in the name of Allah sma-jafari

AI agents.
From code to production.

I build the AI agent layer for real companies.
Software, deployment, and infrastructure.

Explore my work

I’m currently responsible for building AI agents at Pricepoint.

Mohammad Ali (sma-jafari)

In the name of Allah. Hi everyone, I’m Mohammad Ali. I build AI agent systems for companies, from the agent software to deployment and infrastructure.

For me, the interesting part is making the whole system work together: giving an agent the right tools, passing information between steps, and handling the moments when something fails or needs clarification. I care about those details, from the first line of code to a running service.

My background is in computer engineering, and my PhD research focuses on AI for startup valuation. Along the way, I’ve built multi-agent frameworks and voice agents. I’m currently responsible for building AI agents at Pricepoint.

This website is a look at how I think and what I build. Feel free to explore my work, read about my background, or connect with me. Thanks for being here.

Conceptual system All layers Task → agent → tools → result. Task Runtime Release

One system.
Every layer.

From the agent software to the infrastructure it runs on.

Whole system Agent software A task uses a tool, then returns a checked result. Task Runtime Release

What the agent does.

The logic and integrations that turn a business task into agent behavior.

Define the tools.
Specify required inputs, returned data, and the errors the agent needs to handle.
Connect the steps.
Set agent roles, pass results between them, and keep the information needed for the next decision.
Test difficult requests.
Try missing details, failed tools, and unexpected responses. Decide when to retry, ask for clarification, or stop.

Illustrative example

A request is missing a customer ID. Ask which customer before calling the lookup tool, then return the matching record.

See Emerald and IDEA SPARKS

From code to a running service.

Packaging and releasing the agent system into its intended environment.

Make startup repeatable.
Package code and dependencies with a clear startup command. Supply configuration and credentials separately from the code.
Check before switching.
Start the new version in its intended environment. Exercise the request and tool paths that need to work before sending it traffic.
Keep a way back.
Retain the previous working version and document the steps to restore it if a release fails.

Illustrative example

A new version fails its startup check. Stop the rollout and restore the last working version while the failure is investigated.

Where the agent runs.

The runtime, resources, and operating environment behind the agent.

Fit the workload.
Decide how requests run, how much memory they need, and what happens when work takes longer than expected.
Limit access.
Keep credentials out of source code. Give each integration access only to the systems and data it needs.
Make failures traceable.
Connect a request to its tool calls, timings, and errors so a failed run can be located and understood.

Illustrative example

A tool stops responding. A timeout ends the wait, and the execution trace identifies the call where the request stalled.

Read about embedded AI at Suaka

Choose a layer to explore my scope.

Engineering
is my foundation.

I'm Mohammad Ali, known online as sma-jafari.

I build AI agent systems for companies, from agent software to deployment and infrastructure.

My background is in computer engineering. My PhD research focused on AI for startup valuation.

Connect on LinkedIn
Mohammad Ali (sma-jafari)

Experience

Near-Dynamics

Built an AI agent framework from the ground up and developed a voice agent that receives phone calls and handles complex caller requests.

Lab for AI Applications in Business Studies

Created a cognitive scoring model that evaluates candidates through their performance in cognitive games, helping HR teams assess specific skill dimensions.

Suaka

Developed embedded AI for a security system on an STM32 microcontroller. Implemented human-versus-animal detection in C++ from scratch under constrained resources, with alerts when a person crossed the sensors.

Systems

Emerald

Multi-agent framework

Created Emerald Core, a custom framework for building multi-agent AI systems. It decomposes complex problems into specialized agents with defined tools, roles, and interaction protocols.

Digital Transformation Assistant

Built with Emerald to support decisions using global strategies and current macro KPIs.

IDEA SPARKS

Built a multi-agent application based on Emerald to help accelerators and startup studios validate startup ideas before launch. Macro, Meso, and Micro agents evaluate different aspects of an idea.

Education

Computer engineering

BE · University of Tehran

My studies at the University of Tehran also include an MA.

Research

Research background

Notes on AI agents.

Writing about building AI agent systems.

Read on LinkedIn