53 Coding Prompts for Claude Code & Cursor
Paste these prompts into Claude Code, Cursor, Codex, or any coding agent to build Context.dev into your own codebase. Each one names the stack, points the agent at the Context.dev docs and the official SDK for your language, and ends with a clear definition of done, such as passing tests or a documented environment variable. With the Context.dev MCP connected, the agent can also read the live docs and make test calls while it works.
Coding prompts
Add the SDK to my repo
Add Context.dev to [repo path] using the official SDK for [language]. Read https://docs.context.dev/sdks first, create one shared client that reads the key from the CONTEXT_DEV_API_KEY environment variable, and add a smoke test that scrapes [URL] to Markdown. Done means the test passes, the variable is in .env.example and the README, and no unrelated files changed.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Interview me before building
I want to add [feature] to [app] with Context.dev. Read https://docs.context.dev, then interview me with short multiple-choice questions until you could write a spec: which endpoints, inputs and outputs, failure handling, credit budget, and what’s out of scope. Write the answers to SPEC.md and stop without writing code.
Uses: Web Search, Scrape, Answers. Install the Context.dev MCP if you haven’t already.
Plan first, then implement
Explore [repo path] and the docs at https://docs.context.dev, then propose a numbered plan for adding [feature]: files to change, Context.dev endpoints involved, and how you’ll verify each step. Wait for my approval before editing. After implementing, have a fresh subagent review the diff against the plan, skipping style, and show me the test output.
Uses: Web Search, Scrape. Install the Context.dev MCP if you haven’t already.
Document Context.dev for agents
Add a Context.dev section of 20 lines or fewer to [CLAUDE.md or AGENTS.md]: where the client lives, which environment variable holds the key, which endpoints we call and why, the test command, and links to the matching pages on https://docs.context.dev. Check every line against the code and the docs, and leave the rest of the file untouched.
Uses: Scrape, Web Search. Install the Context.dev MCP if you haven’t already.
Debug a failing Context.dev call
This Context.dev call fails: [error message and request ID]. Reproduce it in a minimal script with the official SDK for [language], read the Troubleshooting docs at https://docs.context.dev, and name the root cause before changing code. Write a failing test that reproduces it, then fix it. If it’s an API bug, draft a bug report with the request ID instead of a workaround.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Review my Context.dev integration
Review every Context.dev call in [repo path] against the Production checklist at https://docs.context.dev. Check where the key lives, whether each output’s success flag is handled, cache freshness, deadlines, retries, and request ID logging. Report findings by severity with file and line, skip style, and don’t change code until I approve.
Uses: Scrape, Web Search, Brand. Install the Context.dev MCP if you haven’t already.
Prefill signup from a work email
In my [Next.js] signup flow, look up the company behind the user’s work email with Context.dev Brand and prefill company name, logo, and brand color as editable fields. Read the lookup-by-email docs at https://docs.context.dev and call the official TypeScript SDK on the server only. Skip free email domains, never block signup on a failed lookup, and test found, not found, and timeout cases.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Theme each workspace from its domain
When a team enters [company domain] during onboarding in [framework], fetch its colors and fonts with Context.dev Styleguide and apply them as CSS variables for that workspace. Read the Styleguide docs at https://docs.context.dev and use the official SDK for [language] on the server. Store the result instead of refetching, fall back to my default theme when text contrast fails WCAG AA, and let admins override it.
Uses: Styleguide, Brand. Install the Context.dev MCP if you haven’t already.
