Connect Snowflake read-only
A username and password, or a key pair. Bicycle only ever sees what the role you give it can see.
Bicycle on Snowflake
Know why your
Know why your
KPI moved
before anyone asks.
Connect Snowflake read-only. Bicycle watches your revenue-critical KPIs, names the cause, and recommends the next step. First agent in about 15 minutes.
No credit card·Real product, real data
BICYCLE_DATABASE.PUBLIC
CART_VALUE_BAND
CHECKOUT_ERROR_TYPE
CHECKOUT_SESSION
CHECKOUT_STEP
CUSTOMER_SEGMENT
DEVICE_TYPE
PAYMENT_ATTEMPT
PAYMENT_METHOD
RECOVERY
RECOVERY_CHANNEL
WATCHINGCheckout Completion Rate by Funnel Step
On top of Cortex
The KPI is in Snowflake.
The KPI is in Snowflake.
The cause often is not.
Checkout Completion Rate
DROP
It falls on mobile web. The cause is a payment provider's certificate rotation, and it lives in your gateway logs, not in your warehouse.
With Snowflake Cortex
Someone has to notice first
The drop is already true in your tables. It becomes a question only when a person opens the dashboard and decides something looks off.
You frame the question
Cortex writes the SQL once you decide which metric, which window, which drivers. It confirms the drop in that segment, quickly and well.
The cause sits outside the warehouse
Cortex reasons over what is in Snowflake. The certificate rotation is in your gateway logs. Reaching them, correlating them, and acting on what you find are three systems you build and maintain.
With Bicycle
D
Detect
The drop surfaces on its own, ranked by revenue impact, with the segment and the device type already named. Nobody had to go looking.
E
Explain
Cause analysis tests drivers inside and outside Snowflake, ties the drop to the certificate rotation, and rules out a code deployment in the same window.
A
Act
Escalate to the payment provider, recommended to the owner who can approve it. Previewed, bounded, reversible, logged.
L
Learn
The signature is kept, so the next drop with this shape is recognized the moment it appears.
Bicycle runs on top of Cortex and your warehouse rather than replacing them. What it adds is the detection you did not have to schedule, cause analysis that reaches past the warehouse boundary, and a governed next step.
Compare in depth
Also compared: Dashboards · Build your own
What to expect
One connection.
One connection.
Four ways to get the answer.
Connect Snowflake read-only and the agent comes to life across the surfaces your team already lives in: alerts, data stories, chat, and dashboards. All from the same KPI and the same approved definitions. About 15 minutes after you connect.
Alerts
KPI movement, surfaced before anyone asks. Checkout completion falls on mobile web, and the alert names the surface, the size of the drop, and what caused it.
Data stories
The week or the quarter, as slides. What changed, why it changed, and what it cost, assembled into a deck you can present and share. Alerts cover today. Data stories cover the stretch.
Chat
Every follow-up, grounded. Ask why, ask where, ask what changed, and the answer comes back with its evidence attached.
Dashboards
Dashboards you did not have to build. Bicycle creates them from the KPIs it onboarded, and you can ask for another in plain language. They sit alongside the dashboards you already have.
A real Snowflake connection, start to finish: connect, pick an agent, watch the model assemble.
No integration project.
Connect, and Bicycle does the rest.
Select the tables in scope
Pick only the tables your agent needs. Fewer tables, fewer warehouse queries, lower compute cost.
Choose your first agent
Bicycle reads your schema and proposes the agents your data can already support. Checkout completion rate, payment decline analysis, cart recovery by channel, and more.
Bicycle builds the data model
Confirm three screens. Data model, KPIs, patterns, thresholds. About 10 to 15 minutes, and we email you when it's ready.
Tell it when your warehouse loads. Set it to 2 AM and it analyzes a complete day rather than a half loaded table. That is the difference between a real alert and a false one.
What it built
Ten Snowflake tables in.
A working data model out.
Bicycle classifies your tables into events and dimensions, maps each one to its source, and sets a refresh schedule per object. Every inference is visible, and every one is editable. You keep the guardrails.
This is the part that normally takes an analytics engineer weeks. It happens once, from a read-only connection.
Your warehouse,
your rules.
Your data team sets the guardrails and the agent runs inside them, which keeps the recurring investigations off the analyst queue without giving up control of what gets trusted.
01
Read-only
Bicycle never writes to your warehouse.
02
Queried in place
Your data is not copied out of Snowflake.
03
Scoped by you
You pick the tables. Nothing outside that scope is visible.
04
Fully editable
Every inferred mapping, KPI, and threshold is yours to change.
What to have ready
before you connect.
What do I need to connect?
A Snowflake account identifier, a warehouse, and a read-only role. Username/password or key pair.
Does Bicycle write to my warehouse?
No.
What will this cost me in credits?
Bicycle runs read queries on your warehouse on the schedule you set. Narrower table scope and lower refresh frequency mean fewer queries.
Can I add sources beyond Snowflake?
Yes. Snowflake for the KPI, and as many other sources as you like for cause analysis.
What if I'm on BigQuery?
Same flow, same four steps. Start the BigQuery build.
How long until the first agent is live?
Usually 10–15 minutes.
Bring one KPI.
Connect Bicycle to Snowflake.
Read-only, in place, live in about 15 minutes.
No credit card · Real product, real data
bicycle.ai/snowflake