The setting
's lets data teams build, transform, govern and validate their data workflows, either in a web browser or with command-line tools.
AISQL answers look credible while their metric lineage is uncertain.
Enterprise expansion protects analyst access while regulated customers require every answer to follow governed definitions.
Who you’d be doing this for
“My CFO asked where that number came from, and I had to reopen the whole project.”
Hanne Lund · Analytics Engineering Manager · a character in this brief
Leads a regulated enterprise analytics team using dbt metrics for executive reporting.
What is at stake
Plausible AISQL answers are reaching warehouses without a dependable link to approved metric definitions. You must weigh fast containment against preserving useful answers for ambiguous analyst questions.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- enterprise access vs traceable metric lineage
- fast containment vs durable runtime contracts
- ambiguous analyst language vs deterministic tool selection
- response latency vs verification depth
Why Fivetran
AISQL depends on dbt metric definitions and warehouse execution, so an untraceable answer weakens the governed analyst experience.
Written with these in mind
Not your kind of problem? 54 more at Fivetran, or browse every organization.
Where the organization context comes fromThe postings this brief was written from, and the reporting read before it.
The organization context comes from public information. The situation and characters are written for the brief.
Job postings it was written from
Public descriptions of the work at Fivetran. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.
- Staff R&D Software Engineer, Fivetran AI · no longer posted
- Drive the AISQL capability forward: natural language to SQL grounded in dbt metric definitions, executed natively against the warehouse
- Fivetran AI operates like a startup within Fivetran, and we need engineers who thrive on that range and ambiguity rather than staying in one lane.
- Sr. Principal AI Systems Architect (opens in a new tab)
- Define the architecture for the analyst AI stack across prompts, tools, metadata, memory and context strategies, evaluation, and runtime safety.
- Practical understanding of LLM prompting, tool use, retrieval, structured outputs, and evaluation methods.
- Senior R&D Software Engineer, Fivetran AI · no longer posted
- Considered a trusted expert in your subject area, capable of executing complex, ambiguous tasks with minimal hand-holding
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.
Where similar work appears
Other live briefs connected to this one, and what connects them.
Similar problems at other organizations
Like this one, each of these turns on deciding on evidence that's still thin.
Analysts are rerunning plausible agent-generated SQL because they cannot see the context behind it.
You have to weigh inspectable evidence against the response speed that keeps the workflow useful.
Unsupported-answer judgments are 12% when permission-filtered retrieval leaves too little authorized evidence.
You have to weigh useful completion against the cost of confident answers with weak support.
Pilot enterprise workspaces need approved metric logic to appear consistently across their analysis surfaces.
You have to weigh administrator control against an analyst flow people will actually adopt.
The same setting, from another role
Each is set around Fivetran’s dbt platform, written for a different role. They’re separate briefs, not the same scenario.
Enterprise CSMs must reconcile conflicting records in 17 of 40 onboarding questions.
You decide whether AI may infer a remaining step from conflicting notes, or must leave that part of the reply for the CSM.
Six of eight Enterprise customers depend on one person to maintain their dbt models.
You need to weigh proof of independent maintenance against the practice time customers will actually protect.
An enterprise customer may remove two business units from its annual renewal today.
You must weigh preserving ten reporting workloads against committing to savings that a full monthly close has not tested.
Other problems with a similar purpose
In each of these, as in this one, the aim is to build machine-learning systems that earn trust by staying explainable where their errors carry real consequences.
An audit found sensitive fields in 7% of shared artifacts that manual review missed, and the classifiers disagree on the edge cases.
You have to build evidence for a production commitment you cannot easily reverse.
One threshold sends very different numbers of drivers into coaching in each region, and reviewers there agree less often.
You have to balance fair treatment of drivers against enough coverage to improve coaching.
Confirmed takeover messages are reaching guests, while legitimate pre-check-in threads are also being blocked.
You must weigh fraud prevention against a guest losing the instructions needed to enter a booked stay.
