back_office_ops · saas · workflow
Digits: Lessons from two years running AI agents in production for accounting
Moving AI agents from prototype to production in an accounting platform requires solving hard infrastructure problems—observability, guardrails, memory, and safe tool generation—that open-source frameworks do not yet address in production-ready form.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Task objective defined
An objective defines what needs to be accomplished by the agent.
Tools used
OpenTelemetryGo
Outcome
Digits has been running AI agents in production for over two years across three use cases—vendor data enrichment, client onboarding, and complex user questions—with qualitative improvements in manual research time and data quality, and faster task completion with higher accuracy using upfront task planning.
What failed first
Open-source agent frameworks like LangChain and CrewAI were evaluated but found too complex with too many dependencies to be production-ready without significant modification.
Results
Time savedreducing manual research time
Volumehigher accuracy
Running sinceover 2 years
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes.
agentic workflowai agentragknowledge basebuilder submittedfailure mode describednamed customerproduction runtime claimedsource backedtools describedworkflow describedfinancial servicessoftwareaccuracy improvementcycle time reductiontime savedtechnical build writeupback office opscustomer supportdata entry opsagentic task executionescalation workflow