Search & analytics
A user-funnel agent that reads Google Analytics and shows where users stall.
Connect Google Analytics and OpenHelm's journey analyst maps your product's key user journeys from the product itself and its GA4 events. Where users stall, it files a task with the evidence, and charts and data tables show funnels, retention and audience. If a live product has no analytics at all, OpenHelm files a task and can create the GA4 property and data stream, then wire the measurement ID into the deployment.
What agents do with Google Analytics. Recurring jobs, checked every run.
Map the key user journeys
Work out the journeys that matter for the product, such as sign-up to first use, from the product itself, then match each step to the GA4 events that measure it.
Turn stalls into tasks
Where users drop out of a journey, file a task with the evidence: the step, the numbers behind it and what the agent thinks is causing it.
Funnel, retention and audience views
Keep data tables of funnel, retention and audience figures up to date, drawn as charts on the product's screens so the trend is visible at a glance.
Analytics for a product that has none
Create a GA4 property and web data stream under your connected account, link it to the product, then set the measurement ID in the deployment and redeploy.
Connect Google Analytics. A few minutes, once.
Connect Google Analytics
Add Google Analytics under Connections in the OpenHelm app and complete the hosted sign-in, or mint a connect link programmatically with POST /v1/connections/links.
Describe the job in plain English
Tell OpenHelm what you want done and how often. It drafts a plan with a schedule, the tools it will use, and a clear definition of done.
Approve the plan
No job fires until you have reviewed the plan. Set the autonomy level to control whether writes execute directly or queue for your approval.
It runs, self-checks and reports
Runs execute in isolated cloud sandboxes on schedule. An independent evaluator scores each run against the goal, and results arrive as logs, emails or data-table rows.
Or provision it over the API (see the Connections API docs):
curl https://api.openhelm.ai/v1/connections/links \
-H "Authorization: Bearer oh_live_..." \
-H "Content-Type: application/json" \
-d '{ "provider": "<provider id>", "name": "Google Analytics" }'
# Returns a short-lived hosted link. Open it once to authorise,
# then poll GET /v1/connections until it shows as authenticated.Questions
Can OpenHelm create the Google Analytics account too?
It can create properties and data streams under an account you already administer, once the connection has edit access. Creating a new account needs a person to accept Google's terms, so that one step stays with you.
How does OpenHelm connect to Google Analytics?
Through a scoped OAuth grant: you sign in to Google Analytics once via a hosted connect flow, in the OpenHelm app or via a connect link minted with POST /v1/connections/links. OpenHelm stores no passwords, the grant is limited to what your jobs need, and you can revoke it at any time.
Can the jobs run on a schedule without me?
Yes, that is the point. Jobs run once, on an interval, or on a cron expression. A scheduler fires them, a watchdog times out anything hung, and a separate evaluator checks each run actually advanced the goal. You approve the plan before anything runs for the first time.
Is my Google Analytics data safe?
Each run executes in an isolated cloud sandbox with scoped, revocable credentials and no middle-layer copy of your data. Every action is logged per run, results come back with evidence, and the agent never fabricates data it could not verify.
Keep reading
More in Search & analytics
Give your product a team that never clocks off.
Start free in the browser, or run it on your Mac with your own Claude Code or Codex plan.