AI agent for ux researchers
Study Plan Feasibility Agent
Produce a study plan that answers the research questions within the real deadline and budget.
What it does
A study plan often promises more than the time or budget allows. This agent starts from the research questions and drafts a method and sample size. It then estimates recruiting time, session hours, analysis days and incentive cost, and compares the total with your deadline and budget. If the plan is too big, it adjusts the scope: fewer participants, a shorter session, or a remote method. After every change it recalculates the whole plan to confirm the questions are still answered. You approve the plan before it is shared. Edge case: the study needs eight rare-role participants, and the agent shows recruiting would take 5 weeks and proposes a mixed sample.
How it works
Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.
Read the steps as a list
- Research request is accepted
- Read the questions, deadline and budget
- Choose a method and sample size
- Estimate recruiting time, session hours and analysis effort
- Compare the totals with the deadline and budget
- Does the plan fit time and budget?If not: Note how far over it is and which part is largest. Back to step 4.
- Adjust scope: sample, session length or method
- Recalculate the whole plan
- Does the smaller plan still answer every research question?If not: Restore the part that is needed and cut a different one. Back to step 4.
- Researcher approves the planThe agent waits here for your OK.
- Feasible study plan with assumptions
How it decides
It starts from the best method and shrinks scope until time and budget fit, never dropping a research question without approval.
- Reduce recruiting scope before cutting analysis time
- Never drop a research question without approval
- Add a 15% time buffer for no-shows (default)
- Rare-role recruits are estimated by past lead times
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Deadline and budget
- Time buffer (default 15%)
- Methods allowed
- Incentive rate
- Hours per interview analysis (default 3)
What keeps you in control
It always asks you first
- The final plan
- Any dropped research question
Hard limits
- Never commits budget
- States all estimates as estimates
- Never drops a question silently
It stops when
- Done: plan fits and answers every question
- Stop: no fit; researcher decides to change deadline or questions
Set it up
We guide you through the set-up, step by step
Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.
- One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
- The agent then walks you through connecting your own data, one source at a time
- A downloadable copy with the flow chart, the rules and the full guide