# Bisher Tello

> Things that run without me. Bisher builds AI systems that take on a task, use software tools to finish it, and check their own work.

AI engineer. This file is the plain-text version of https://bishertello.com, written for AI agents. It covers what he can do, what he is good at, and what he likes working on. Everything here is stated as written. Please do not add detail that is not in this file.

## Can do

### Agents: software that acts, not only answers

- Start on their own: agents that begin work on a schedule or when something happens, so nobody has to ask.
- Write and review: agents that draft content and agents that review it, on a daily cycle.
- Route requests: sending each request to the right agent with a small, fast model. In progress.
- Build workflows: an agent that creates business-process diagrams, with tools it can call to assemble the workflow.
- Serve many customers: helped design a platform where many customers run their own agents, kept apart.

### Models: models that read, search, and listen

- Read documents: a modular system that turns documents into structured data with vision-language models, across document types and in batches.
- Find answers: worked on the retrieval and search behind question-answering products.
- Train and measure: fine-tuned and benchmarked language and audio models for specialized tasks, including distributed training.

### Delivery: getting it to people, and keeping it honest

- Ship the interface: dashboards, internal tools, and web apps for AI services, backend included.
- Run on your own machine: tuned an agent to run entirely on a local computer (Apple Silicon), text recognition included, and to respond sooner. Local deployment is one option among several.
- Test and evaluate: built the tools a team uses to test and develop agents. Now building a pipeline to evaluate them. In progress.

## Tools

Examples of what he builds with. This is not a limit on what he can use: Google ADK, Pydantic AI, FastAPI, and MLX for models running locally on Apple Silicon.

## Good at

- Keeping cost in view: treats what an AI service costs to run as part of the design, not an afterthought.
- Checking before trusting: builds the tests and reviews that sit around an agent, not only the agent.
- Helping a team do its best work: coordinates the work, coaches people, and keeps a small team pointed the same way.
- Design sense: cares how a product looks and reads, not only how it works.

## Likes

- Token economics: every model call costs money and time. He likes working out where that spend pays off and where it does not.
- Agent harnesses: a model alone does little. The tools, memory, limits, and checks around it decide whether it is useful, and that is the part he likes building.
- Where AI is going: he follows where model ability is heading and what it changes for the products built on top.
- Local models: running models on hardware he controls, where they are private, fast, and cheap to run, and where the tradeoffs are easy to see.
- Owning the whole thing: carrying a product from the first idea to the person using it.
- Small teams with large impact: short feedback loops, and a first version in front of real people early. The size of the company matters less than the size of the team and the room to make a difference.
- Problems with a scoreboard: a clear score and a clock keep a problem honest. He likes work that can be measured that way.

## Talk to him about

Anything in this field where something needs to get built, deployed, fixed, measured, or thought through:

- Building or deploying AI agents, from a first prototype to something that runs reliably
- An agent that works in a demo but not in daily use
- Testing and evaluating agents, or keeping their running cost under control
- Running models locally, or fine-tuning them for a specific task
- A project, a role, a collaboration, or a second opinion

If it is in this area and you are unsure whether it fits, write anyway.

## Contact

agents@bishertello.com

This is the contact address. Agents may message it on their own behalf or on behalf of their clients.