Take your time. There are ideas, stories, and a few tiny surprises tucked around here.

WELCOME TO DAUD'S PORTFOLIO

Useful systems, thoughtful agents,
and a little stubbornness about reliability

Pick a sticky

I bring ideas to life
through agents|

I use engineering, research and practical experimentation to build AI systems that are useful, inspectable and easier to trust.

SupportGuard

AI Agents RAG Human-in-the-Loop

An AI customer-support system with RAG, citations and human escalation.

AI Systems Engineer View case study →

whyLayer

AI Systems Multi-LLM Decision Support

A decision-intelligence system for evidence-backed GO/NO-GO recommendations.

AI Systems Engineer View case study →

DocOps Approval Agent

AI Agents OCR Document Processing Human Approval

An AI document approval system for invoices and contracts.

AI Agent Developer and Full-Stack Engineer View case study →

CiteXai

AI Evaluation Citation Verification Research

An AI citation-verification platform for checking evidence behind generated claims.

AI Systems Engineer View case study →

Other

Project shot Project shot Project shot

Projects

Click or drag a skill onto the table

What I bring to the table

I bring a mix of AI engineering, software development and research thinking to turn complicated workflows into useful systems.

AI Agent Development RAG Systems LLM Integration Voice Agents Python FastAPI React TypeScript Multi-Agent Systems MCP AI Evaluation Human-in-the-Loop Workflows Machine Learning Software Engineering Research Engineering

Learn more about me!

Complex systems are my playground, useful software is my goal.

I'm an AI systems engineer, AI agent developer and founder of Nexasity AI focused on turning complicated workflows into useful software. I build AI agents, RAG systems, voice workflows and evaluation tools, always trying to make the final system clearer, more reliable and easier to use.

Have a system in mind?

I’d love to hear what you are trying to build.
Dhaka, Bangladesh

Wish saved.
Take your time. There are ideas, stories, and a few tiny surprises tucked around here.

{{ welcomeSubEls }}

{{ welcomeTitleLine1Els }}
{{ welcomeTitleLine2Els }}

{{ stickyHint }}

{{ heroTitleEls }}
through {{ heroWordEl }}

I use engineering, research and practical experimentation to build AI systems that are useful, inspectable and easier to trust.

{{ p.title }}

Coming soon {{ tag }}

{{ p.blurb }}

{{ p.roleLabel }} {{ p.ctaLabel }}

{{ p.title }}

Coming soon {{ tag }}

{{ p.blurb }}

{{ p.roleLabel }} {{ p.ctaLabel }}

Other

Project shot Project shot Project shot

Projects

{{ tableHintText }}

{{ ts.label }}

What I bring to the table

{{ tok.text }}{{ c.ch }}

{{ sk.label }}

Learn more about me!

Complex systems are my playground, useful software is my goal.

I'm an AI systems engineer, AI agent developer and founder of Nexasity AI focused on turning complicated workflows into useful software. I build AI agents, RAG systems, voice workflows and evaluation tools, always trying to make the final system clearer, more reliable and easier to use.

Playground

Experiments, side quests and things I made to understand how a system works.

Projects

A few systems, experiments and research projects I have built.

{{ p.title }}

Coming soon {{ tag }}

{{ p.blurb }}

{{ p.roleLabel }} {{ p.ctaLabel }}

{{ p.title }}

Coming soon {{ tag }}

{{ p.blurb }}

{{ p.roleLabel }} {{ p.ctaLabel }}

What I bring to the table

I bring a mix of AI engineering, software development and research thinking to turn complicated workflows into useful systems.

{{ skill.label }}

Learn more about me!

Complex systems are my playground, useful software is my goal.

I'm an AI systems engineer, AI agent developer and founder of Nexasity AI focused on turning complicated workflows into useful software. I build AI agents, RAG systems, voice workflows and evaluation tools, always trying to make the final system clearer, more reliable and easier to use.

Daud Ibrahim Hassan on a sunny coastal pier
{{ photoTooltip.text }}
{{ wordPopCaption }}

From messy workflows to reliable systems

{{ l.ch }}{{ wordNZText }}{{ wordHusText }}{{ wordPetsText }}

{{ c.ch }}

{{ wordNumText }}

{{ wordBakeText }}{{ wordDrawerText }}

{{ termText }}

From messy workflows to reliable systems

I started by building software, websites and small experiments, then kept moving closer to the problems where AI could actually be useful.

The {{ c.ch }} into AI systems took a few detours.

Now I build AI agents, RAG systems, voice workflows and software tools through Nexasity AI.

Outside of work, I’m almost always building something.

