a fantasy football analytics hub, and Astra running Midjourney with mood boards and style references. GPT Image 2.5 multi-edit comments, sketch input, custom aspect ratios, and template creator. Anthropic's threat report, Moonshot and Kimi distillation, and the viral AI researcher resignation.

---

⏱️ Fast Hour

00:00 What’s on Fast Hours this week?

06:35 Why do traumatic moments burn into memory

07:42 What was different before social media

13:48 This week: Astra, GPT Image 2.5, a viral resignation

15:04 Did an AI researcher really resign over ASI

18:40 How to tell what is true in AI news

20:42 Why quitting your AI job can't stop superintelligence

27:01 What do the cited reports allege about Kimi

28:33 What AI misuse examples do the hosts discuss?

34:07 How did Astra build a golf course prototype?

35:35 How did research improve Astra’s first attempt?

36:33 What happened when two AI chats collaborated?

39:29 Why did Rory stop the drainage research?

40:02 How did Drew approach his Blender experiment?

40:52 How did Astra recreate Drew’s typewriter?

43:49 How long does AI-assisted 3D work take?

44:43 How did Drew build a ChatGPT dashboard?

48:32 What happened when Astra explored Midjourney?

53:56 How did mood boards shape Astra’s prompts?

58:49 What improved in GPT Image 2.5?

01:00:24 How do GPT Image 2.5 edit comments work?

01:01:47 How do you request multiple image variations?

01:03:30 How well did GPT Image 2.5 resize ads?

01:07:11 How reusable templates in GPT Image 2.5 can help brands

01:08:37 What’s coming next for Fast Hours?

To run a solo business on AI, build a system of small skills and agents that handle the admin, comms, and ops so your time goes to creating.

---

Two founders who swore AI would give them their time back open the hood on what they actually run.

Drew walks through 37 hand-built skills and a 21-layer system for writing in his own voice.

Rory runs his whole business out of Notion and Claude, down to finding an online fax machine for New York State. Neither of them can remember what half their own skills do.

That's kind of the point.

This episode covers building an AI operating system for a one-person business. Topics include Claude skills and agents, a voice system for writing, email and call ingestion, Notion as a CRM, red-teaming contracts and MSAs, predicting LinkedIn reach, Nano Banana prompt engineering, and handling taxes, invoices, and vendor forms. Fable and Astra model releases open the show.

An AI creative director combines design fundamentals, AI fluency, tool selection, and repeatable workflows to produce better creative work.

The boys over at Fast Hour invites a 24-year-old AI creative director to give away her playbook and somehow gets reminded that buying more AI subscriptions does not count as mastery.

Jamey Gannon explains why AI is a skill, what top operators do differently, how Midjourney mood boards become brand systems, and why sometimes the smartest AI move is opening Photoshop.

Jamey Gannon explains how self-taught design, social media, freelancing, and AI fluency shaped her work as an AI creative director. Jamey Gannon demonstrates Midjourney mood boards, SREFs, Midjourney V8.2 Edit, Krea K2, Claude, Figma, Photoshop, Flora, Nano Banana, and the CXO brand system, including when to build custom tools instead of forcing an existing workflow.

---

⏱️ Fast Hour

00:00 Who is Jamey Gannon?

06:43 How Jamey taught herself design at 15

12:23 Why Gen Z chases money over job titles

15:35 What first freelance clients look like at 17

18:43 Why social media is a freelance prerequisite

22:16 Freelance math: 20 clients vs one salary

24:13 How her sister makes $5K–$10K/month with AI

27:08 What is an AI creative director?

28:58 What the AI Creative Director course teaches

33:05 Is Krea catching Midjourney?

