ContextOverflow
Describe what your AI keeps getting wrong — get the named technique that fixes it. Learn it, teach it to your AI, get better together. Free, no login.
What’s going wrong?
Say it the way you’d say it to a colleague — “it keeps making things up” is enough. No jargon needed.
Questions asked here are collected anonymously — no account, no identity — and used to grow the library and understand how people and AI think together.
Or pick the complaint that sounds most like yours
| The problem, as you experience it | Where to look |
|---|---|
| “My AI forgets everything between sessions” | Lost the thread |
| “I’m outsourcing my thinking and getting dumber” | Doing my thinking |
| “My AI states things that turn out to be false” | Confidently wrong |
| “My AI tells me I’m right even when I’m not” | Agrees with everything |
| “The AI stalls instead of acting” | Stalls instead of acting |
| “I ask something simple and get a wall of text” | Bloated answers |
| “It starts producing before it understands the task” | Starting blind |
| “The task is too big and it (or I) can’t hold it” | Problem too big |
Every technique page gives you the problem, why it happens, how to fix it yourself, and how to have your AI assistant fix it too — ending in a worked prompt you’ll know how to build, not just paste.
One more thing, and it’s the unusual part: your AI assistant can learn these same techniques, under the same names. You read Self-Ask Before Delegating here; mid-task, your assistant says “breaking this into its sub-questions before answering” — and you know exactly what it’s doing. That’s the premise of this whole place: not a smarter AI, not a dependent human — the pair, thinking better together.
For your AI assistant — connect it once
ContextOverflow speaks MCP — a plug-in standard your AI assistant can install. Point it at this address and it gets the same techniques you just learned:
Claude Code
claude mcp add --transport http contextoverflow https://contextoverflow.org/mcp
claude.ai / Claude Desktop
Settings → Connectors → Add custom connector → paste
https://contextoverflow.org/mcp. No OAuth fields needed.
Cursor
Add to ~/.cursor/mcp.json:
{ "mcpServers": { "contextoverflow": { "url": "https://contextoverflow.org/mcp" } } }
VS Code (Copilot agent mode)
Add to mcp.json:
{ "servers": { "contextoverflow": { "type": "http", "url": "https://contextoverflow.org/mcp" } } }
OpenAI Responses API
{ "type": "mcp", "server_label": "contextoverflow", "server_url": "https://contextoverflow.org/mcp" }
Anything stdio-only
npx mcp-remote https://contextoverflow.org/mcp
Full details for every client are on the connect page. From then on it narrates: it tells you which technique it’s running, in the same words you learned here.