Twitter Agent

Find and analyze tweets by keyword, URL, author, list, or thread. Filter by language, media type, engagement, date range, or location. Get a clean table of tweets with authors, links, media, and counts; then refine the table and generate new columns with AI.

Skills

Find Tweets

Search X by keywords, URLs, handles, or conversation IDs. Filter by engagement (retweets/favorites/replies), dates, language, location, media type (images/videos/quotes), user verification status, and author/reply/mention relationships. Sort by Top or Latest. Return 1-10,000 results.

Examples

Find 100 tweets asking 'anyone know' or 'looking for' about fintech tools from the last month.

Find tweets from the last 30 days mentioning our competitor '@competitorhandle' with at least 10 likes, max 200 results.

Find 500 tweets from verified users mentioning 'stealth startup' or 'building in public' with at least 20 retweets from the last month.

Find 1000 tweets mentioning 'hiring a' and 'marketing agency' from the last 14 days, English only.

Find tweets mentioning 'open to opportunities' or 'looking for new role' from software engineers in New York from the last 7 days.

Find 200 tweets mentioning 'need someone to' and 'web scraping' or 'data collection' from the last month, sorted by Latest.

Find 2000 tweets from verified users in Germany, France, and Spain discussing 'supply chain' or 'logistics' from the last quarter.

Filter Table

Use AI to intelligently filter tweets based on nuanced intent, sentiment, credibility, and context that simple parameters cannot capture. Analyze tweet text, author bios, and engagement patterns to identify genuine opportunities versus noise.

Examples

Keep only tweets where the author appears to be genuinely seeking solution recommendations (not promoting their own product).

Filter for tweets that express genuine pain points or feature requests about competitors (exclude generic praise or complaints).

Keep only tweets about startups that mention concrete traction indicators (revenue, users, funding) rather than just ideas or announcements.

Remove tweets from individuals who appear to be job-seekers or students; keep only those from established businesses with buying authority.

Filter for tweets from people whose bios suggest they have relevant professional experience (exclude students, bootcamp graduates, or career switchers).

Keep only requests that explicitly mention budget, payment, or hiring (exclude people asking for free help or learning resources).

Filter for tweets from authors whose bios indicate they work at enterprise companies or hold decision-making roles (exclude news aggregators or hobbyists).

Generate Table

Use AI to extract, infer, and generate structured insights from unstructured tweet data. Create new columns by analyzing text sentiment, classifying user intent, extracting implied information, scoring opportunity quality, and crafting personalized outreach.

Examples

Infer what problem they're trying to solve from the context, rate urgency level as High, Medium, or Low, suggest what type of person I should interview, and draft a starter question.

Identify any competitor pain points mentioned, infer missing features they want, score user sentiment from 1-10, and flag whether it's a good opportunity to reach out with reasoning.

Extract the startup name if mentioned, classify the industry vertical, infer their stage (Seed, Series A, etc.), identify what traction signal they're showing (funding/growth/product), and rate follow-up priority from 1-10.

Pull the company name from their bio or tweet, identify their industry sector, estimate company size (Startup/SMB/Enterprise), summarize their pain point, score lead quality from 1-10, and suggest a personalized pitch angle.

Infer seniority level from their bio or tweet, extract their primary tech stack, determine location preference (Remote/Hybrid/specific city), gauge availability (Immediate/Exploring/Passive), and suggest which outreach template to use.

Classify the project type, rate technical complexity as Low, Medium, or High, estimate hours required, suggest a price range, list required skills, and outline key points for the proposal.

Extract company name from their bio, identify job title and role, infer their department (Supply Chain, Ops, etc.), categorize their data need, identify market or region focus, score enterprise readiness from 1-10, and suggest a custom research angle.