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 →Redis MCP
Connects MCP clients to Redis instances for key inspection, pub/sub monitoring, and data operations so agents can reason about cached state alongside code changes.
Datadog MCP
Exposes Datadog metrics, logs, and dashboards to MCP clients so agents can read application performance and error rates while working in the editor.
Neon MCP
Links MCP clients to Neon serverless Postgres for schema inspection, branch management, and query execution—bringing database context into the agent workflow without leaving the editor.
Linear MCP
Connects MCP clients to Linear workspaces for issue tracking, project status, and team velocity data—giving coding agents visibility into sprint context without opening a browser.
Agent Protocol MCP
Implements the Agent Protocol standard so MCP clients can coordinate with external agent frameworks using a shared task, step, and artifact schema—useful when you want Claude or Codex to hand off to a specialized agent.
OpenAPI MCP
Loads OpenAPI specs and exposes API endpoint inspection, parameter validation, and example generation to MCP clients so agents can reason about REST surfaces without leaving the codebase.
Skills to try
More →Agentic workflow design
Structures multi-step agent tasks with clear inputs, outputs, fallbacks, and handoff protocols so agents reliably complete complex workflows instead of stopping at the first blocker.
Codebase indexing
Builds and maintains semantic indexes of your codebase so agents can retrieve relevant context — file relationships, symbol usage, historical decisions — without re-parsing everything on every query.
AI product requirement writing
Writes PRDs that AI agents can act on reliably — explicit about constraints, edge cases, and acceptance criteria so the gap between what you mean and what the agent builds is minimal.
Security review for AI-generated code
Reviews AI-generated code for injection risks, credential exposure, dependency vulnerabilities, and access control gaps—catches what agents miss when they optimize for functionality over safety.
Fine-tuning preparation
Curates,清洗, and formats training datasets for fine-tuning—deduplication, quality filtering, and output formatting—so the resulting model actually improves on your target behavior.
Evaluation and benchmarking
Builds eval suites with ground-truth answers, automated scoring, and regression detection so you know whether model or prompt changes actually improve outcomes before shipping.