35:53 The "easy, fast, cheap" AI lie

38:43 Three moments that hooked Jamey on AI

42:23 How to build brand mood boards

46:00 How one SREF cracked the brand style

46:27 Midjourney + Figma: the pixel shader pipeline

49:06 When you should not use AI

51:53 Two ways to use Midjourney mood boards

56:44 What top AI creatives do differently

59:44 Build the tool when the workflow doesn't exist

1:11:28 Midjourney V8.2 Edit: first live tests

1:15:00 What works and what drifts in Midjourney Edit

1:20:06 Midjourney Edit vs Nano Banana: identity lock

1:21:32 Can Midjourney edit text and fonts now?

1:25:23 Can Midjourney's edit model preserve logos and apparel graphics?

1:31:05 Is Midjourney inpainting or regenerating?

1:34:33 The verdict: using Nano Banana less

1:37:34 Where Nano Banana still fits

Brands pay five figures for AI workflows that turn repetitive creative work into reusable systems teams can run at scale.Drew Brucker and Rory Flynn speedrun their way into a useful business model while trying to explain node-based AI without melting anyone’s brain. The opportunity itself is practical. Find expensive, repetitive creative bottlenecks, turn them into reusable workflows, and make the complicated machinery simple enough that an entire team can actually use it.The boys break down Figma Weave, node-based AI workflows, system prompts, batch processing, arrays, Claude, ChatGPT, Gemini, Flux, Nano Banana, Gen Effect, and MCP. SharkNinja and BarkBox examples show how AI workflows support localization, product visualization, asset re-versioning, creative production, team handoff, and scalable content generation.The bigger idea here is that the value comes from encoding the process, creative logic, and standards into a system that can be reused across hundreds of assets without starting from zero.#AIWorkflows #CreativeAutomation #GenerativeAI #FigmaWeave #aiforbusiness ---⏱️ Fast Hour00:00 Cold opener07:22 Why a full Figma Weave episode09:53 How node workflows went mainstream in a year14:10 Why use a node-based AI tool at all?19:02 Inside the Figma Weave AI toolbox20:53 How to sell AI workflows to businesses23:24 Why brands pay five figures for AI workflows24:33 How SharkNinja localizes across 35 markets30:07 Why recurring tasks belong in workflows31:34 Live build: your first AI workflow39:09 What the Gen Effect node can do44:00 How to turn an image into a 3D asset48:46 Scale one fashion image into reusable assets55:18 How to build a batch-processing engine1:03:24 Prompt vs system prompt: what's the difference?1:05:38 Turn a node graph into a reusable tool1:12:17 Engineering an automated listicle video1:14:51 One-shot video vs modular AI production1:24:29 How BarkBox fixed one production bottleneck1:35:20 Where AI workflows create business ROI1:38:20 Why workflows survive every new AI model1:39:29 Paste your workflow into Claude to debug it1:42:57 Use AI workflows as callable functions1:44:28 Publish your workflows into Claude MCP1:46:09 Resources and wrap-up---FIGMA WEAVE 15% OFF: Use code FASTHOURS15 at checkout- 15% off the first purchase of a Figma Weave Starter, Pro, or Team subscription- One-time use per person- Applies to the first month (for monthly plans) OR first year (for annual plans)OUR FREE FIGMA WEAVE WORKFLOWS:

• Drew's Apparel Photoshoot: https://app.weavy.ai/flow/JV8vBtbkOl3vNeiJjAYwxN
• Drew's Product Social Images: https://app.weavy.ai/flow/la8iMD20eGX4eGF91qunVu
• Rory's Listicle: https://app.weavy.ai/flow/SpLj0jsU8hThMmHWtfmT37
• Rory's SD2.5 Prompting: https://app.weavy.ai/flow/MdYt6UJi6ch0MkgxTaCe6r
• Rory's GenEffects Collage: https://app.weavy.ai/flow/sX4dJgsrp9DIrOz5f9ojX1
• Rory's Batch Generator: https://app.weavy.ai/flow/f9OljOQLkPbJ9Q04iN8Uou
• Rory's El Camino Concept: https://app.weavy.ai/flow/BPfVXywHhoymEi3CFxOO3Q