The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Audits go faster when records are ready before anyone asks.
Auditors typically request things like bank reconciliations, supporting documents for larger transactions and grant agreements. If those live in one organized place, the audit is mostly a formality. If they're scattered across inboxes and shared drives, it turns into weeks of searching.
You don't need to wait for an audit notice. Pulling those items together each quarter makes the real thing much less stressful.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Reviewing your audit log workflow for a legal tech platform
Agents fail tax work by filling the gaps in the file.
Surge AI's new benchmark gives agents 50 real tax assignments, about 30 documents each, and the best one passes 10.8%. The failures in their write-up aren't misread PDFs. One agent decided a couple wasn't married from their Florida address, while the file showed a Colorado ceremony. Another assignment plants a ledger entry pointing at a receipt that isn't there.
That matches what I see on 200-page loan files. Reading the pages is the easy part. The hard part is a value with no page behind it, because the model fills it with something plausible and the output looks finished.
The Hacker News thread says better tooling around the model would fix most of this. I think it fixes part of it. The tooling has to make the agent cite a page for every answer and accept "not in the file" as a result.
If you think tooling closes most of that 90% gap, what would you add to it first?
Show a status the same way everywhere it appears. //Micro-case study
In B2B products, one record moves between people and screens. A rep sees it on their phone. A manager sees it on a desktop dashboard. If each screen shows the status differently, each person learns a different product.
In a sales coaching app, a plan in review looks the same on both screens:
→ The same word, "In review"
→ The same orange dot
→ The same pill
I find consistency like this helps users:
Learn the product's words once
Understand what the other role sees
Move faster, because nobody stops to ask
Get to the value sooner
