Pace
← All cookbooks Product cookbook

Product

Interview transcripts synthesized in one pass. Competitive scans on a cadence. Spec drafts that match house style.

Marquee recipe

User-interview synthesis at the end of every research sprint

A day's worth of transcript synthesis becomes a 10-minute review.

Trigger
Interactive, after a batch of interviews
Skills
synthesize-research
Features
Fireflies/Otter connector (transcripts), sub-agent per transcript, plan mode for review

The hardest part of user research is synthesizing 8-15 transcripts into themes without flattening the signal. Pace runs one sub-agent per transcript in parallel, then a coordinator rolls them up into a synthesis doc with quote evidence and frequency counts. A day's work becomes a 10-minute review.

How to set it up

  1. 1
    Install the product-management plugin
    Install in Cowork ↗ claude plugin install product-management@pace
  2. 2
    Authorize Fireflies or Otter

    Whichever transcript service you use. First time you ask Claude to read a transcript, OAuth opens. Optional: Notion or Linear if you want the synthesis doc saved there.

  3. 3
    Open a Claude session with your interview list

    No routine needed : this one is interactive (you only run it at the end of each sprint). In Claude Code or Cowork, start a new chat.

  4. 4
    Paste this prompt with your sprint's transcript list
    Routine prompt 
    Run synthesize-research against these
interviews from the past sprint:

  - <Fireflies URL or meeting title 1>
  - <Fireflies URL or meeting title 2>
  - <...>

Spawn one sub-agent per transcript to extract themes,
direct-quote evidence, and friction points. A coordinator
sub-agent should roll them up into a single synthesis doc:
top 5 themes by frequency, supporting quotes per theme,
disagreements between participants, and 3 candidate
product implications. Use plan mode : show me the
synthesis before saving.
  5. 5
    Review and save

    Plan mode parks the draft for your review. Edit themes, push back where the AI over-synthesized, then save to wherever your team keeps research docs (Notion, Linear, Confluence).

Weekly competitive scan, ready for the team channel

Trigger
Routine, schedule, weekly Friday 15:00
Skills
competitive-brief
Features
Routines (cloud schedule), web search, brand-voice plugin for the digest copy

A scheduled run of competitive-brief watches the competitive set you care about, summarizes what shipped or changed, and posts a digest to #product-watch. No more "did anyone see the X launch?"

Customer-feedback weekly: signal from noise

Trigger
Routine, schedule, weekly Friday 15:00
Skills
synthesize, update
Features
Routines (cloud schedule), Intercom + Linear connectors, multi-source aggregation

Pulls last week of Intercom tickets, sales-loss reasons from HubSpot, and Linear bugs tagged customer-impact. Synthesizes into themes (not transcripts). Adds the themes as comments under the relevant roadmap items in Linear, and posts the executive summary to #product.

How to set it up

  1. 1
    Create the scheduled routine in Cowork

    In Cowork, open Routines → New routine → Schedule. Match the cadence described in the trigger above.

  2. 2
    Paste this as the routine prompt
    Customer-feedback synthesis prompt 
    Every Friday at 3pm, pull the week's Intercom tickets, sales-loss reasons from HubSpot, and Linear bugs tagged customer-impact. Synthesize into themes, not transcripts: cluster by what the customer was trying to do, what got in the way, and what they did instead.

Add each theme as a comment under the relevant roadmap item in Linear. Post the executive summary to #product with five bullets max.
  3. 3
    Click Run now to verify

    Eyeball the first run for accuracy. Once it looks right, the routine fires on its trigger from then on. Assumes the plugin from the marquee above is already installed and connectors authorized.

Spec review queue: comments addressed before the PM opens Linear

When stakeholders leave comments on a Linear spec, a routine reads each comment, drafts a response inline (accept / push back / clarify), and threads the drafts under the original. The PM walks into Linear with the busywork already done and the judgement calls highlighted in red. Roundtripping a spec shrinks from a week to two days.

Trigger
Routine, Linear webhook on comment-added
Skills
spec, synthesize
Features
Routines (Linear webhook), Linear + Slack connectors, plan mode

How to set it up

  1. 1
    Create the API-triggered routine

    In Cowork, open Routines → New routine → API. Save and copy the routine URL + bearer token; point the upstream webhook at it (e.g. calendar provider, Intercom webhook, PagerDuty webhook, depending on the trigger).

  2. 2
    Paste this as the routine prompt
    Spec-comment review prompt 
    When stakeholders leave comments on a Linear spec, read each comment in context. For each one, write a candidate response in a thread under the original comment: accept-and-update, push-back-with-reasoning, or ask-for-clarification.

Mark the responses that need product-manager judgment in red; leave the obvious ones as drafts the PM can approve in a single pass.
  3. 3
    Click Run now to verify

    Eyeball the first run for accuracy. Once it looks right, the routine fires on its trigger from then on. Assumes the plugin from the marquee above is already installed and connectors authorized.