Company autocomplete field
Add a company autocomplete to [form] in [React or Vue] that suggests brands by name or domain as the user types, with logo, name, and domain. Read the Auto-complete Brand docs at https://docs.context.dev and call it through a server route with the official SDK, debounced, with stale requests cancelled. Fetch the full brand profile only after a pick. Be ambitious: handle keyboard navigation and the loading, empty, and error states, with tests.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Logos in my customer table
Show a company logo beside each row of [table component] with Context.dev Logo Link, following the pattern of [existing avatar component]. Read the Logo Link docs at https://docs.context.dev, keep the public client ID in an environment variable, reserve width and height to prevent layout shift, and hide images that fail to load. List the referring-domain restrictions to configure in the PR description.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Merchant logos for transactions
In my [Python or Go] transactions service, turn raw card descriptors like [example descriptor] into a merchant name, logo, and domain with Context.dev Brand. Read the lookup-by-transaction docs at https://docs.context.dev, use the official SDK, cache results per descriptor, and leave unresolved rows as they are instead of guessing. Add table-driven tests for matched and unmatched descriptors.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Personalized demo page per prospect
Add a route to [Next.js app] at /demo/[domain] that renders my product demo with the prospect’s logo, colors, and one-line description from Context.dev Brand. Read the Brand docs at https://docs.context.dev, call the official TypeScript SDK on the server, and cache each domain for [24 hours]. Show a neutral fallback for unknown domains and mark the pages noindex.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Design tokens to a Tailwind theme
Write a [Node.js] script that pulls design tokens for [domain] with Context.dev Styleguide and generates a [Tailwind theme or CSS variables file]. Read the Styleguide docs at https://docs.context.dev and use the official TypeScript SDK. Map colors, typography, and spacing, skip anything missing rather than inventing values, and snapshot-test the generated file.
Uses: Styleguide. Install the Context.dev MCP if you haven’t already.
Laravel company enrichment job
In my [Laravel] app, add a queued job that fills logo, colors, and description on the [Company model] from Context.dev Brand when a company is created. Read the PHP SDK and Brand pages at https://docs.context.dev and follow the PHP brand lookup example there. Read the key from config backed by an environment variable, retry with backoff, and cover it with a [Pest or PHPUnit] test that fakes the API.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Brand lookup serverless function
Build an [AWS Lambda or Vercel function] in [Node or Python] that returns a slim brand profile (name, logo, colors) for a domain from Context.dev Brand. Read the Brand docs at https://docs.context.dev, use the official SDK, load the key from [secret manager], and cache responses in [cache store]. Validate the domain input, return 404 for unknown brands, and add unit tests with a mocked client.
Uses: Brand. Install the Context.dev MCP if you haven’t already.
Schema extraction service
Build a [FastAPI] service with POST /extract that takes [URL list] and returns JSON matching [JSON schema] for each page using Context.dev Scrape. Read the Scrape JSON docs at https://docs.context.dev and use the official Python SDK. Add bounded retries with jitter, a cache keyed by URL and schema, and per-URL errors instead of failing the whole request. Done means pytest passes with the SDK mocked.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Migrate a Puppeteer scraper
Replace the Puppeteer code in [file or folder] with the official Context.dev SDK for TypeScript. Read the Scrape and Browser actions docs at https://docs.context.dev, list each behavior the scraper relies on (waits, clicks, selectors, screenshots), and map it to a documented option, flagging anything you can’t map instead of guessing. Keep function signatures the same and remove Puppeteer only after the existing tests pass.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Migrate a BeautifulSoup script
Rewrite [script.py], which uses requests and BeautifulSoup, to fetch pages through the official Context.dev Python SDK. Read the Scrape docs at https://docs.context.dev and pick Markdown, CSS selector rules, or JSON with a schema based on what the script extracts today. Compare old and new output on [5 sample URLs], explain each difference, and keep the CLI arguments unchanged.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Switch from another scraping API
My code calls [current scraping or search API] in [paths]. Read https://docs.context.dev and move every call to the official Context.dev SDK for [language], covering auth, timeouts, errors, and response parsing. Write a table mapping old options to Context.dev options, flag anything unsupported instead of inventing a workaround, and keep the existing tests green.
Uses: Scrape, Web Search, Crawl & Batches. Install the Context.dev MCP if you haven’t already.
