All loops
GrowthHard 13 min· claude-opus-4-1

Activation analyst

Identifies the activation event most predictive of retention.

Read the full Growth build guide →
NOT DEPLOYEDNOT DEPLOYED
0183ms
Trigger
cron(0 7 * * *) fired · every day · 07:00
02843ms
Agent
claude-opus-4-1 · in 1143 tok · out 385 tok
03113ms
Tools
fetch-mcp/anthropic:messages.create → 200 OK · 83ms
0473ms
Verify
schema check · json-schema draft-2020 passed
05103ms
Output
slack #growth · 5-bullet digest posted
0623ms
Notify
audit log written · runbook link attached
SUCCESS
0%
0 runs
P50
0ms
median
P95
0ms
tail
AVG COST
per run
LAST OK
never
LAST FAIL
never
none
Latency · last 30 runs0 samples
no runs yet
Latest output · what your users see
Slack· #growth-radarnow · via ClaudeLoops
Competitor diff · Wed, Jul 29
  • Vercel shipped a new pricing tier ($49/mo Team) — added seat-based caps.
  • Linear rewrote the homepage hero; H1 changed to "Ship in a weekend".
  • Clerk published a changelog: 4 new MCP tools, incl. `workspace.search`.
  • 2 competitors added an "AI" nav link since yesterday.
  • No pricing changes across 14 tracked pages.
scanned 14 pages · 3 diffs · 11 unchanged · next run 07:00
// press Test to run once · Watch live to keep streaming · Deploy to make it real
The problem

Growth experiments require copy, briefs, and analysis humans don't have time for.

The outcome

Each experiment ships with the artifacts it needs, on cadence.

Ingredients & skills

Secrets
  • ANTHROPIC_API_KEY
Providers
  • Anthropic
MCP servers
  • fetch-mcp
#growth#content#seo

How it works

Identifies the activation event most predictive of retention.

Step 1

1 — Pull data

Connect to the source (analytics, SERP, CRM).

Step 2

2 — Draft

Claude writes; you approve from Slack with one emoji.

Step 3

3 — Publish

Approved drafts ship via the relevant channel.

One-line deploy

The button above runs the same command with your saved config. This is the raw CLI form.

bash
npx claudeloops deploy activation-analyst

Related loops