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
A healthcare-adjacent B2B service provider came to me with AI-drafted legal documents: a Privacy Policy and a "one-size-fits-all" BAA, and no Terms of Service covering visitors who never became clients. I interviewed the founder to map their actual data flows, uncovered the gap, and drafted a ToS with a clear, reasonable liability cap, while aligning it with tightened Privacy Policy language.
Result: consistent, fit-for-purpose documents that protect the business without scaring off prospects. AI is a great first draft. However, it is important to make it more defensible. That's why I look beyond the paperwork to identify loopholes, risks, and gaps.
Do you trust AI drafts or would you prefer a review before using them?
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
Luxury Handbag Collection Launch - Instagram CampaignDesigned this aesthetic product launch post for a fashion accessories brand. Focus was on minimal luxury aesthetic, earthy tones and premium feel to attract Gen-Z women buyers.
Tools: Canva, Photoshop
Goal: Increase saves & website clicks
Saves and clicks pull against each other a bit — a post complete enough to save doesn't leave much reason to tap through. What's worked for me is holding one detail out of frame so the tap has a job to do. Which of the two did the client actually care about more?
Why do people visit my website but choose someone else?
Because you sound like everyone else.
Your website should help the right client recognize why you may be a good fit for them.
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?