How I replaced a two-hour daily Pain Depot ritual with a Cowork synthesis pipeline

Scale

5+ sources Slack, Gong, Pylon, Meet notes, Linear
3 outputs PRD input, CS field guide, leadership summary per run

Results

Daily ritual

~2 hours per day Manual combing across channels
One Cowork run Automated synthesis pipeline

Every new project at Aampe used to start the same way: hunt across Slack, Gong, Pylon, Meet notes, and Linear for the last time someone said something true. The Pain Depot ritual surfaced signal — but synthesis still lived in my head and in scattered docs.

I built a pipeline instead: a Chrome extension that exports Slack via your own session to local JSON (no bot token, no third-party server), a shared notes repo so context compounds, and Claude Cowork skills that output KB articles citing every claim back to the source message.

Automating context gathering — Pain Depot ritual replaced with a Cowork synthesis pipeline at Aampe
Context gathering at Aampe — from daily Pain Depot combing to an automated synthesis pipeline.

What one run produces

One Cowork run now produces three outputs from the same source set:

  • PRD input — structured problem framing for design and product
  • CS field guide — language Customer Success can use with customers
  • Leadership summary — escalation-ready brief with linked sources

Every claim in a KB article links back to the source message. CS and leadership can verify synthesis instead of trusting a summary.

Chrome Slack export extension — structured JSON download via your own session
Slack exporter — search and download via your session; data stays in the org.

Architecture

Five source connectors feed a synthesis agent:

  • Slack export (Chrome extension, local JSON)
  • Gong call summaries
  • Pylon support threads
  • Meet notes
  • Linear issues

The agent clusters themes, resolves duplicates, and writes to the shared notes repo. Cowork skills read accumulated context on the next run instead of starting from zero every morning.

Shared notes repo — cumulative context for each Cowork synthesis run
Shared notes repo — context compounds instead of resetting every morning.

Automate synthesis, not judgment

AI handles reading, clustering, sourcing, and formatting. Deciding what to escalate stays human. The pipeline saves hours of combing — it does not replace product judgment.

Cowork synthesis pipeline — from Slack export to source-cited KB articles, PRD input, and leadership summaries
Cowork synthesis pipeline — from export to source-cited outputs for product, CS, and leadership.
TLDR; 3 Learnings

Automate synthesis, not judgment

AI handles reading, clustering, sourcing, and formatting. Deciding what to escalate stays human.

Context compounds in a shared notes repo

Each export and synthesis run adds to a shared notes repo. Cowork skills read accumulated context instead of starting from zero every morning.

Source-cited outputs

Every claim in a KB article links back to the source message. CS and leadership can verify synthesis instead of trusting a summary.