Celerp brings modular, self-hosted accounting to AI-native workflows
YC-backed Celerp launches local-first accounting software with modular architecture enabling users to build custom modules via AI coding tools without forking the codebase.
The Wire — Page 13
Study proposes verification-cost metric to evaluate AI reliability in accounting
Researchers argue AI model evaluation for accounting must measure verification effort, not just correctness—identifying a new failure mode where auditors miss errors within budget constraints.
8 more from arXiv: AI + Accounting
Open-Weight Models Close Gap With Proprietary LLMs on Financial Document Anal...
Updated Financial Touchstone benchmark with 2,967 Q&A pairs from 495 annual reports tests 20 open-weight and proprietary models; Chinese AI labs' models show improved financial text comprehension b...
Large Language Models Automate IT Audit Control Evaluation
IntelliAudit uses retrieval-grounded multi-agent LLMs to automate IT audit evidence evaluation by synthesizing heterogeneous organizational data across policies and records—addressing the semantic ...
Researchers introduce Agent Auditing Engine for evaluating LLM-based agents
Researchers introduce A²E (Agent Auditing Engine), an end-to-end evaluation framework for assessing LLM agent capabilities across domains, addressing the gap in systematic auditing of complex agent...
Researchers introduce A²E agent auditing engine for LLM evaluation
Academic researchers present A²E, a systematic evaluation framework for auditing LLM-based agents, addressing gaps in capability testing critical for enterprise AI deployments in regulated domains ...
Graph Transformer model forecasts accounting KPIs from sparse small-business ...
New Accounting Graph Transformer enables joint 12-month forecasting of 13 financial KPIs from limited accounting history, addressing a core pain point for small business planning and risk workflows.
Video Language Models Struggle With Event Bookkeeping in Controlled Benchmarks
Research paper introduces trace-grounded parametric profiling to expose video language model failures in event counting tasks—a core requirement for automated audit and bookkeeping workflows.
Research Framework for Auditing Autonomous Analysis Agents
Academic paper proposes methods to detect errors in autonomous data analysis agents used in audits, addressing reliability gaps in unsupervised error detection systems.
FinReportBench: New benchmark evaluates LLM quality for institutional financi...
Researchers introduce FinReportBench, an expert-grounded benchmark measuring LLM-generated financial report quality for institutional use, identifying gaps in identity, compliance, sourcing, and vi...
CLA trains proprietary AI model on client accounting data via Digits partnership
CLA, a top-10 US accounting firm, is investing in a three-year build with Digits to train a proprietary AI model on its client accounting practice, capturing transaction judgments to create reusabl...
Botkeeper outlines 7-step process to slash accounting close from 10 days to 2
Botkeeper shares a practical framework for accelerating month-end close cycles by up to 80% through automation and process optimization, targeting accounting teams managing complex close timelines.
Zoho launches AI agent for expense workflows via conversational interface
Zoho Expense MCP enables AI-powered expense management through conversation, moving beyond data analysis to automate actual workflow completion for accounting teams.
Aprio partners with Fieldguide to build AI agents for audit workflows
Aprio, a $681M accounting firm, expands collaboration with Fieldguide to develop role-specific AI agents for financial audits across planning, fieldwork, and reporting phases.
Financial Reporting Automation Connects ERP Layers Into Single Workflow
Guide explains how financial reporting automation integrates ERP, consolidation, and reconciliation to eliminate manual spreadsheet work and accelerate month-end closes.
AI verification tax consumes 15+ hours weekly for half of finance pros
Study reveals accounting firms investing in AI spend 15-30+ hours weekly verifying AI work, contradicting job-loss narratives and highlighting hidden compliance costs of automation.
Snowflake deploys agentic AI for automated contract review
Snowflake introduces agentic intelligence system for contract review that detects novel clauses using semantic analysis beyond rule-based patterns, combining known-standard language detection with ...
Building an AI accounting document agent from scratch
Live coding session demonstrates building an AI agent to automate invoice, receipt, and statement processing—extracting client data, filing documents, and chasing missing information.
UK accounting firm reimagines partnerships for AI-native era
Part 9 of 'The Self-Improving Firm' series explores how a traditional Top 50 accounting firm could be restructured around AI automation, questioning traditional partner roles and firm economics.
AP automation ERP integration patterns compared: native APIs vs middleware vs...
Stampli breaks down how AP automation platforms connect to ERPs via native APIs, third-party middleware, or flat files—each affecting data visibility, error handling, and implementation responsibil...