> ## Documentation Index
> Fetch the complete documentation index at: https://clearskies.cc/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Product Feature Requests

> The features and gaps customers bring up, ranked by the revenue behind them. Not a wishlist, a weighted read on what is actually costing you deals.

Feature requests reach product through whoever is loudest. A rep escalates on Slack, a CS manager forwards an email, an account with a strong relationship gets heard twice. What nobody has is the whole set with revenue attached: which gaps came up, in how many accounts, and how much pipeline or renewal value sits behind each. Product feature requests reads the requests out of the conversations they were made in and ranks them by what they are worth.

## Data Sources

| Category         | Required | Recommended |
| :--------------- | :------- | :---------- |
| Calls            | ✓        |             |
| CRM              | ✓        |             |
| Email + Calendar |          | ✓           |
| Support tickets  |          | ✓           |
| Issue tracking   |          | ✓           |

**Starter** (required only): the requests and gaps raised on calls, grouped, with the accounts and deal values behind each.

**Full** (required + recommended): the same, plus requests that arrived by email or as support tickets, and whether each one already exists in your issue tracker. The last part is what makes the report actionable rather than another list product has to reconcile by hand.

CRM is required, not recommended. A feature request without revenue attached is a wishlist, and the ranking is the entire point.

See the [Context Graph](/docs/unifying-gtm-data/customer-context-graph) for how each source feeds the report.

### Choose your path

| Path                       | Best for                                                                 | Output is delivered                   |
| :------------------------- | :----------------------------------------------------------------------- | :------------------------------------ |
| Build in Clearskies        | Teams who want a standing read for product review                        | To Slack DMs or channels              |
| Build in Claude or ChatGPT | Product and leaders asking about one feature, one account, or one window | In the Claude or ChatGPT conversation |

## Build in Clearskies

Build the workflow once and product gets the weighted read on a cadence rather than a stream of escalations.

### The Workflow

In the Clearskies app, open the workflow builder and describe what you want in plain language:

```text theme={null}
Every Monday at 8am, review the customer calls and emails from the
last 14 days. Identify the features and capability gaps customers asked
about or said were missing. Group them, and for each one list the accounts
that raised it and the open deal or renewal value behind those accounts.
Rank by total value. Post the report to the #product channel.
```

The app configures the schedule, the sources in scope, and the destination.

Scheduled workflows have no meeting context, so the conversations come from a record lookup over a date range. Record lookups cap at 100 records per step, so scope the window or the segment rather than sweeping everything.

A weekly run over a rolling two-week window is a good starting point. The window is long enough to see whether two accounts asked for the same thing, and running it weekly means a request reaches product while the deal is still live.

### Deploy to Slack

Once published, product gets the ranked read:

```text theme={null}
Feature Requests — Aug 1 to Aug 14
48 calls and 74 email threads reviewed · 17 accounts

Ranked by revenue behind the request

1. Scheduled report delivery to a distribution list — $296K
   4 accounts. Raised as a blocker in 2 of them. The pattern is consistent:
   buyers want a weekly report a VP reads without an analyst rebuilding it,
   and per-user delivery is what breaks that.
   Already tracked: yes, one open issue.

2. SSO and SCIM provisioning — $210K
   3 accounts, all enterprise. In one deal it is a procurement requirement
   rather than a preference, and that deal is in commit.
   Already tracked: yes.

3. Run without email access — $155K
   3 accounts, all regulated. New in this window. Framed as a compliance
   constraint, not a feature preference, which means a workaround may
   matter more than a roadmap item.
   Already tracked: no.

4. Historical backfill beyond the current window — $84K
   2 accounts. Both raised it during evaluation, neither called it a
   blocker.
   Already tracked: yes.

Raised once, no revenue attached yet
Custom field mapping on import (1 account, no open deal). Bulk export
(1 account, renewal in Q1).

Worth noticing
Requests 1 and 3 both come from the same underlying constraint: customers
wanting the output to reach people who are not users of the product.
```

### Customize the rollout

* Set the cadence to match your product review rhythm
* Weight by open pipeline, by renewal value at risk, by account tier, or by count of accounts rather than dollars
* Group against your existing roadmap themes so the report reconciles with what product already tracks
* Separate blockers from preferences, since a request that lost a deal is a different item than one that was nice to have
* Route it to product, to a leadership channel, or both
* Chain it with [churn and renewal risk](/docs/use-cases/churn-and-renewal-risk) so gaps raised by at-risk accounts are visible as retention risk, not just roadmap input

## Build in Claude or ChatGPT

The better path for the specific question, which is how product usually asks. Someone is scoping a feature and wants to know exactly who asked for it and what they said.

### The Prompt

Open Claude or ChatGPT with the Clearskies MCP connected and paste this (or modify to your needs).

```text theme={null}
Using the Clearskies Context Graph, review the feature requests and gaps
customers raised in the last 90 days.

For each one:
- What they asked for, in their words
- Which accounts raised it, and the open deal or renewal value behind them
- Whether it was framed as a blocker or a preference
- Whether it came up before or after they saw the product

Rank by total revenue behind the request. Separate blockers from
preferences.

Quote customers directly. Do not translate a request into our roadmap
vocabulary, because that hides whether two accounts asked for the same
thing or two different things.
```

### Make it yours

* Add `Show me every quote about scheduled report delivery` to go from the ranking to the raw material for a spec.
* Add `Which customers mentioned this in the last week` for the standing question product asks most.
* Add `Did we win or lose the deals where this was a blocker` to size the cost of not building it.
* Add `Which of these are already in our issue tracker` when Linear or Jira is connected.

<Tip>
  Want this packaged for your team? [**Reach out**](mailto:support@clearskies.cc) and we'll help you customize this into a skill for your workflow.
</Tip>

## The Plugin

**Ready to make this part of your team's workflow?** We'll set up the Clearskies plugin with you. Clearskies workflows, Claude skills, all tailored to how your team works.

[**Book 15 minutes →**](https://calendly.com/pouyan/new-meeting)

## Next steps

1. [Sign in to Clearskies](https://app.clearskies.cc/)
2. Connect your data sources
3. Get your [Clearskies MCP server](/docs/building-with-clearskies/mcp-server) and try with [Claude](/docs/building-with-clearskies/mcp-clients/claude) or [ChatGPT](/docs/building-with-clearskies/mcp-clients/chatgpt)