loopfour

Workflow automation, without AI hallucinations.

2.9Score#359 of 999 agents#10 of 22 in Bookkeeper and accountant

Why it ranks #359

loopfour, an AI bookkeeper and accountant from YC W23, ranks #359 of 999 AI agents and #10 of 22 in Bookkeeper and accountant, with a score of 2.9 of 10. Data as of 3 Oct 2026.

The score adds four parts, each 0 to 10, by weight. Every point comes from public evidence. How scoring works ·

Proof 0 × 30% 0.0
Scale 5 × 30% 1.5
Momentum 2 × 25% 0.5
Autonomy 6 × 15% 0.9
= 2.9

Proof
Do customers use it? 30% of the score
0
No public claims of customers or revenue yet.
Not found: revenue or growth (+4), named customers (+3), a customer result (+2), a customer count (+2), work done at scale (+2)
Scale
Is there a real company behind it? 30% of the score
5
20 people.
- +5
  20 people on its YC page20 to 49 people
Not found: funding round in its news (+3)
Momentum
Is it shipping and growing now? 25% of the score
2
Shows hiring.
- +2
  Hiring: 1 open roleSocial Media InternYC page
Not found: launch YC post in the last 6 months (+3), new traction claim in the last 6 months (+2), funding news in the last year (+2), a batch in the last year (it is YC Winter 2023) (+1)
Autonomy
How much of the job does it do on its own? 15% of the score
6
Supervised agent: takes actions in other systems; a person approves key steps.
- +6
  Level 2 of 4: Supervised agentTakes actions in other systems; a person approves key steps.
What the model read
- Acts in other systems: 87% likely
- Finishes whole tasks: 26% likely
- Calls itself an agent: 6% likely
Level 2: Takes actions in other systems; a person approves key steps.

About loopfour

Deterministic, auditable automation for the finance workflows your team dreads. We build and run it on your existing stack. You approve only the exceptions.