Cam

510 posts

Cam

Cam

@camduncan

Enterprise software design & direct response marketing.

Brisbane, Australia Katılım Ağustos 2024
1.1K Takip Edilen215 Takipçiler
Cam retweetledi
Bryan Cano
Bryan Cano@BryanECano·
🚨 Meta released their Ads MCP and CLI today – if you use Claude or ChatGPT you should install this asap (resources in comments). What makes this announcement so interesting is that it gives AI tools direct, authorized access to help manage your Meta Ads account through natural language. 1. Comprehensive reporting Pull detailed reports, surface performance trends, and quickly understand what is happening across campaigns. 2. Campaign management Create and edit campaigns, ad sets, and ads without manually clicking through Ads Manager. 3. Catalog management Create product catalogs, add product data, and troubleshoot feed issues faster. 4. Signal diagnostics Access signal health and quality insights so you can prioritize the parts of your setup that need attention. This is a huge step forward in agentic media buying. Will be testing this rest of the week!
Bryan Cano tweet media
English
129
289
3.2K
635.1K
Cam retweetledi
Ahmad
Ahmad@ahmad_a_wahabb·
Breaking🚨: Claude can now build full ad workflows for you. connect claude to crafft drop your character + product in chat claude builds the workflow, writes the prompt, runs Seedance 2 no time limit. no scene pre-gen. one ref = infinite ads. RT + comment "skill" and I'll send the file
English
107
74
86
8K
Cam
Cam@camduncan·
If you’re writing copy, download the ElevenReader app and upload your copy and you can have it speak it back to you without any limits. You pick up on things when you hear someone else speak it to you.
English
0
0
0
37
Cam
Cam@camduncan·
@orenmeetsworld Running local models will become more and more important to avoid cost, censorship and sameness. It’s expensive now to setup but will be more cost effective long term.
English
0
0
0
57
Oren John
Oren John@orenmeetsworld·
Exactly how subsidized are tokens for Claude, Perplexity etc right now? Realistically if we're building workflows dependent on these that are running two $200/m max plans... does this change to... $1000? $5000? More? When?
English
63
1
230
94.7K
Cam
Cam@camduncan·
@letskree8 @heysatya_ “Work with the 🦎 team to get premium branding, web & product design”
English
0
0
1
133
Cam
Cam@camduncan·
a UI component library that is pre-designed in code that you need a paid subscription to ping via MCP/API would be cool Could just ask claude to use the library and if you’re authenticated it uses them instead of generating components from scratch …just an idea but with your audience could be big
English
0
0
1
260
Nick
Nick@nickbakeddesign·
Build web apps using a custom design .md file for each web app collection on baked supply Pick a theme/collection, use the design. md file on Cursor & build your SaaS > tables > navigation > toasts > modals > input fields > buttons
Nick@nickbakeddesign

Made $0 😇

English
5
2
41
7.6K
Cam
Cam@camduncan·
I’ve found using Nano Banana via the API much more reliable. There’s a bunch of these node based editors that allow you to create with the API: - weavy.ai (my personal fav to use) - Freepik - Higgsfield Best part is it has the video generation models too so you can just link your image output and turn into video in one click
English
0
0
2
224
MEDIA
MEDIA@ipb_media·
need help with nano banana i have the highest paid version of gemini but whenever i paste in a JSON prompt it keeps getting cut off like i paste the entire thing and once i hit enter it looks like its getting cut off at like 50-70% depending on how long the prompt is. pls help this used to never happen and cant figure out how to fix
English
4
0
7
2.4K
KAZ
KAZ@almightykazs·
@camduncan Wait till I show you what we are doing internally next week 😈
English
1
0
3
237
KAZ
KAZ@almightykazs·
All this AI CMO/AI creative strategist bs just makes me go back to one fundamental rule i have always followed When everyone zigs, just zag Making an ad that does 6 figs+ rev a day is simply not something a generic AI solution can do right now (without human intervention)
English
11
1
105
5.8K
Cam
Cam@camduncan·
I pray my competitors use an AI CMO and outsource all creative thinking to the same models.
English
3
0
2
109
Cam
Cam@camduncan·
Want to use AI to its fullest potential? Document every process and SOP as a Claude skill. Store them as markdown files in your skills repo. Your team can inherit the whole library easily. They’re now one slash command away from doing things exactly how you would.
English
0
0
2
82
Cam
Cam@camduncan·
@ipb_media I’m the same, I actually created a Claude skill to help prevent derailing from the main goal so anytime I say “I have a new idea…” it knows to weigh up if it helps the overall mission or if parts of the idea can help
English
0
0
0
68
Cam
Cam@camduncan·
Use weavy.ai (not affiliate just what I use) Nano Banana 2 model to create your image and then link it up to Sora model to create the video Promoting will be your friend here. Find any examples upload a screenshot from them to ChatGPT to get a ‘style JSON profile’
English
0
1
1
336
Scott Simmons
Scott Simmons@scottsimnz·
You’ve seen those 3d animated ai ads? Anyone have experience with those models? I have an idea I want to test with animated cartoons. Don’t even know where to begin.
English
23
0
43
5.9K
Alfie Carter
Alfie Carter@AlfieJCarter·
I created a free resource to build a full Claude Code GTM infrastructure for 2026 that runs automation on autopilot. I've spent the last year testing what actually works across every Claude Code use case for GTM engineers. ✓ Sub-agents running research, enrichment, and outreach in parallel ✓ Turning n8n workflows into live deployed apps from inside Claude Code ✓ MCPs connecting Claude Code directly to Clay, ClickUp, Slack, and your full stack ✓ CLAUDE.md self-improvement loops that make every correction permanent ✓ A full deployment system on Modal and Trigger.dev running 24/7 without you And I finally turned it all into a step-by-step playbook you can steal. This is how GTM engineers are building infrastructure in 2026 - without manual node building, without broken workflows, and without duct-taping tools together. And we're giving away the full playbook for free. Here's what's inside: ✅ The WAT Framework How to structure every Claude Code build with workflows, agent, and tools so nothing breaks when complexity scales. ✅ CLAUDE. md Self-Improvement Loop How to make every correction permanent institutional knowledge so the agent gets smarter every single session. ✅ MCP Stack for GTM How to connect Clay, ClickUp, Slack, and Amplitude so Claude Code reads, writes, and acts inside your actual tools without tab switching. ✅ Sub-agents and Agent Teams How to run parallel research, enrichment, and outreach tasks in isolated contexts so your main session stays clean. ✅ Deployment with Modal and Trigger. dev How to push workflows to production so they run on schedule 24/7 without you triggering anything. This is the same system used to: → Build n8n workflows from plain English descriptions without touching a single node manually → Deploy signal monitoring automations running every Monday at 6am without intervention → Connect Clay and ClickUp so prospect scoring and task creation happen in one session → Run five parallel sequence variant builds simultaneously with zero conflicts using worktrees → Turn browser automation into live LinkedIn workflows that run without manual input All without manual builds. All mapped out. All free. Want the full Claude Code GTM Engineer's Playbook? Reply CLAUDE and I'll DM it to you. Follow me so I can dm you.
Alfie Carter tweet media
English
393
31
303
28K