Price tracker cron script
Write a [Node.js] cron script that scrapes [product URL list] with Context.dev product extraction and stores price, currency, and availability in [Postgres table]. Read the Product docs at https://docs.context.dev and use the official TypeScript SDK. Insert a row only when a value changes, log failed URLs with their request ID, and add a README section on running it locally.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Screenshot service for link previews
Add an endpoint to [Express app] that captures a viewport screenshot of a submitted URL with Context.dev Scrape, uploads it to [S3 or R2], and serves the stored copy for [7 days]. Read the Screenshot docs at https://docs.context.dev and use the official SDK. Validate URLs, reject private network addresses, and test valid, invalid, and failed captures.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Click and scroll before scraping
Extend the scrape of [listing URL] in [scraper file] to click “[button text]” and scroll before capture with Context.dev browser actions. Read the Browser actions docs at https://docs.context.dev, stay within five actions (a paid plan feature), and return items as JSON matching [schema]. Add a test against a saved fixture and note the plan requirement in the README.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
App review sync job
Add a nightly job in [stack] that pulls recent reviews for [App Store and Google Play app URLs] with Context.dev’s prebuilt review parsers and writes new ones to [table]. Read the Pre-built parsers docs at https://docs.context.dev, use the official SDK for [language], and dedupe on a stable key built from the returned fields. Include tests with saved fixtures and document the schedule in the README.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Google Maps business importer
Write a Go command that takes [Google Maps search URL] and imports business name, address, phone, rating, and website into [database] with Context.dev’s Google Maps prebuilt parser. Read the parser docs at https://docs.context.dev, use the official Go SDK, upsert on a stable place identifier, and add a --limit flag. Done means go test passes against a saved fixture.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Careers pages to a job board
Add a [Django] management command that reads [careers page URLs], extracts open roles as JSON matching [schema] with Context.dev, and upserts them into my [Job model]. Read the Scrape JSON and Crawl docs at https://docs.context.dev and use the official Python SDK. Mark roles missing from the latest run as closed rather than deleting them, and add tests with fixtures.
Uses: Scrape, Crawl & Batches. Install the Context.dev MCP if you haven’t already.
Batch runner for 10k URLs
Build a [Python] job runner that submits [CSV of URLs] as a Context.dev batch, tracks progress, and saves results to [storage]. Read the Batches docs at https://docs.context.dev, use the official SDK, and send a retry key so a resubmit doesn’t create a duplicate batch. Show progress, resume after a crash, and list failed URLs with reasons at the end.
Uses: Crawl & Batches, Scrape. Install the Context.dev MCP if you haven’t already.
Batch webhook receiver
Add a route to [framework] that receives Context.dev batch webhooks, verifies the signature, and loads the results into [database]. Read the Webhooks docs at https://docs.context.dev: save each batch’s webhook secret from its submit response next to the batch ID (it’s only returned there), look it up per request, verify the HMAC over the raw body in constant time, and reject stale timestamps. Make processing idempotent and test valid, tampered, and replayed payloads.
Uses: Crawl & Batches. Install the Context.dev MCP if you haven’t already.
Docs site into a vector store
Build an ingestion script in [language] that maps [docs domain], crawls its pages as Markdown with Context.dev, chunks them, and upserts embeddings into [vector store] with URL and title metadata. Read the Map, Crawl, and Website and PDF RAG docs at https://docs.context.dev and use the official SDK. Re-runs should only touch changed pages, and a test should show a sample page round-tripping into the index.
Uses: Map URLs, Crawl & Batches. Install the Context.dev MCP if you haven’t already.
Sitemap diff against my CMS
Write a [Node.js] script that lists every URL on [domain] matching [path regex] with Context.dev Map, compares the list with [my CMS or database], and prints new and removed URLs. Read the Map docs at https://docs.context.dev and use the official TypeScript SDK. Add a --json flag and unit tests for the diff logic.
Uses: Map URLs. Install the Context.dev MCP if you haven’t already.
SEO checks on every preview deploy
Add a [GitHub Actions] job that crawls [preview URL] with Context.dev after each deploy and fails when a page lacks a title, meta description, or H1. Read the Crawl and Batches docs at https://docs.context.dev to pick an option that returns each page’s HTML, and write the check in [Node or Python] with the official SDK. Read the key from a repository secret, cap the crawl at [N] pages, and print a table of failures.
Uses: Crawl & Batches. Install the Context.dev MCP if you haven’t already.
Vercel AI SDK search tool
Add a web search tool to my [Vercel AI SDK] agent in [file] that calls Context.dev Search and returns titles, URLs, and short passages. Read the Search docs and the live web context recipe at https://docs.context.dev, call the official TypeScript SDK on the server, and cap results at [5]. Tell the model to cite the URLs it used, and test the tool schema and the empty-result path.
