what did we give the agent to start the research?
  1. step-by-step instructions
  2. a goal, a photo, a text file
  3. a list of websites to visit
  4. a program we wrote
where did the agent do its work?
  1. all of it on the laptop
  2. files here, model in the cloud
  3. in the browser, like chatgpt
  4. on a university server
8 sub-agents researched at once. who decided that?
  1. our prompt told it to
  2. the agent itself
  3. a setting in the app
  4. it always works that way
the agent asked us which file held the milestones. what does that show?
  1. it could not read the file
  2. it noticed a mismatch
  3. it asks before every step
  4. it had forgotten the prompt
part 2
what is an agent?
who did the work while we watched?
image: ai-generated (gpt-image-2.5-flare)

chatbot vs. agent

a chatbot only answers, while an agent acts on its own.

a working definition

an AI agent runs tools in a loop
to achieve a goal.

workflow or agent?

the goal and the model

what we saw: a few sentences, a photo, a text file.

tools

what we saw: it listed the folder, downloaded papers, wrote files.

the loop

what we saw: it read a source, then decided what to do next.

context window

what we saw: "context 14 %" in the corner of the app.

plan and instructions

what we saw: "show me your plan. wait for my go."

sub-agents

what we saw: "research by 8 agents", and nobody asked for that.

all of it together

the model decides, the tools carry it out, and the loop keeps running until the goal is reached.

the harness

the same model in a different harness is a different agent.

models and apps

where does it run?

see also: open models, an LLM on your own laptop.

why now?

the length of tasks agents can finish doubles every few months.
an agent acts with your permissions
it can read every file you can read.
it can run every command you can run.
it can publish to the internet.
image: ai-generated (gpt-image-2.5-flare)
we open the loop.
layer by layer, down to the model and back.
image: ai-generated (gpt-image-2.5-flare)