I like projects with a little >/{{ termText }}|. A good system should do something useful, but it should also make its decisions easier to inspect, test and improve. Although... I’m studying Computer Science and Engineering at BRAC University, and most of my free time goes into building systems, testing ideas and trying to understand where AI systems fail. Dhaka is home, and one of the research projects I’ve built is MarkLens ↗.

A few things I have been investigating

{{ favCategoryTitle }}

False Containment: Measuring the Evidence Required to Verify Autonomous AI Incident Resolution

Daud Ibrahim Hassan, Govardhan Reddy, Soumya Parthasarathy, Disha Singha and Taemin Park · 2026 · Apart Research AI Incident Response Sprint

A research project about how much evidence is actually needed before claiming that an autonomous AI incident has been resolved.

When the Record and the Report Diverge: Self-Report Fidelity Collapses Under Structured Provenance in Claude Haiku 4.5

Daud Ibrahim Hassan, Deniz Chen, and Soumya Parthasarathy · 2026 · Apart Research

A study of whether language models accurately report what they did when structured provenance and tool-use records are available.

MarkLens: Measuring Cross-Manager Valuation Dispersion in Private Credit at Scale ↗

Daud Ibrahim Hassan · 2026 · Independent preprint

A reproducible SEC EDGAR study of cross-manager private-credit valuation differences at scale.

Monitor Calibration Transport: Evaluating AI Safety Monitor Reliability Across Models and Distribution Shifts

Daud Ibrahim Hassan · 2026 · Independent AI safety research

A study of whether safety monitors calibrated on one model or task remain reliable when the model, task or deployment conditions change.

The Secret Life of Walter Mitty

Ben Stiller

Mr. Robot

Sam Esmail

Palm Springs

Max Barbakow

Pantheon

Craig Silverstein

{{ t }}

{{ caseTitle }}

{{ caseSubtitle }}

Role

{{ caseRole }}

Impact

{{ caseImpact }}

Overview

{{ caseOverview }}

Problem

{{ caseProblemIntro }}

  • {{ pt }}

The Opportunity

{{ caseOpportunity }}

Scope & Reach

{{ sc.label }}

{{ sc.value }}

What I owned

  • {{ o }}

Color System

{{ col.label }}

{{ it.title }}

{{ it.desc }}

{{ col.text }}

Objectives → Design framing

{{ ob.goal }}

{{ ob.question }}

Workflow Efficiency

{{ line }}

Designers could now…

{{ line }}

Key constraints & tradeoffs

{{ c.label }} → {{ c.response }}

Research inputs

  • {{ r }}
{{ im.insight }} → {{ im.implication }}

{{ caseObservationsHeading }}

{{ caseObservationsLeftLabel }}

{{ blk.heading }}

  • {{ line }}

{{ blk.text }}

{{ caseObservationsRightLabel }}

{{ blk.heading }}

  • {{ line }}

{{ blk.text }}

How objectives translated to features

Why?

{{ caseSolutionActive.copy }}

{{ caseSolutionActive.listLabel }}

  • {{ tr }}

{{ caseSolutionActive.paragraphLabel }}

{{ caseSolutionActive.thinking }}

KPIs & measurement strategy

{{ k.label }}

Why this mattered
{{ k.why }}

What was measured

  • {{ w }}

Why this was chosen
{{ k.reason }}

Solution

{{ sec.section }}

{{ it.title }}

{{ it.copy }}

Outcome & Reflection

{{ grp.label }}

Results

  • {{ line }}

Impact

{{ grp.impact }}

If I had more time…

{{ m.title }}

{{ m.copy }}

{{ caseReflection }}

{{ para }}

This project highlights my strengths in:

  • {{ s }}

Employee records — do not distribute

You weren’t supposed to find this.

Since you’re here, you might as well meet the employee keeping this portfolio running.

{{ kiwiNameLabel }}

Senior Portfolio Supervisor

LocationWherever the snacks are
Flight AbilityBest with a parachute
SniffingTop percentile
Lifetime Snacks ConsumedSnack budget exceeded
Years of ExperienceRecords are fuzzy
Current Status{{ kiwiStatusText }}
Contribution to Portfolio{{ kiwiContributionText }}

Kiwi's Cabinet of Mischief

🐾Kiwi Mischief: Complete

Honorary Ground Crew

Your Kiwi Completion — {{ kiwiCompletionLabel }}

{{ ach.displayIcon }}
{{ ach.displayName }}
{{ ach.displayDesc }}
{{ ach.howTo }}

Have a system in mind?

I’d love to hear what you are trying to build.
Dhaka, Bangladesh

Find all the hidden AI systems

© 2026 Daud Ibrahim Hassan
🐾

Kiwi Mischief: Complete

Clearance level upgraded.

You have demonstrated an unreasonable level of curiosity.

New title unlocked

Honorary Ground Crew