SAT tax agent + assisted month-end close
An accounting firm with a portfolio of corporate clients. We built a SAT tax agent that downloads CFDI e-invoices, reconciles them against the books and prepares workpapers for the month-end close.
Mid-sized accounting firm (client under NDA)
The firm's client base grew faster than its team. Junior accountants spent entire weeks downloading CFDIs and reconciling by hand. The monthly close for some clients dragged on, and the risk of errors climbed with the workload.
Stack and deliverable
A SAT agent that works client by client: it downloads the month's issued and received CFDIs, reconciles them against the books (the client's accounting system), flags discrepancies and prepares workpapers in a standard format. The junior accountant receives a close that's already mostly done and only validates the edge cases. A per-client audit log supports audit compliance.
What changed in the operation
What we learned
Accounting firms are a near-perfect fit for AI automation: the processes are repetitive, the volume is high and the data lives in accessible systems (SAT and ERPs). The cultural factor — training the team to trust the agent — was harder than the technical implementation.
How it was built
Technology: SAT CFDI API · Accounting systems · Drive · Audit log
Delivery: Staged delivery through to production
FAQ · this case
How did this Professional services · Tax project make it to production?
Staged delivery through to production: design, build, testing with real data and launch. By the end, the client's team was running the agent in production, with observability dashboards and guardrails already configured. Stabilization is part of the delivery.
What tech stack was used in this Professional services · Tax case?
SAT CFDI API · Accounting systems · Drive · Audit log. Each piece was chosen to fit the client's existing systems — no forced migrations, integrating through official APIs wherever they were available.
How are results tracked?
Before the project starts, we agree on an operational baseline with the client, and during stabilization it's reviewed on the operations dashboard. Because of the NDA, we don't publish this client's figures. In the diagnostic we define what to measure in your case.
Can this be replicated at another company in Professional services · Tax?
The pattern is replicable; the specific implementation depends on the current stack, operating volume and internal rules. The Studio diagnostic identifies which pieces apply to your context and estimates the return for your case.
Who runs the agent after the project?
The client's team. Studio hands over the agent running and trains the team on monitoring, prompt adjustments and exception handling. Stabilization support is included for the first few months; after that, an optional monthly retainer is available.
What happens if the AI model changes or gets more expensive?
We don't depend on a single provider. If a model changes or gets more expensive, we move the agent to another one without rebuilding it.
Facing similar challenges in Professional services · Tax?
A Studio diagnostic with an architect. We identify which processes to automate first and estimate the return for your case.
No cost · No commitment