# Hadi Mulia

> AI product and systems engineer in Singapore. Researching patterns across systems and building agent software, native tools, and product experiences. AI Engineer at Atos.

## Professional identity and evidence

- [Hadi Mulia · AI Product & Systems Engineer](https://hadimulia.com/): AI product and systems engineer in Singapore. Researching patterns across systems and building agent software, native tools, and product experiences. AI Engineer at Atos.
- [About Hadi Mulia](https://hadimulia.com/about): Hadi Mulia's engineering background, areas of work, and the evidence behind them.
- [Projects · Hadi Mulia](https://hadimulia.com/projects): Personal products, native tools, and agent systems by Hadi Mulia, with dedicated project records.
- [Evidence · Hadi Mulia](https://hadimulia.com/evidence): Public code, releases, upstream contributions, project decisions, and the limits of the evidence.
- [Thinking applied to engineering · Hadi Mulia](https://hadimulia.com/thinking): How Hadi Mulia's research on systems, evidence, and abstraction connects to concrete engineering decisions.
- [Fantopy AI · Hadi Mulia](https://hadimulia.com/fantopy): Hadi Mulia's contribution record at Fantopy AI, March to July 2026: product interfaces, agent orchestration, verification, and launch work.
- [Fantopy AI: full contribution record · Hadi Mulia](https://hadimulia.com/fantopy/full): The full, directly accessible Fantopy contribution record across seven domains, with evidence scope and AI authorship disclosure.
- [Workbench · Hadi Mulia](https://hadimulia.com/workbench): Why Hadi Mulia packages recurring ways of working with coding agents as portable skills.
- [Terminus · Personal AI operating system · Hadi Mulia](https://hadimulia.com/terminus): A reference architecture for personal agents that stay useful as your life changes.
- [Site information · Hadi Mulia](https://hadimulia.com/site-info): Public crawl policy, discovery files, and the page directory for hadimulia.com, available as readable HTML.

## Research and thinking

- [AI, From the Atoms Up](https://hadi.sh/research/ai-stack-model-to-system/): What turns a model into an operational AI system?
- [Functional Anatomy of Systems](https://hadi.sh/research/functional-anatomy-systems/): How do complex systems divide responsibility without losing coherence?
- [Red Trees](https://hadi.sh/research/red-trees/): How does an inherited error survive, and how should it be corrected?
- [All Roads Lead to Rock](https://hadi.sh/research/technology-abstraction-stack/): What changes when one technical layer hides the complexity of another?
- [Business Shape Morphology](https://hadi.sh/research/business-shape-morphology/): How do capabilities, constraints, and recurring market gaps shape a product?
- [From A to B](https://hadi.sh/research/from-a-to-b/): How can a useful practice survive when the reasons behind it are forgotten?
- [Stories and the AT Field](https://hadi.sh/research/stories-and-the-at-field/): Why can a lesson be easier to consider through someone else's story?
- [The Law of the Jungle](https://hadi.sh/research/the-law-of-the-jungle/): How should rules be assessed when their authors also hold power?

## Open source and upstream credit

- [Merged contribution to OpenClaw agent-skills, shipped in OpenClaw](https://github.com/openclaw/agent-skills/pull/298): Filed the autoreview bug (#297) and fixed it (#298): absolute in-repository finding paths no longer abort the run and discard every other finding. Merged 30 September 2026 by maintainer Peter Steinberger with a changelog credit, carried into openclaw/openclaw in #165103 with the upstream credit "@kennykankush for finding-path normalization", and released in OpenClaw v2026.10.5, which lists @kennykankush among its thanked contributors. One specific merged contribution; it does not imply maintainership. The changelog credit line was submitted with the pull request, following the repository's convention.
- [Proposed plain-language plugin approvals for OpenClaw](https://github.com/openclaw/openclaw/pull/81864): Rewrote chat-delivered plugin approval prompts as plain-language summaries that fail closed, across OpenClaw's chat channels. Listed by the agents-radar daily digest of 17 May 2026 among significant open pull requests. Not merged: the pull request went stale after a merge-gate check found conflicts and failing CI, and closed for inactivity. The digest is an automated third-party summary.

## Public records

- [GitHub profile](https://github.com/kennykankush)
- [Public profile data](https://hadimulia.com/ai-profile.json)

## Scope

Project records distinguish public artifacts from self-reported private work. Research notes are AI-assisted. AI-generated assessments are not employer references or corporate endorsements.
This file is a curated index. The linked human-readable pages carry the claims, evidence, and limitations.