Popular AI tools
View all →NotebookLM
NotebookLM ingests PDFs, docs, and slides you provide, answers with inline references, and can turn dense material into spoken audio overviews—aimed at students, researchers, and analysts who need traceability more than generic chat.
Bolt
Bolt targets rapid UI shells, marketing sites, and mobile prototypes with hosting and GitHub sync—use it when speed matters more than bespoke backend complexity.
Gemini
Gemini pairs conversational answers with strong Google Workspace and Search adjacency—useful when your prompts mix text, images, and quick research across languages.
GitHub Copilot
Copilot meets developers where PRs and issues already live—inline suggestions, workspace-aware chat, and agent flows that can touch multiple files inside VS Code or JetBrains.
Replit Agent
Describe a product, iterate in the design canvas, and let Replit Agent scaffold code, dependencies, and deploys—popular with students and indie hackers validating ideas in hours.
ChatGPT
ChatGPT spans everyday Q&A, long-form writing, code explanation, and image or file inputs—plus GPTs and connectors when you need repeatable workflows instead of one-off chats.
Claude
Claude shines when you need to load large PDFs, compare versions, or iterate on nuanced prose—team features and projects help keep institutional knowledge in one thread.
DeepSeek
DeepSeek is a go-to when you want chain-of-thought style answers, math-heavy prompts, or repository-scale coding help without burning premium credits.
MCP picks
More →Netlify MCP
Exposes Netlify CLI and API operations to MCP clients so agents can scaffold sites, wire build settings, trigger deploys, and inspect domains from the same editor session.
Sentry MCP
Connects coding assistants to Sentry issues, stack traces, releases, and performance data through a hosted MCP endpoint with OAuth—so triage starts from real error context instead of a pasted message string.
Vercel MCP
Hosts a remote MCP endpoint with OAuth so agents can search Vercel docs, inspect projects, and read deployment logs using the same account you already trust for previews—no more pasting dashboard screenshots to explain an incident.
Stripe MCP
Exposes Stripe objects—customers, invoices, subscriptions, and payouts—to MCP clients so finance and support copilots can look up live billing state with explicit scopes instead of exporting CSVs by hand.
Docker MCP
Lets agents inspect containers, images, compose projects, and logs through Docker’s MCP integration—so debugging local stacks does not require copy-pasting docker ps output into chat.
MongoDB MCP
Lets assistants run explain plans, inspect collections, and draft aggregation pipelines against MongoDB clusters you authorize—useful when debugging document models and slow queries without pasting dumps by hand.
Skills to try
More →Canary rollouts
Ships a small percentage of traffic to a new build first, watches error budgets and latency, then widens or rolls back—so surprises stay small when agents touch deploy pipelines.
Structured logging
Defines a small set of log fields (request id, user id, feature flag, latency bucket) so production debugging does not depend on grep across inconsistent printf strings.
Threat modeling
Walks data flows and trust boundaries before you ship: who can call what, which secrets move where, and which failures become customer-visible—so security reviews start with diagrams instead of last-minute checklist panic.
Safe refactoring
Splits refactors into small, test-backed steps—rename, extract, move—so behavior stays pinned while structure improves.
Incident response
Structures on-call work: timeline, blast radius, mitigations, and customer comms—so fixes stay coordinated instead of chaotic thread hopping.
Humanizer
Removes Wikipedia-documented “AI writing” tells—significance inflation, -ing fluff, em-dash stacks, chatbot closers—and runs a final “still obviously AI?” pass before shipping prose.