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

# Cookbook

> End-to-end recipes that stitch several Squad features together, from raw feedback to a shipped decision.

<img className="block dark:hidden" src="https://mintcdn.com/squad/O_98Wy8uNjlYcgBb/images/hero-cookbook-light.png?fit=max&auto=format&n=O_98Wy8uNjlYcgBb&q=85&s=d0e38786c48569c675b63cc80430cccf" alt="Cookbook" width="2400" height="720" data-path="images/hero-cookbook-light.png" />

<img className="hidden dark:block" src="https://mintcdn.com/squad/O_98Wy8uNjlYcgBb/images/hero-cookbook-dark.png?fit=max&auto=format&n=O_98Wy8uNjlYcgBb&q=85&s=8aa140f7d591df7ba534669c48a66ccb" alt="Cookbook" width="2400" height="720" data-path="images/hero-cookbook-dark.png" />

Recipes that stitch several features together. Each per-feature page has its own focused cookbook;
these are the end-to-end journeys that cross the whole product. They assume you've connected at
least one source. If not, start with the [Quickstart](/quickstart) and
[Integrations](/integrations).

<CardGroup cols={2}>
  <Card title="Raw feedback to a shipped decision" icon="workflow" href="/cookbook#from-raw-feedback-to-a-shipped-decision">
    The full chain, start to finish.
  </Card>

  <Card title="Your weekly triage routine" icon="calendar-check" href="/cookbook#your-weekly-triage-routine">
    A repeatable loop built around the dashboard.
  </Card>

  <Card title="Investigate a spike in complaints" icon="trending-up" href="/cookbook#investigate-a-spike-in-complaints">
    Find the theme behind a jump in pain-point feedback.
  </Card>

  <Card title="Turn a quarterly goal into tracked work" icon="trophy" href="/cookbook#turn-a-quarterly-goal-into-tracked-work">
    Goal, evidence, actions, owners.
  </Card>

  <Card title="Let an agent watch something for you" icon="bot" href="/cookbook#let-an-agent-watch-something-for-you">
    Configure a trigger, get a report each run.
  </Card>

  <Card title="Trace any decision back to its evidence" icon="git-branch" href="/cookbook#trace-any-decision-back-to-its-evidence">
    Follow a claim down to the original quote.
  </Card>

  <Card title="Bring your own data over the API" icon="code" href="/cookbook#bring-your-own-data-over-the-api">
    POST feedback from a helpdesk, survey tool, or app.
  </Card>

  <Card title="See who changed what" icon="activity" href="/cookbook#see-who-changed-what">
    Reconstruct how something got to where it is.
  </Card>
</CardGroup>

## From raw feedback to a shipped decision

The full chain, start to finish.

<Steps>
  <Step title="Get feedback flowing" icon="plug">
    Connect a source (see [Integrations](/integrations)) or pipe data in over the
    ingestion API. Feedback starts arriving as **signals** under
    **Insights → Data Signals** ([Data signals](/signals)).
  </Step>

  <Step title="Squad groups signals into clusters" icon="layers">
    Related signals become **clusters**, themes like "slow search" or "requests for
    SSO" ([Signal clusters](/signal-clusters)).
  </Step>

  <Step title="A strong theme becomes an insight" icon="lightbulb">
    When a theme is strong enough, Squad synthesises it into a scored **insight** (`IN-…`). Open it
    to read its strength and momentum and the signals behind it.
  </Step>

  <Step title="Link the insight to a goal" icon="trophy">
    Link it to a **goal** it supports ([Goals](/goals)), so the work
    ladders up to strategy.
  </Step>

  <Step title="Work the recommended actions" icon="circle-check">
    Squad recommends **actions** off the insight ([Actions](/actions)). Prioritise them, assign
    an owner, and **Start** the ones with a chat prompt to hand them to the assistant.
  </Step>

  <Step title="Write the decision up" icon="file-text">
    When a decision needs writing up, generate a **one-pager**, a PRD to spec the work, or a
    decision brief to make the call ([One-pagers](/one-pagers)). It cites the evidence
    automatically.
  </Step>

  <Step title="Make the call" icon="gavel">
    Review the brief on the [Dashboard](/dashboard) under **One pagers to review**, choose **Build**,
    **Defer**, or **Research**, and **Mark decided**.
  </Step>
</Steps>

## Your weekly triage routine

A repeatable loop built around the dashboard.

