R015 · Agent principles and patterns › Workflows over agents

Psychology of programming and deterministic workflows

Read the original

deterministic-workflowspsychology-of-programmingagent-workflowscontext-engineeringmental-modelsagent-harness

TL;DR

Source: a 105-second Facebook reel by Jake Van Clief (creator of Clief Notes and the Interpretable Context Methodology, ICM), captioned "everyone wonders why I did my master's thesis on the psychometrics of language models". Published around September 2026.

What the video says

The reel has no written post beyond the one-line caption; the argument is in the spoken track, burned in as one-word captions. In order:

  1. Thesis (0:00 to 0:04). "For the next 10 years, psychology is going to be more important than programming."

  2. Credential (0:04 to 0:10). He is in Dubai for three weeks, contracted by "some big companies" specifically on this concept.

  3. Historical hook (0:10 to 0:43). Programming and software engineering have "always been about psychology". He reads from Weinberg's 1971 book: programming is not only human behaviour but complex human behaviour; under 20% of code is aimed at the problem itself; much of the other 80% could go entirely, through psychological rather than physical change.

  4. Translation to agents (0:43 to 0:54). Psychologically, "agent" is a naming convention. People write hundreds of lines of code just to get one agent to the right place at the right time.

  5. Diagnosis (0:54 to 1:07). Microsoft Copilot and custom GPTs were "the rage" last year, but were the psychologically wrong thing to build: the frame you adopt changes what you are even programming for.

  6. Reframe (1:07 to 1:21). Remove "agent" from the goal and think about automating a workflow; you route completely differently. Many people use CLAUDE.md or AGENTS.md to route to a series of instructions that are just Markdown files. The screen shows a workflow diagram with the rule every arrow needs a verb: reads, uses, writes, and a node labelled "Owner reviews" pointing to a gaps.md file.

  7. Mechanism (1:21 to 1:35). Instead of coding, or using AI to create new code, use the AI as the runtime for the instructions, "like a compiler on top of the software we've built".

  8. Close (1:35 to 1:45). Switch your psychological frame of where the information is and why you are using the tool, and you stop building the wrong things and start building things that last.

All quotes are short excerpts from the captions; the rest is paraphrase.

The Weinberg source

Gerald Weinberg's The Psychology of Computer Programming (Van Nostrand Reinhold, 1971) is the founding text of the field: programming as a social and cognitive activity, "egoless programming", and the idea that teams, not tools, set the limits. The passage on screen walks through a programming example and concludes that most of the code existed because of how the problem was understood and divided, not because the problem needed it.

What it supports:

What it does not support:

Architecture: agent frame vs workflow frame

The video's core move is a change of design unit. In the agent frame you build a persona and then the code that keeps it on track. In the workflow frame you write down the route and the step contracts, and the model executes one narrow step at a time.

Same job, two frames: the model decides the route, or the files doAgent frame"An agent that does X" (persona, goal, tools)Orchestration code: memory, handoffs,tool routing, retries, when-am-I-done logicModel chooses the next step each turnHundreds of lines to steer one agent to theright place at the right time (Weinberg's 80%).Workflow frameCLAUDE.md / AGENTS.md: route table per jobStep 1 .mdreads input, usesscript, writes out1Step 2 .mdreads out1,writes gaps.mdOwner reviews (gate)Model = runtimeEvery arrow has a verb: reads, uses, writes.Determinism = fixed route + scripts + checks,not the model reading Markdown.
agent frame vs workflow frame

The right-hand side is what the on-screen diagram in the reel shows: steps as Markdown files, arrows labelled with verbs, an owner review that writes gaps to a file. What turns it from "a workflow" into a deterministic one is everything the model does not decide: the route table, the scripts and the checks.

Tradeoffs and failure modes

Where determinism actually comes from. A model reading Markdown instructions is a stochastic interpreter: the same file and the same input can take different paths, skip a step, or write to the wrong file. A workflow becomes deterministic only to the degree you remove decisions from the model:

LayerDeterministic ifTypical leak
Route (which step runs next)encoded as a fixed table, state machine or engine, not inferred from prosethe model decides it is "done" early or loops
Step contracteach step names its inputs and its single output file ("every arrow needs a verb")step writes extra files or edits upstream ones
Repeated workturned into a script the model callsthe model re-derives the same transform each run, slightly differently
Exit checka validator, test or schema check that fails the stepan LLM self-check that always passes
Human gateplaced at irreversible or judgment-heavy steps ("Owner reviews")gate on every step, so people rubber-stamp

The video's "compiler" metaphor overstates the first row. A compiler is a deterministic function of its input; the model is closer to a junior operator following a runbook. The design goal is to make the runbook so narrow that variance does not matter.

Where the reframe wins.

Where it loses.

Review checklist

Use this when someone proposes "an agent" for a job:

Source notes

Connections

See R015 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.