hermes

Get feedback from your first users

Plans a lightweight routine for an early product to learn from its first users - founder calls, in-product asks, a shared channel, what to ask, what to watch and how often.

context

You advise early-stage teams on learning from their first users. With tens or a few hundred users, every user can be known by name, and the founder or product lead should talk to them directly. Early feedback is distorted in predictable ways: friends and early fans are polite, loud users dominate shared channels, and feature requests describe solutions rather than problems. Behaviour is more honest than opinion: who comes back each week, who invites colleagues, who would be upset if the product disappeared. A common structured signal once there are roughly 40 or more engaged users is the "How would you feel if you could no longer use this?" question, read by segment rather than as one number. The routine has to be light enough to keep doing every week while also building the product.

Product and stage:

product stage

Only if [CONSTRAINTS] is given:

Constraints:

constraints given

task
  1. Say who to hear from first: the most active users, users who stopped, and users who match the intended customer. Name how to find each group with the data an early product usually has. Warn about over-weighting friends, investors and non-target users.
  2. Choose the channels for this stage (one-to-one calls, watching users use the product, a one-question in-product ask, a shared chat channel or group, replies to a short update email) with the purpose and the main risk of each.
  3. Lay out a weekly routine that fits the time available: how many conversations, when to review usage, when the team reads all feedback together, and a monthly look at retention by cohort.
  4. Write what to ask: five or six open questions about real recent use, the problem behind it, alternatives they use, and what nearly stopped them; plus the "no longer use" question and when to start asking it.
  5. List what to watch in behaviour: return visits, key action frequency, invites, drop-off points, and what to watch for in sessions.
  6. Give a simple logging method: one shared sheet or board with fields (user, date, said, observed, problem, request, severity) and a weekly tally of repeated problems.
  7. Say when to change approach: signs the routine is not working (same people every time, only requests, no behavioural follow-up) and the point where you need more structure (a feedback tool, tagging, a beta programme).
  8. Remind the team to tell users what changed because of their feedback, and suggest how.
constraints
  • Keep the routine within the stated time; if none was given, assume under three hours a week and say so.
  • Do not present early user counts as statistically meaningful; talk in names and patterns, not percentages, below about 40 users.
  • No incentive schemes or tooling purchases unless clearly needed.
  • Do not invent user numbers or results.
output format

Who to hear from

Bullets.

Channels

A table: channel | purpose | risk.

Weekly routine

A table: day or frequency | activity | time.

What to ask

Numbered questions.

What to watch

Bullets.

Logging

The fields and the weekly tally.

When to change approach

Bullets.

1 required value still a placeholder; the assistant will ask for it.

details

kind
Prompt: a task you run by name to get one finished thing back
domain
Product management
category
User feedback
level
Beginner
depth
Start here
made for
Founder / business owner, Product manager
risk
read-only
version
v1.0.0 · incubating
reviewed
2026-10-11
works in
Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Antigravity, OpenCode, Windsurf, Zed, Continue, AGENTS.md, ChatGPT, claude.ai

Edit on GitHubReport a problem

use in

Hodios CLI
npx @hermes-hq/hodios install get-feedback-from-first-users --target claude-code

This entry is in the full catalog, not the curated set the skills installer and plugins carry, so install it with the Hodios CLI.

pairs well with

All of User feedback
PromptUser feedback

Plan a beta program

Plans a beta or early-access programme with learning goals, recruitment and screening, feedback channels, a weekly cadence, participant communications and exit criteria for general availability.

plan-beta-program
PromptUser feedback

Design an in-product survey

Designs an in-product survey or micro-poll around the one question that matters, with the trigger moment, sampling, response options, bias checks and how the answers feed decisions.

design-in-product-survey
PromptProduct discovery

Write a customer interview guide

Writes a discovery interview guide that asks about specific past behaviour instead of opinions or hypotheticals, with timed sections, follow-up probes and a check for leading questions.

write-customer-interview-guide
PromptUser feedback

Close the feedback loop

Writes personal replies to users whose feature request shipped, partly shipped or was declined, segmented by request, with honest reasons, how to use it or alternatives, and next steps.

close-feedback-loop
PromptUser feedback

Analyse cancellation feedback

Analyses cancellation reasons and exit-survey comments into churn themes with counts and quotes, separates preventable from unavoidable churn, and proposes fair save offers and fixes to test.

analyze-cancellation-feedback
PromptUser feedback

Analyze user feedback

Clusters user feedback, reviews or NPS comments into themes with counts, sentiment, representative verbatim quotes and product implications, and states what the sample can and cannot show.

analyze-user-feedback