The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Built this AI agent to find, organize, and manage leads through Gmail, helping automate lead handling and outreach.
The Gmail lead-intake workflow is a useful problem to tackle. How are you handling duplicate leads and the boundary between organizing a lead and sending an outreach email? I’d keep a human review step before the first send, plus a record of why each lead was selected, so the automation stays auditable.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Lost 2 days building a complex n8n workflow. Here's what I learned.✌️
The project: A 12-node AI Receptionist automation for a luxury resort in Bangladesh. Multi-channel (WhatsApp, Telegram, Voice), 9 Google Sheets, Gemini API, payment automation, customer CRM.
What went wrong: Added a new voice integration node. Accidentally deleted the entire workflow.
Why it happened:
No JSON exports after milestones
No version control (Git)
Testing changes LIVE on production workflow
No documentation
Building locally with zero redundancy
The fix (now implemented):
✅ JSON backups after every 2-3 nodes
✅ GitHub versioning
✅ Clone workflows for testing
✅ Modular design
✅ Complete documentation
For automation professionals: You're not just builders—you're engineers.
Treat workflows like software:
Documentation
Version control
Backup strategy
Modular testing
Client delays = lost revenue + credibility damage.
Make the systems bulletproof.
How do you prevent data loss in your automation builds? 👇
#n8n #Automation #WorkflowAutomation #NoCode #LessonsLearned #make #AIAutomation #DataAnalyst #MachineLearning
I'd try restoring one of those JSON backups into a cloned workflow before the next handoff. That way you know it can actually get you running again.
I went the wholesome and grounded route because yeah lol.
Series Title: Daisy on the Prairie
Original Character: https://cantina.com/i/s4jat (@daisyontheprairie)
Pilot Episode: https://cantina.com/i/m5zx8
Info:
Daisy is a Prairie Ground Squirrel who is out here to teach you about the Prairie and the native plants and animals on the land. She quite friendly, down to earth, and a protector of prairie lands.
The pilot is a quick intro how Daisy lives and her start to prep for a major seasons for the prairie: wildfire season.
I imagine a children's show like pacing where there is a new activity or adventure to learn from with each episode while weaving an overall narrative. The goal would be to show the importance of prairie land, and how the plants and animals being and presence positively impacts the prairie ecosystem. Characters introduced would be her parents, friends like bison, other ground squirrels, birds, and so much more. Then there would be focus on plants and other important dynamics of the ecosystem. Also challenges would focus on natural disasters or major shifts in ecosystems and how the animals and ecosystem react to these challenges.
Behind the scenes on this one, because the build was more interesting than the result.
The task: get an AI agent to play a browser Tetris clone and beat the high score.
Problem one — the game renders to a <canvas>. No DOM, no list of filled cells, just pixels. So the first thing to build was a reader: divide the canvas into a 10×18 grid, sample each cell, decide filled or empty.
First attempt classified by colour, matching each cell against known block colours. Failed instantly and silently. Purple pieces read as empty. Gradient regions read as empty. The bot was playing against a board that was largely imaginary.
The fix was changing the question. Not "what colour is this cell" but "how much does this cell vary." Empty cells are flat. Filled cells have an edge, a bevel, a highlight. Measure luminance across the cell, take max minus min, threshold it. Works on every piece colour without enumerating any of them.
Then a flood fill to isolate the falling piece, and a placement search — for every column and rotation, simulate the drop, score the resulting board, pick the best.
Problem two — the browser protocol caps each execution at 45 seconds. Tetris doesn't finish in 45 seconds. So instead of an async loop that waits, you install an interval, return immediately, and poll the page every twenty seconds.
That's where it went wrong. The smart bot was too slow, so it got simplified down to a fixed key pattern. And the number being polled turned out to be the loop's own tick count, not the game score. Five runs of "improving" numbers that measured nothing at all.
The interesting part was the cleanup. To find out what actually happened, I went back to a 30-minute screen recording:
— ffmpeg to pull frames at 2fps
— locate the playfield in pixel coordinates
— classify every cell across a dense frame sequence
— then render the classifier's verdicts back over the frames and check them by eye
That last step is the one that mattered. The first pass flagged the bottom row as complete in almost every frame, which looked like a bug in my grid alignment. It wasn't. The row genuinely was complete, and the game genuinely never cleared it.
Verified: a completed line sits in the well for ten full seconds while the stack piles on top of it. Across ninety seconds of play the board empties about thirty times, and every one of those is a game over, not a line clear.
The lesson I'm taking into the next build: before you simplify under pressure, write down what you're optimising for, then check whether the simplification is still attached to it.
infiniteup.dev
The Tetris Clone Didn’t Clear Lines. Our AI Agent Didn’t Notice. - InfiniteUp
We pointed an AI agent at a browser game and it reported five runs of improving scores that measured nothing at all. It also reached a correct conclusion on worthless evidence. What that failure means for anyone deploying agentic AI.
tetris on a canvas is a tough one. did the agent beat the high score?