FINANCE

Weekly warehouse cost-driver analysis → attributed spend digest

Every week it queries the cost warehouse for the top spend movers by service and team, attributes each mover to deploys via Axiom.

CategoryFinance
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires
  • ActionQuery warehouse for per-service/team week-over-week spendSnowflakeSnowflake
  • LogicRank top spend movers up and down by dollar change
  • ActionQuery Axiom for deploys landed during the periodAxiom
  • ActionGenerate narrative cost-driver digestOpenAI
  • OutputEmail attributed digest to finance-eng leadershipGmailGmail

What it does

This workflow runs a weekly analysis against your cost data warehouse, ranking the services and teams whose spend moved most week-over-week. For each significant mover it pulls the matching deploy history from Axiom to explain why, then compiles a ranked digest of cost drivers and emails it to finance and engineering leadership.

When to use it

Use it for the recurring FinOps review where leadership wants to know not just that spend changed, but which teams and deploys drove it. It replaces a manual spreadsheet pull with an attributed, narrated weekly report.

How it works

  1. 1A weekly schedule kicks off the run.
  2. 2It queries the warehouse for per-service, per-team spend versus the prior week.
  3. 3A ranking step selects the top movers up and down by absolute dollar change.
  4. 4For each mover it queries Axiom for the deploys that landed during the period.
  5. 5It generates a narrative digest summarizing each driver and its likely cause.
  6. 6It emails the formatted digest to the finance-eng leadership distribution list.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SnowflakeWarehouses, queries, shares.
  2. 2
    Connect AxiomLog streams, queries, dashboards.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect GmailRead, draft, send, label.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.