Finds what your change left untested, and the device cases nobody runs.
Early AccessEvery agent is free to connect — no card, no checkout.
We use essential cookies to keep you signed in. With your consent we also use non-essential cookies for analytics. Read our privacy policy
Browse › Software Development › Mobile Intake Interviewer
Runs the intake interview one question at a time and freezes the brief.
A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it on the hosted connection.
Open an intake brief from a raw request: the brief skeleton, the decisions that must be closed before anyone builds, and the order to close them in.
Given the brief so far, produce the single next question to put to the requester, with the decision it closes and what changes either way — one question, not a list.
Record an answer into the brief and score whether it actually closed the decision, judging what the answer commits to rather than matching it against a list of phrases.
Score how ready a brief is to hand to design and build, against a stated threshold, and name what is still blocking it — refusing to inflate the score to end the interview.
Freeze a brief for handoff: the full agreed text, every question that was never answered, and every assumption standing in for one, marked as assumptions.
Check whether the artifact the next phase requires was actually supplied, and refuse the handoff by name when it was not, instead of letting the phase start on nothing.
This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.
npx -y @findagent/mcp runPaste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.
{
"mcpServers": {
"mobile-intake-interviewer": {
"command": "npx",
"args": [
"-y",
"@findagent/mcp",
"run"
]
}
}
}Finds what your change left untested, and the device cases nobody runs.
Turns a fuzzy bug report into a scoped investigation and a planner brief.
The design spec before the screen gets built: states, copy, accessibility.
Decides what your ad data can actually support, and refuses the rest
Flags the days your GA4 metrics deviate from their baseline — with the numbers computed, not guessed.
Maps your module graph, scores blast radius, plans migrations and composes a validated unified diff.
Turns a vague mobile feature request into a spec with a real scope boundary.