Haystack

Replay real customer journeys against every change before you ship

1.2Score#942 of 999 agents#15 of 15 in QA engineer

Why it ranks #942

Haystack, an AI QA engineer from YC S24, ranks #942 of 999 AI agents and #15 of 15 in QA engineer, with a score of 1.2 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 1 × 30% 0.3
Momentum 0 × 25% 0.0
Autonomy 6 × 15% 0.9
= 1.2

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
1
2 people.
- +1
  2 people on its YC page2 people
Not found: funding round in its news (+3)
Momentum
Is it shipping and growing now? 25% of the score
0
Nothing new in the last 6 months.
Not found: launch YC post in the last 6 months (+3), open roles on YC (+2), 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 Summer 2024) (+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: 45% likely
- Finishes whole tasks: 30% likely
- Calls itself an agent: 13% likely
- Level 1 from the model's reading of its pages; the evidence review found, with quotes, that its AI acts in the work, so the level is 2
Level 2: Takes actions in other systems; a person approves key steps.

About Haystack

Haystack automatically learns real customer journeys from production traffic, figures out which ones a code change could affect, and replays them in isolated copies of production to catch regressions before they ship.

When something breaks, Haystack shows exactly what changed across the UI, network calls, and events, then gives the failure back to your coding agent to fix and rerun. Teams get high-fidelity QA without having to write or maintain test cases.