Site information
Public discovery files, crawl policy, and a directory of pages on hadimulia.com.
Discovery files
This HTML page and the raw documents use the same source data. If a reading tool cannot open a text or XML file, the policy and directory are available here without JavaScript.
- robots.txt
- Crawl rules for this hostname.
- sitemap.xml
- The canonical page directory in XML.
- llms.txt
- A curated reading index in plain text.
- ai-profile.json
- The public identity, evidence, and research data behind the portfolio.
A generated HTML copy explains the published configuration. It does not establish that another service successfully fetched a raw endpoint.
Crawl policy
User-Agent: *
Allow: /
Disallow: /api/
User-Agent: OAI-SearchBot
Allow: /
Disallow: /api/
Sitemap: https://hadimulia.com/sitemap.xml
Page directory
24 listed pages. The XML sitemap also includes public routes that are omitted from navigation.
- https://hadimulia.com/
- https://hadimulia.com/about
- https://hadimulia.com/projects
- https://hadimulia.com/evidence
- https://hadimulia.com/fantopy
- https://hadimulia.com/fantopy/full
- https://hadimulia.com/workbench
- https://hadimulia.com/terminus
- https://hadimulia.com/listening
- https://hadimulia.com/site-info
- https://hadimulia.com/projects/cherminal
- https://hadimulia.com/projects/constant
- https://hadimulia.com/projects/rifter
- https://hadimulia.com/projects/skillpack
- https://hadimulia.com/projects/fleetwatch
- https://hadimulia.com/projects/ever
- https://hadimulia.com/projects/burnrate
- https://hadimulia.com/projects/replaydeck
- https://hadimulia.com/projects/purser
- https://hadimulia.com/projects/voicer
- https://hadimulia.com/projects/voicepack
- https://hadimulia.com/projects/jobber-mochi
- https://hadimulia.com/projects/thinking-room
- https://hadimulia.com/projects/bonfire
Reading index
The listed links and descriptions below also appear in llms.txt. The raw index includes unlisted public routes.
Professional identity and evidence
- Hadi Mulia · AI Product & Systems Engineer
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
Hadi Mulia's engineering background, areas of work, and the evidence behind them.
- Projects · Hadi Mulia
Personal products, native tools, and agent systems by Hadi Mulia, with dedicated project records.
- Evidence · Hadi Mulia
Public code, releases, upstream contributions, project decisions, and the limits of the evidence.
- Fantopy AI · Hadi Mulia
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
The full, directly accessible Fantopy contribution record across seven domains, with evidence scope and AI authorship disclosure.
- Workbench · Hadi Mulia
Why Hadi Mulia packages recurring ways of working with coding agents as portable skills.
- Terminus · Personal AI operating system · Hadi Mulia
A reference architecture for personal agents that stay useful as your life changes.
- Site information · Hadi Mulia
Public crawl policy, discovery files, and the page directory for hadimulia.com, available as readable HTML.
Research and thinking
- AI, From the Atoms Up
What turns a model into an operational AI system?
- Functional Anatomy of Systems
How do complex systems divide responsibility without losing coherence?
- Red Trees
How does an inherited error survive, and how should it be corrected?
- All Roads Lead to Rock
What changes when one technical layer hides the complexity of another?
- Business Shape Morphology
How do capabilities, constraints, and recurring market gaps shape a product?
- From A to B
How can a useful practice survive when the reasons behind it are forgotten?
- Stories and the AT Field
Why can a lesson be easier to consider through someone else's story?
- 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
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
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
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.
The research site
hadi.sh has its own files and crawl policy. Read the research site information.