Web search

Models have training cutoffs; your problems don't. The agent's web_search tool lets it look things up on the live web mid-task — no browser tab, no copy-paste, and no separate search API key to configure.

When the agent reaches for it

The tool is described to the model as the way to get up-to-date information — so the agent typically searches when a question outruns what it can know from training or from your project:

• Current versions — "what's the latest stable release of Next.js?" before pinning a dependency.
• Documentation — API shapes, config options, or flags for a library it's about to use.
• Error messages — pasting an unfamiliar build error and asking for a fix often triggers a search for the exact message.

You can also just ask it to search ("look up how X changed in v3") and it will.

What you see in the transcript

A search shows up like any other tool call — a tool card with the query, a running indicator, and expandable results once it completes. The results are a readable list: each hit's title, URL, and snippet. The agent then reasons over those snippets in its answer, and when the answer draws on them it ends with a short Sources list of the URLs it actually used, as links.

Because web_search is read-only, it never raises an approval card — searches run freely, like file reads.

How it works underneath

The search request goes through Mel's backend, which queries a free public search source and returns the formatted results to the agent. Two practical consequences:

• No key, no setup — search works out of the box on every install.
• Snippets, not full pages — the agent sees result titles, URLs, and summaries. That's enough to answer most "what's current" questions; for deep dives into a specific page's content, it may quote the snippet and give you the link to read further.

Working well with search

• Include the error text or version constraint in your prompt — concrete strings make for precise queries.
• If you want the agent to *avoid* the web (offline work, or to keep it grounded in your repo alone), say so; it only searches when it decides fresh information is needed.
• Search pairs naturally with agentic work: "find the current recommended config for this tool, then update our setup to match" runs a search, then edits files with the usual diff cards and approvals.