Uses: Web Search. Install the Context.dev MCP if you haven’t already.
LangChain search and read tools
Give my [LangChain] agent in [repo path] Context.dev tools for web search and reading a URL as Markdown. Read the LangChain integration page at https://docs.context.dev and use it if it covers what I need before writing wrappers. Add a small eval of [3 questions] that checks each answer cites a page the agent fetched, and document setup in the README.
Uses: Web Search, Scrape. Install the Context.dev MCP if you haven’t already.
Tools for the OpenAI Agents SDK
Add two function tools to my [OpenAI Agents SDK] agent, backed by Context.dev: web search and read a URL as Markdown. Read the Search and Scrape docs at https://docs.context.dev and use the official Python SDK. Trim tool output to [N] characters with source URLs, return timeouts as tool errors the model can see, and test both tools with a mocked client.
Uses: Web Search, Scrape. Install the Context.dev MCP if you haven’t already.
Claude tool-use loop with live web
Build a tool-use loop with the [Claude API SDK] in [language] where Claude can call three tools backed by Context.dev: search the web, read a page, and research a question as JSON with sources. Read the Search, Scrape, and Answers docs at https://docs.context.dev and use the official Context.dev SDK. Log each tool call with its request ID. Done means a sample run answers [question] with cited URLs.
Uses: Web Search, Scrape, Answers. Install the Context.dev MCP if you haven’t already.
Slack bot with live answers
Build a Slack bot with [Bolt for Python or JavaScript] that answers questions in [channel] using Context.dev Search and Answers, replying in a thread with source links. Read both docs pages at https://docs.context.dev and use the official SDK. Post a clear message on timeouts or credit errors, and put Slack app setup and every environment variable in the README.
Uses: Web Search, Answers. Install the Context.dev MCP if you haven’t already.
Claim checker with sources
Build a [Python] function that takes claims from [document or CMS field], researches each with Context.dev Answers, and labels it supported, contradicted, or unclear with source URLs. Read the Answers docs at https://docs.context.dev, including sources and deadlines, and use the official SDK. Run claims concurrently within my plan’s concurrency limit and test three claims with a mocked client.
Uses: Answers, Web Search. Install the Context.dev MCP if you haven’t already.
Live search fallback for RAG
In my [RAG chatbot], fall back to Context.dev Search when the vector store’s best match scores below [threshold], and read the top results’ content. Read the Search docs at https://docs.context.dev, including result content and filters, and use the official SDK. Save fetched pages back to the index with a fetched-at timestamp, and test both the index-hit and fallback paths.
Uses: Web Search, Scrape. Install the Context.dev MCP if you haven’t already.
Company news panel
Add a “Recent news” panel to [account page], following the pattern of [existing panel component], showing articles about the account’s company from Context.dev News. Read the News docs at https://docs.context.dev, query by the company’s domain with the official SDK on the server, cache for [1 hour], and paginate with the returned cursor. Cover loading, empty, and error states in tests.
Uses: News Search. Install the Context.dev MCP if you haven’t already.
Morning news alerts to Slack
Write a [scheduled function or cron job] that searches Context.dev News for [keywords or competitors] each morning and posts new articles to [Slack webhook] with title, source, and link. Read the News filter docs at https://docs.context.dev and use the official SDK for [language]. Remember posted URLs in [storage] so nothing repeats, and add a --dry-run flag.
Uses: News Search. Install the Context.dev MCP if you haven’t already.
Change monitor with a signed webhook
Write a setup script that creates Context.dev monitors for [competitor pricing URLs], plus a webhook handler in [framework] that verifies the signature and stores each change.detected event. Read the Monitors and Webhooks docs at https://docs.context.dev, use the official SDK, and turn on retries. Return 2xx fast, make handling idempotent, and test valid, tampered, and duplicate deliveries.
Uses: Monitors. Install the Context.dev MCP if you haven’t already.
Monitor admin page
Build an admin page in [framework] where my team can add, pause, and delete Context.dev monitors for [URLs] and see each monitor’s latest runs and changes. Read the Monitors docs at https://docs.context.dev and call the official SDK from the server only. Check monitor limits before creating one, confirm before deleting, and ask me before running anything against production.
