---
title: "Parsa Mohammadi (@tomosu) | Hashnode"
description: "Production Reliability Governance for the AI Era. Read the latest articles by Parsa Mohammadi on Hashnode."
url: "https://hashnode.com/@tomosu"
---

@tomosu

# Parsa Mohammadi

@tomosu · London, UK · Joined September 2026

Production Reliability Governance for the AI Era

## Comments

[the lint message that points the agent at the right path is the best idea in here, the codebase corrects the agent and you’re not in that exchange at all. the place most people are still the relay is the failure side, timeouts, retries, errors that get swallowed, since lint rules rarely cover those. that’s where the tomosu MCP server sits, the agent pulls reliability findings mid-task with the before and after fix already written, same idea as your lint messages](https://hashnode.com/posts/trust-before-parallelism/6afb493e86de5f505812ca00/comment/6afbb5af8d613899f8d40992)

Comment · Article · 1d ago · [Trust before parallelism](https://hashnode.com/posts/trust-before-parallelism/6afb493e86de5f505812ca00)

[yeah a bare score gets skimmed the same way “61%” does. what keeps it readable is when it fires rarely and carries its why, so most PRs come back ready and the few that don’t show the actual finding plus a before/after fix. your weekly sample is a nice check on that too, if people keep approving the not ready ones without reading, the threshold’s just too loose.](https://hashnode.com/posts/human-in-the-loop-ai-agents-2026-designing-the-handoff/6aeb715d4f806a32422dcb8f/comment/6aeb8f76989c2669f846a91e#reply-6aed2e649679e09ddad588c0)

Reply · Article · Nov 6 · [Human-in-the-Loop AI Agents (2026): Designing the Handoff](https://hashnode.com/posts/human-in-the-loop-ai-agents-2026-designing-the-handoff/6aeb715d4f806a32422dcb8f)

[the approvals-per-hour number is the one more teams should steal, the same thing happens with agent PRs where 30 green approvals an hour means nobody read any of them. your “refund $40, confidence 61%” point carries over too, a reviewer reads a PR that comes with a risk score and the reason behind it, and clicks through one that just says approve, which is the idea behind a PRI (Production Reliability Index) score on each change.](https://hashnode.com/posts/human-in-the-loop-ai-agents-2026-designing-the-handoff/6aeb715d4f806a32422dcb8f/comment/6aeb8f76989c2669f846a91e)

Comment · Article · Nov 4 · 1 · [Human-in-the-Loop AI Agents (2026): Designing the Handoff](https://hashnode.com/posts/human-in-the-loop-ai-agents-2026-designing-the-handoff/6aeb715d4f806a32422dcb8f)

[good catch, and it bites hardest when the upstream is already slow, since the retries pile onto the struggling dependency.](https://hashnode.com/posts/why-requests-get-timeout-5-can-still-hang-and-how-to-set-a-total-deadline/6ade99556123af80316ccc42/comment/6adf36ffb03fc607cd39a1a4#reply-6adf400a336ac1971c45134f)

Reply · Article · Oct 26 · [Why requests.get(timeout=5) can still hang, and how to set a total deadline](https://hashnode.com/posts/why-requests-get-timeout-5-can-still-hang-and-how-to-set-a-total-deadline/6ade99556123af80316ccc42)

[happy to! quickest way is to try it on a repo yourself. it plugs in wherever you already work. a GitHub App that reviews every PR, a plugin for VS Code, Cursor and Antigravity, an MCP integration so CodeRabbit can pull the scores into its reviews, and a one-off scan of any repo. each one takes about two minutes to set up, it’s all here https://tomosu.ai/docs](https://hashnode.com/posts/everything-you-need-to-know-about-code-review-for-ai-generated-code/6ad74bece77a6c87fe656eea/comment/6ad8e544d40e0eb5fe7c014c#reply-6ad93a8eaec251c528581928)

Reply · Article · Oct 21 · [Everything You Need to Know About Code Review for AI-Generated Code](https://hashnode.com/posts/everything-you-need-to-know-about-code-review-for-ai-generated-code/6ad74bece77a6c87fe656eea)

[Spotify’s two incident questions are the best part. the first one is harder than it looks though, you need to know which change caused the incident, and most teams figure that out by hand. we looked at a Spotify outage from that angle at Tomosu, whether the risk was visible before it shipped. the PR looked reasonable on its own, the risk only showed up in how it interacted with the rest of production. that’s the gap we’re working on https://tomosu.ai](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad8e3ecbe72bf71319b757a)

Comment · Article · Oct 21 · 1 · [AI-Driven Development Is a Diagnostic for Your Organization](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52)

[the omissions list is the useful part. missing timeouts and unhandled failure paths are easy to automate, which leaves the human review for the claims and the edges. that’s roughly the split we use at Tomosu, flagging the omissions on every PR so the reviewer starts from the parts that need judgment.](https://hashnode.com/posts/everything-you-need-to-know-about-code-review-for-ai-generated-code/6ad74bece77a6c87fe656eea/comment/6ad8e2e56e2986e39ad27f7e)

Comment · Article · Oct 21 · 1 · [Everything You Need to Know About Code Review for AI-Generated Code](https://hashnode.com/posts/everything-you-need-to-know-about-code-review-for-ai-generated-code/6ad74bece77a6c87fe656eea)

[A static list goes stale fast. The module behind last quarter's incident often isn't on it yet. Scoring each change against what has actually broken before keeps that list current, and tells the human reviewer which PRs deserve a real comment instead of a click. The audit point lands too. "A check ran" is a timestamp. A verdict that records why a change was judged safe or not is something a person can stand behind. That's the gap Tomosu works on: a reliability score and merge verdict on every PR with the reasoning attached, using incident history once it's connected, and a human still making the call.](https://hashnode.com/posts/ai-code-review-healthcare-engineering-mentorship/6abd23f8a5aad5fba3593869/comment/6abe667557750b9715d545df)

Comment · Article · Oct 1 · [What AI Code Review Quietly Removes From Engineering Teams](https://hashnode.com/posts/ai-code-review-healthcare-engineering-mentorship/6abd23f8a5aad5fba3593869)
