Research a question

webref delegates your question across multiple sources — docs, forums, blog posts, and technical articles — and returns a complete, source-traced answer. The same information that other tools dump as 16k+ tokens of noise, webref delivers in ~1.5k tokens with confidence scoring and knowledge gap analysis. Nothing useful gets cut, it's just expressed more clearly.

You can ask questions, pass URLs, or mix both. The planner figures out what to search and what to read.

Usage

bash

webref "your question here"

Pass a URL to read and synthesize a specific page:

bash

webref "summarize https://example.com/article"

Mix questions with URLs to combine web search and targeted page reads:

bash

webref "compare https://lib-a.dev/docs and https://lib-b.dev/docs for auth support"

By default, webref shows a minimal live progress view in a real terminal: generated searches, source progress, then the final answer.

bash

webref "Docker networking explained"

When piped, webref switches to one additive plain-text transcript:

bash

# Save to file
webref "GraphQL best practices" > notes.md

# Copy to clipboard (macOS)
webref "JWT token structure" | pbcopy

Result anatomy

Every research result has five parts.

The synthesis is the main body — a focused, well-structured answer drawn from multiple sources. Every factual claim is cited inline with a source URL, so you always know where information came from. This isn't a summary that loses detail. It's the same information reorganized to eliminate redundancy across sources.

Source links are embedded directly in the text as markdown hyperlinks. Your agent (or you) can follow any link to read the full page if more depth is needed.

Confidence rates the answer as high, medium, or low based on source agreement, freshness, and whether primary or secondary sources were used. This tells your agent how much to trust the result.

Gaps lists specific things the research couldn't confirm or didn't cover. Each gap is concrete enough to write a follow-up query from. When the results are comprehensive, this reads "None identified."

Tips for better queries

Write queries with clear intent, not keyword lists. The synthesizer needs to understand what you want to know, not just which terms to match.

bash

# Good - clear intent
webref "how to handle file uploads in Next.js 14 app router"

# Less good - keyword soup
webref "next.js file upload handler api route multipart"

Be specific about what you're trying to learn. Include version numbers, frameworks, or specific use cases when relevant.

bash

webref "how to set up TypeScript path aliases in Vite"
webref "Drizzle vs Prisma performance and DX tradeoffs"

Ask natural questions for comparison or evaluation.

bash

webref "What's the difference between useMemo and useCallback?"
webref "better-auth pricing and license model"

Split multi-topic queries into separate research calls. If you need both pricing info and setup instructions, run two research calls. Each call should have a single clear intent.

Credits

Each query costs 1 credit. Credits are only deducted for successful results — if something goes wrong, you're not charged.

Check your balance anytime on your dashboard.