Book restaurant tables via OpenTable and Resy
In a hands-on test, Claude showed Resy availability but could not book, and ChatGPT's agent clicked through OpenTable but set the wrong party size.
Anthropic’s AI model for writing, analysis, coding and agents.
Claude is a family of AI models from Anthropic. It is strong at long documents, careful reasoning, coding and tool use, which makes it a common “brain” inside agent workflows built with n8n, Zapier, Make or custom code.

In a hands-on test, Claude showed Resy availability but could not book, and ChatGPT's agent clicked through OpenTable but set the wrong party size.
The author uses Claude web and Jules (Gemini with GitHub integration) as pair-programming partners, navigating while coding locally and submitting back.
Users relay that their AI agent installed a scheduling skill, linked social accounts and scheduled about 100 videos; these are vendor-relayed testimonials.
The author connected Claude to Ghidra through MCP to analyze and rename functions in an Atari River Raid ROM.
After the RAG indexer crashed on an uploaded book, Claude used Unix commands to work out the file format and grep the book manually.
InstantDB had Codex, Opus, and Gemini each try to build a multiplayer shooter.
An open-source text-to-CAD tool that produces 3D models from text and image references by generating CAD as code.
A chemistry professor ran 11 students' problem sets through Claude to see if its annotations could help manual grading; the project was accidentally left public, exposing student information.
An agent built on Claude and Agno implements capabilities in its own source code in Docker, with changes validated, committed, or rolled back; it reached 21+ capabilities.
A toolset and docs let ChatGPT and Claude agents write LDraw source files that become LEGO CAD models, packaged as a dockerized web app.
A PCWorld writer asked Claude to book a table for three in Midtown Manhattan via the Resy connector; it picked a restaurant but the exchange was clunky, with raw JSON and permission prompts.
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
An hour before each discovery call, get a one-page brief on the account, the attendee and recent news, saved to Salesforce.
Each month, find posts whose search clicks dropped, research what changed with Perplexity, and get a Claude-written refresh brief for each one.
Turn one campaign brief into 20 Meta and Google ad variants, score each against your brand rules and limits, and queue the best for approval.
Descript transcribes each discovery call, Claude tags pains, requests and quotes, and Notion keeps a themes database the whole team can search.
Record a 30-minute customer call, transcribe it in Descript, and have Claude turn it into a structured case study draft in your Notion template.
Every Monday, get a Slack summary of spend, CPA and ROAS by campaign, with week-over-week changes and anomalies flagged before standup.