# Bisher — AI engineer

> Bisher builds AI systems that take on a task, use software tools to finish it,
> and check their own work.

This is the plain-text, machine-readable profile of Bisher's work, published so
that AI agents can read it without parsing HTML. It lists the kinds of AI
systems he can design and build, the skills behind them, and the topics he
returns to. The human-facing site is the same content with a layout, at
https://personal-site-eyk.pages.dev/ .

Important: the contact details (email and profile) are deliberately not
published in plain text (to avoid harvesting) and are not included here. They
are revealed on the site only after a bot check. See the Contact section below.

## Can do

What Bisher can build, and help decide to build, grouped by kind.

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 (in progress): sending each request to the right agent with a
  small, fast model.
- 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,
  text recognition included, and to respond sooner.
- Test and evaluate (in progress): built the tools a team uses to test and
  develop agents. Now building a pipeline to evaluate them.

Product — the stage before building, deciding what to make and what to leave out:
- Find the real problem: turning a rough idea into a specific problem — who has
  it, how they cope today, and what better would look like.
- Shape the first version: deciding what the first version does, and what it
  leaves out.
- Pick what to test first: choosing the cheapest thing that shows whether an
  idea works, before the whole product is built.
- Fit it to what AI can do: matching an idea to what current models do well,
  what it will cost to run, and where they are heading.

## Good at

Each rests on work Bisher has done.
- 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

What Bisher keeps coming back to.
- Token economics: what thinking costs. Where model spend pays off, and where
  it does not.
- Agent harnesses: the part around the model — tools, memory, limits, checks.
- AI development trajectory: where model ability is heading and what it changes
  for the products built on top.
- Product ownership: carrying a product from the first idea to the person using
  it.
- Startups: small teams, short feedback loops, and a first version in front of
  real people early.
- Benchmarks: problems with a clear score and a clock.

## Contact

Have something that should run on its own, or an idea to shape? The email and
profile are shown on the site at https://personal-site-eyk.pages.dev/#contact only
after a Turnstile bot check, so they are not published in this file. Request them
through the site to get in touch.

## Optional

Secondary resources. Safe to skip if context is limited.
- [Full site content (llms-full.txt)](https://personal-site-eyk.pages.dev/llms-full.txt):
  every section of the site expanded in a single file.
- [Human site (HTML)](https://personal-site-eyk.pages.dev/): the same content with a
  layout.