ClosedLoop AI
Sign in Start free Open app →

Product context in Claude Code

Customer evidence, inside Claude Code.

Claude codes better when it understands the real user problem, not just the ticket. One command to install, then ask Claude what to build, which bugs matter, and what customers are saying.

$ curl -fsSL https://closedloop.sh/install | bash
Read docs
  • Claude Code
  • One-line install
  • Free

What it looks like

Type "implement", get the full customer picture. Customer evidence is auto-injected on feature prompts: Claude sees insight counts, deal blockers, and verbatim quotes before it writes a line of code.

Claude Code ClosedLoop AI connected

>implement the data export feature

ClosedLoop AI / Customer evidence: data export

Role-specific export templates. 6 insights "Manual reporting takes ~3h/week, hundreds of rows nobody reads"
Background export for large datasets. 4 insights Deal blocker "We export 50k rows and it just times out"
CSV export with filters. 8 insights "I just need to export what I'm looking at, not the whole table"

18 insights from 12 customers. The main pain is large datasets timing out and no way to filter before exporting.

Background async export with download link
CSV with current filters applied (8 asked for this)
Progress indicator: "I had no idea if it was running"
Skip Excel/PDF for now, only 2 mentions

Want me to start with the background job implementation?

What you can ask Claude

Hundreds of decisions per feature: API design, edge cases, what to ship now versus later. Claude makes better calls when it knows what users actually said.

Implement

Build with context

Tell Claude to build a feature. It pulls real user pain, workarounds, and expected behavior, then writes code that solves the problem.

"implement the Slack integration for feedback"
/closedloop:prd

Generate a PRD

Get a full product requirements doc backed by real customer quotes, insight counts, and workarounds. Not opinions, evidence.

/closedloop:prd data export
/closedloop:spec

Write a tech spec

Claude searches your codebase, pulls customer evidence, and writes a design doc grounded in both code patterns and user needs.

/closedloop:spec Slack integration
Scope

Scope v1 from evidence

Claude sees which features have 12 insights and which have 1. Your v1 includes what users asked for and skips what they didn't.

"what's the minimum scope for export?"
Auto-inject

Evidence on every feature prompt

Type "implement" or "build" and customer evidence appears automatically. No extra step. Claude already knows the user problem.

fires automatically on feature prompts
Search

Search your feedback

Ask Claude about any topic and it searches your product insights: pain, workarounds, severity, deal blockers. Not a Jira summary.

"what are customers saying about search?"

Setup2 minutes

Up and running in minutes

From zero to exploring product insights with Claude in under 2 minutes.

  1. Get your API key

    Sign in at app.closedloop.sh/api-keys and copy your key. Free plan works for personal projects.

  2. Run the installer

    One command adds ClosedLoop AI to Claude Code globally, works across all your projects.

    $ curl -fsSL https://closedloop.sh/install | bash

  3. Manual config (optional)

    If you'd rather edit your Claude Code config directly, drop this into ~/.config/claude/mcp_servers.json:

    jsonMCP client config
    {
  "mcpServers": {
    "closedloop": {
      "url": "https://mcp.closedloop.sh",
      "transport": "http",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

  4. Ask Claude

    Restart Claude Code and start exploring your product insights and opportunities. Claude has read access to your whole workspace.

Keep it secret

Your API key carries your workspace access. Store it in your config or an environment variable, never in a repository. Rotate it from settings the moment it may be exposed.

Start building from customer evidence