Uses: Monitors. Install the Context.dev MCP if you haven’t already.
Weekly change digest email
Build a weekly job that reads changes from my Context.dev monitors on [competitor changelog URLs], groups them by company, and emails a summary through [email provider]. Read the Runs and changes docs and the change digest recipe at https://docs.context.dev, and use the official SDK. Include failed checks as well as changes, and snapshot-test the email HTML.
Uses: Monitors. Install the Context.dev MCP if you haven’t already.
Upload pipeline to Markdown
Add a file upload endpoint to [FastAPI or Express] that sends PDF, DOCX, XLSX, and PPTX files to Context.dev Parse and stores the Markdown for retrieval. Read the Parse docs at https://docs.context.dev, including PDFs and OCR, and use the official SDK. Enforce [max file size], reject unsupported types before calling the API, and test with one file of each type.
Uses: Parse Files. Install the Context.dev MCP if you haven’t already.
Invoice parsing worker
Build a [Python] worker that converts uploaded invoices to Markdown with Context.dev Parse, using OCR for scans, then maps vendor, date, line items, and total into [schema] with my existing [LLM client]. Read the Parse docs at https://docs.context.dev and use the official SDK. Send invoices with a missing or mismatched total to manual review, and test with [two sample invoices].
Uses: Parse Files. Install the Context.dev MCP if you haven’t already.
Resume upload prefill
In my [Rails] app, convert uploaded resumes (PDF or DOCX) to Markdown with Context.dev Parse in a background job, then prefill name, contact details, work history, and skills as fields the recruiter can edit. Read the Ruby SDK and Parse docs at https://docs.context.dev. Keep the original file, and add a system test for the upload-to-prefill flow.
Uses: Parse Files. Install the Context.dev MCP if you haven’t already.
Enrich signups into my CRM
When someone signs up in [app], enrich their work email with Context.dev People Enrich and Brand, then sync title, company, and logo to [CRM]. Read both docs pages at https://docs.context.dev and use the official SDK in a background job. Skip free email domains, write fields only above [match score], never overwrite values a person edited, and test each branch.
Uses: People Enrich, Brand. Install the Context.dev MCP if you haven’t already.
Company search box
Add a search box to [internal tool] that finds companies from a plain-language query like “[example query]” with Context.dev Company Search, showing name, domain, and logo. Read the Company Search API reference at https://docs.context.dev and call it from the server exactly as documented. Show an empty state when nothing matches, and add tests for results, no results, and errors.
Uses: Company Search, Brand. Install the Context.dev MCP if you haven’t already.
Prospect list script
Write a [Python] script that runs Context.dev People Search for “[role at company type in region]”, dedupes the results, and writes a CSV ready for [CRM] import. Read the People Search and Credits docs at https://docs.context.dev and use the official SDK. Stop at [N] results, and add a --dry-run flag that prints the query and estimated credits.
Uses: People Search. Install the Context.dev MCP if you haven’t already.
Handle rate limits and credit errors
Audit every Context.dev call in [repo path] and add one shared policy for 429s and billing errors. Read the Rate limits and SDK docs at https://docs.context.dev: honor Retry-After with jitter, size worker pools to my plan’s concurrency limit, set explicit deadlines, and send out-of-credit errors to [alert channel] instead of retrying. Add tests that simulate 429, timeout, and credit errors.
Uses: Scrape, Web Search. Install the Context.dev MCP if you haven’t already.
Tag usage by feature
Add tags to every Context.dev request in [repo path] naming the feature that made it, such as [signup-enrich or docs-ingest]. Read the Usage and request logs docs at https://docs.context.dev, then add an admin page in [framework] showing the credit balance, next refill, and daily credits for [30 days]. Add a test that fails when a call is missing a tag.
Uses: Scrape, Web Search, Brand. Install the Context.dev MCP if you haven’t already.
Mocked client test suite
Write tests for the Context.dev integration in [module path] with [Vitest, pytest, RSpec, or go test] and a mocked client, covering success, empty results, partial results, timeouts, 429s, and invalid keys. Read the Troubleshooting and Timeouts docs at https://docs.context.dev to match real error shapes. Keep CI off the live API, add one opt-in live smoke test gated by an environment variable, and show the passing run.
