Hacker News: pranshuchittora

Claude Opus 5

pranshuchittora — Thu, 23 Jul 2026 18:01:03 +0000

Article URL: https://artificialanalysis.ai/models/claude-opus-5

Comments URL: https://news.ycombinator.com/item?id=49025676

Points: 4

# Comments: 1

New comment by pranshuchittora in "Ask HN: What Are You Working On? (July 2026)"

pranshuchittora — Mon, 13 Jul 2026 11:23:40 +0000

I am working on building an self-improving QA agent for software teams. Free and open-source. It is an agentic testing harness with batteries, includes the test runner infra (web & mobile), memory (vector store, local embedding model powered by transformers.js, self improving loop, issue reporting. More details - https://vostride.ai | Code - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Ask HN: How are you using AI agents for testings features?"

pranshuchittora — Tue, 30 Jun 2026 17:24:26 +0000

GitHub - https://github.com/vostride/agent-qa

Ask HN: How are you using AI agents for testings features?

pranshuchittora — Tue, 30 Jun 2026 17:24:12 +0000

Hey, I am working on building agent-qa https://github.com/vostride/agent-qa which is a self-improving QA agent for software teams.

Processed over 500M+ tokens and thousands of test runs, would love to understand your thoughts on this and how you are approaching testing today.

Comments URL: https://news.ycombinator.com/item?id=48736050

Points: 1

# Comments: 1

New comment by pranshuchittora in "Ask HN: Is Codex with GPT 5.5 Extra High being dumbed down?"

pranshuchittora — Tue, 30 Jun 2026 17:22:09 +0000

Yes, I feel so. I started happening from june first weekish. I have shifted to claude code for planning things and codex for execution (as it is faster, though dumb)

New comment by pranshuchittora in "Ask HN: How do you handle QA at a startup with no QA team? Genuinely curious"

pranshuchittora — Mon, 29 Jun 2026 20:59:46 +0000

Yes - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Ask HN: How do you handle QA at a startup with no QA team? Genuinely curious"

pranshuchittora — Mon, 29 Jun 2026 19:14:54 +0000

Use https://github.com/vostride/agent-qa you don't need a QA team just ask coding harness to write tests and you can review the test runs.

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 12:25:29 +0000

Yes a lot. So with the acceleration of AI in the software engineering. Features are being shipped faster but causes regressions. The only way to verify is either you write tests with AI and spend hours reviewing them or you do manual QA. agent-qa aims to solve the later. First your product should work for the end user, later you can write clean test etc.

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 07:50:46 +0000

Try the OSS alternative - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 07:50:26 +0000

Try the OSS alternative - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 07:50:06 +0000

Try the OSS alternative - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 07:49:17 +0000

Try the OSS alternative - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 07:46:31 +0000

I did. Checkout the OSS alternative - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Fri, 19 Jun 2026 07:46:07 +0000

Try the OSS alternative - https://github.com/vostride/agent-qa

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Thu, 18 Jun 2026 23:05:11 +0000

Some digging FAST_MODEL = "google/gemini-3-flash" (fast mode primary) DEEP_MODEL = "openai/gpt-5.4" (deep mode primary) VISION_CLICK_MODEL= "openai/gpt-5.4" (the visual grounder)

fast: gemini-3-flash, falls back to gpt-5.4, 15-min run timeout, max 2 visual calls/step. deep: gpt-5.4, 15-min timeout, max 3 visual calls/step.

Why such a hard timeout, and why not latest models?

New comment by pranshuchittora in "Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps"

pranshuchittora — Thu, 18 Jun 2026 22:42:30 +0000

Hey, I just gave it a try and ran a quick test on booking.com. It took ~3 mins for a basic test. Do you cache the test steps so that future runs are faster and they don't call LLMs for the subsequent runs?

Also your current pricing is $300 for 1K tests which means $0.3 for each test. We tried out playwright mcp and it easily consumes 1M+ tokens for a test with ~20 steps (including image input). So with this pricing are you guys default alive?

Also is there a benchmark which you ran to prove the efficacy of your testing agent? because in the current stage it is a trust me bro kinda thing.

New comment by pranshuchittora in "Show HN: Id-agent – Token efficient UUID alternative for AI agents"

pranshuchittora — Thu, 21 May 2026 14:24:50 +0000

The word dictionary is curated with guardrails. Also the dictionary contains words which are 1 BPE token long. Under 5-6 characters

New comment by pranshuchittora in "Show HN: Open-Source Agentic QA Harness with Memory"

pranshuchittora — Wed, 20 May 2026 16:21:06 +0000

Thanks for those kind words. The landing page's demo required lots of sculpting. I would say that agent-qa is not only frontend focused. As you can run hooks in sandboxed env to test apis, so a better way to put it is with agent-qa you can test the product end-to-end not only UI.

But the issue with API testing / backend is that coding harnesses are really good at it. A product manager who writes user stories should be able to write tests for the product, and usually PMs don't care about the APIs.

Do give agent-qa a try, and consider giving it a star on GH https://github.com/vostride/agent-qa

Thanks!

Show HN: Open-Source Agentic QA Harness with Memory

pranshuchittora — Wed, 20 May 2026 11:10:47 +0000

GitHub - https://github.com/vostride/agent-qa Live Demos - https://vostride.com/demo/agent-qa

Comments URL: https://news.ycombinator.com/item?id=48205901

Points: 18

# Comments: 2

New comment by pranshuchittora in "Show HN: Id-agent – Token efficient UUID alternative for AI agents"

pranshuchittora — Tue, 19 May 2026 19:52:02 +0000

It is being used in production at https://vostride.com/agent-qa The issues was agent-qa have many different kinds of files tests, memory etc and there's too much FK references which LLMs need to resolve. Using id-agent worked like a charm