reload.wtf
← Blog
#agents#devtools#ai

Agentic development is a loop, not a chatbot

Chat completes text. Agents close a loop: plan, act with tools, observe, verify, repeat.

Most “AI coding” is still chat with extra steps: you paste context, it emits a patch, you run it.

Agentic development starts when the model is allowed to act, then read the result, then act again without you re-pasting the world every turn.

The loop

goal
  → plan (optional, often implicit)
  → tool call (edit, shell, search, browser)
  → observation (diff, test output, HTTP status)
  → update beliefs
  → next action or stop

If there is no observation channel, you do not have an agent. You have autocomplete with better marketing.

What changed vs Copilot-style assist

AssistAgent
Unit of worknext tokens / next edita goal that may span many steps
Feedbackyoutools + environment
Failure modewrong suggestionwrong trajectory (keeps digging)
Valuespeed of typingspeed of closing the loop

The hard part is not “smarter model.” It is bounding the loop so it converges instead of thrashing.

The four primitives

  1. Tools — filesystem, shell, git, browser, APIs. No tools → no agency.
  2. State — working tree, branch, env, open PR. Agents corrupt this silently.
  3. Policy — what it may touch, what needs approval, max steps/cost.
  4. Verify — tests, typecheck, lint, smoke URL, “does the button still work.”

Skip verify and you are automating confidence, not correctness.

Decision rule

Use an agent when the task is:

Keep it as chat when:

Agentic development is software engineering with a non-deterministic intern that types very fast. The loop is the product. The model is just the planner inside it.

get new posts

Occasional notes on agentic development. No spam.