Uses: Scrape, Web Search. Install the Context.dev MCP if you haven’t already.
Go scraping worker pool
Build a Go worker that reads URLs from [queue], scrapes each to Markdown with the official Context.dev Go SDK, and writes results to [storage]. Read the Go SDK and Rate limits docs at https://docs.context.dev, size the pool to my concurrency limit, use context deadlines, and retry 429s with jitter. Done means go test -race passes and the README lists every environment variable.
Uses: Scrape. Install the Context.dev MCP if you haven’t already.
Browser extension with a key proxy
Build a [Chrome extension] that shows the brand profile and recent news for the site in the current tab. Route every Context.dev call through my [backend] so the API key never ships in the extension, and use the official SDK there after reading the Brand and News docs at https://docs.context.dev. Rate-limit the proxy per user and test it with a mocked client.
Uses: Brand, News Search. Install the Context.dev MCP if you haven’t already.
How to use these prompts
Install the Context.dev MCP
Add the Context.dev MCP server to Claude, Cursor, or another agent, or install the ChatGPT app. This gives the assistant live web search, scraping, and data tools.
Pick a prompt
Copy it, or open it straight in Claude or ChatGPT. Every copied prompt tells the assistant to use Context.dev, links the MCP install page, and asks it to cite sources.
Fill in the brackets
Replace every [bracket] with your details, such as a company domain, a competitor, or a file, then run it.
Context APIs behind these prompts
The tools your assistant calls when it runs these prompts.
Coding prompt FAQ
What are Claude Code prompts?
Instructions you paste into Claude Code, Cursor, Codex, or another coding agent to get a specific change made in your repository. Each prompt here adds a Context.dev feature, such as a scraper service, a search tool for an AI agent, or a signed webhook handler, and says what “done” looks like so the agent can check its own work.
What do I need before running these prompts?
A repository the agent can edit and a Context.dev API key stored in an environment variable, never in the prompt or the code. Replace the bracketed placeholders with your framework, file paths, and data, then let the agent plan, write, and test the change.
Why connect the Context.dev MCP to my coding agent?
The prompts tell the agent to read the Context.dev docs and use the official SDK for TypeScript, Python, Ruby, Go, or PHP. With the Context.dev MCP connected, it can also read the live docs and make real test calls, so it checks request and response shapes against the API instead of guessing from training data.
How do I install the Context.dev MCP in Claude or ChatGPT?
Add the Context.dev MCP server to Claude, Cursor, or any MCP client with the MCP setup guide, or install the Context app in ChatGPT for web search and page reading. Then paste a prompt and the assistant picks the right Context tools.
Do these prompts work without Context?
They run, but without live web tools the assistant answers from its training data and can’t open the pages, files, or searches the prompt asks for. Expect older information and more guesses.
More prompt categories
- GTM promptsICP research, positioning, pricing, launches, and market maps.65 prompts
- Lead Generation promptsProspect lists, decision makers, buying signals, and enrichment.48 prompts
- Cold Email promptsResearched first lines, sequences, follow-ups, and reply handling.36 prompts
- Web Scraping promptsExtract products, prices, tables, listings, and whole sites.46 prompts
- Web Search promptsDeep research, fact-checking, sourcing, and comparisons with citations.33 prompts
- File Parsing promptsPDFs, contracts, invoices, spreadsheets, slides, and scans.28 prompts
- News promptsCompany news, competitor alerts, briefings, and media monitoring.31 prompts
- Ad Copy promptsAd copy, hooks, audiences, landing pages, and competitor messaging.27 prompts
- Creative & Design promptsOn-brand image prompts, creative briefs, mockups, and brand kits.26 prompts
- Competitor Analysis promptsPricing, features, reviews, hiring, and change tracking.41 prompts
- SEO promptsSite audits, content briefs, search results research, and internal links.38 prompts
- Recruiting promptsCandidate sourcing, research, pay benchmarks, and outreach.29 prompts
Start building with live web context.
Scrape, search, and research the web with one API. Bring the results straight into your product.