Levels automates UberEats via Claude Code

// 1h agoTUTORIAL

Levels automates UberEats via Claude Code

Pieter Levels automated his UberEats ordering process by using Claude Code to write Playwright browser automation scripts. After a single manual login to preserve session state, the agent successfully orders food items via simple command-line instructions.

// ANALYSIS

Browser automation driven by AI agents is rendering traditional developer APIs obsolete for custom, personal integrations.

–Web-wrapper mobile apps like UberEats are highly vulnerable to seamless playwright automation.
–One-time session state storage solves the complex MFA/OAuth hurdles that normally block agentic scripts.
–The ease of creating these automation scripts with Claude Code makes automating trivial tasks economically viable.

// TAGS

claude-codeplaywrightweb-agentagentubereats

DISCOVERED

1h ago

2026-07-07

PUBLISHED

2h ago

2026-07-07

RELEVANCE

7/ 10

AUTHOR

levelsio

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE16m ago

Mintlify CLI boosts initial builds 3x

Mintlify has optimized its command-line interface, yielding a 3x speedup on initial builds and enabling large documentation sites with over 4,000 pages to compile in 10 seconds. Developers can upgrade by running mint update.

RESEARCH30m ago

NVIDIA Puzzle-75B doubles hybrid MoE throughput

NVIDIA released Nemotron-Labs-3-Puzzle-75B-A9B, a 75B parameter variant of the 120B Nemotron-3-Super model optimized using a new multi-stage "Iterative Puzzle" compression framework. This hybrid MoE model roughly doubles interactive server throughput on B200 nodes and increases 1M-token concurrency by 8x on a single H100 GPU while maintaining quality.

UPDATE50m ago

Grok Build 0.2.89 lands Linux voice dictation

The new Grok Build 0.2.89 update brings voice dictation functionality to Linux users and upgrades image editing capabilities to use the higher-quality Imagine model. Key functional updates also include a new /auto slash command that switches the assistant to classifier permission mode, as well as modifications to the --effort and --reasoning-effort parameters.