<Steps>
  <Step title="Open the dashboard" icon="layout-grid">
    Open the [Dashboard](/dashboard). The caption above the greeting tells you when the daily brief
    was written.
  </Step>

  <Step title="Work Prioritized actions top-down" icon="list-checks">
    Start, mark done, or dismiss each. What is done drops off automatically.
  </Step>

  <Step title="Clear One pagers to review" icon="gavel">
    Decision briefs waiting on a call, and PRDs sitting in draft or review.
  </Step>

  <Step title="Glance at New evidence" icon="radio">
    Anything surprising in the last day.
  </Step>

  <Step title="Press Re-brief" icon="refresh-cw">
    Once you have changed the picture, so the next brief reflects it.
  </Step>
</Steps>

## Investigate a spike in complaints

<Steps>
  <Step title="Open the Signal Clusters tab" icon="layers">
    Open **Insights** and switch to the **Signal Clusters** tab ([Signal clusters](/signal-clusters)).
  </Step>

  <Step title="Filter and sort" icon="funnel">
    Filter by **Type → pain point** and sort by **Data Signals** descending.
  </Step>

  <Step title="Read the member quotes" icon="quote">
    Open the largest cluster and read the **Members** quotes, the real feedback.
  </Step>

  <Step title="Follow the insight, or draft one" icon="lightbulb">
    If it's already an insight, follow the linked `IN-…` and decide whether it needs a goal or an
    action behind it. If not, ask the [assistant](/chat-assistant) to draft one.
  </Step>
</Steps>

## Turn a quarterly goal into tracked work

<Steps>
  <Step title="Create the goal" icon="trophy">
    Create it on the [Goals](/goals) page.
  </Step>

  <Step title="Link the insights that justify it" icon="lightbulb">
    Open its **Insights** tab and link them. This is the evidence for why the goal exists.
  </Step>

  <Step title="Accept the actions and give them owners" icon="user-check">
    From those insights, accept the **actions** Squad recommends and give them owners
    ([Actions](/actions)).
  </Step>

  <Step title="Keep the goal honest" icon="git-branch">
    As work lands, the goal's linked insights and actions keep it honest. You can always trace the
    goal down to the feedback driving it ([Relationships](/relationships)).
  </Step>
</Steps>

## Let an agent watch something for you

<Steps>
  <Step title="Configure what it watches and how often" icon="bot">
    Go to **Agents → New** and configure what to watch (a URL, a Slack channel, a Notion space, or
    a workspace event) plus how often it runs ([Agents](/agents)).
  </Step>

  <Step title="Give it instructions and an output" icon="pencil">
    Give it instructions and, if you want a written brief each run, a report question and where to
    deliver it.
  </Step>

  <Step title="Read what it finds" icon="file-text">
    Each run produces a **report** and folds new findings into your signals, clusters, and insights,
    so an agent quietly feeds the same pipeline everything else uses.
  </Step>
</Steps>

## Trace any decision back to its evidence

Nothing in Squad is meant to be an unsourced claim.

<Steps>
  <Step title="Open the entity" icon="file-text">
    A goal, insight, one-pager, or brief.
  </Step>

  <Step title="Follow its links downward" icon="arrow-down">
    A goal's **Insights** tab → an insight's supporting signals → a
    signal's original quote and source.
  </Step>

  <Step title="Click a reference chip" icon="link">
    Anywhere a reference chip like `SI-12`, `IN-4`, `AC-7`, or `OP-3` appears, click it to jump
    straight to that entity. See [Relationships](/relationships), or ask the
    [assistant](/chat-assistant) "what's the evidence behind this?".
  </Step>
</Steps>

## Bring your own data over the API

<Steps>
  <Step title="Ask Squad for an organisation API key" icon="key">
    Issuance is not self-service today. Write to
    [support@meetsquad.ai](mailto:support@meetsquad.ai) and say which organisation the key is for.
  </Step>

  <Step title="POST your feedback" icon="webhook">
    From your own system (helpdesk, survey tool, app), POST feedback to `/api/v1/signals` with a
    sensible title and any `metadata` you want to keep. Everything arriving this way is recorded
    against the `api` source.
  </Step>

  <Step title="Watch it join the pipeline" icon="workflow">
    Ingested signals join the pipeline exactly like integration data, clustered, scored, and
    surfaced as insights with no further work from you.
  </Step>
</Steps>

<Warning>
  Step one is not something you can do yourself. No screen in the app mints a key and no CLI command
  does either, so you have to ask Squad for one.
</Warning>

## See who changed what

When something looks different from yesterday, open the [Activity](/activity) feed. It records
every create, update, and decision across the workspace (by teammates and by Squad itself) so you
can reconstruct how a goal, insight, or brief got to where it is.
