akougkas.io

WTF-P

A staged research-writing workflow for coding agents.

A staged research-writing workflow a coding agent can run: a specification, an outline, section plans, bounded drafts, and review against the evidence. Released publicly as an npm package and a tagged GitHub release.

Install WTF-P View the code

The writing workflow

  1. Frame the question

    Specify the contribution and gather the evidence.

  2. Plan the argument

    Outline the paper and bound each section.

  3. Draft a section

    Write inside its plan and available context.

  4. Review against evidence

    Check the section against its purpose and sources.

The workflow makes the question, the evidence, and the section boundaries explicit before drafting, and review returns to those decisions.

The question

Language models can produce a plausible paragraph almost instantly. That is not the same as developing an argument, locating its evidence, controlling its scope, or noticing when one section quietly contradicts another.

WTF-P started from a recurring problem in research work: the blank page was only the visible symptom. Underneath it were missing decisions about the question, contribution, evidence inventory, narrative, venue, and ownership. Could an AI-assisted writing tool make those decisions explicit before asking for prose?

The workflow bet

The bet is to treat writing as a staged system. A project begins with a specification. The paper becomes an outline with an argument and word budget. A section receives its own plan and bounded context. Drafting is followed by a review that works backward from the section’s stated purpose and available evidence.

This is less magical than “write my paper,” and deliberately so. It gives the human researcher places to inspect and change the reasoning. It also makes failure more local: a weak paragraph can point back to a missing source, an incoherent section plan, or a project claim that was never resolved.

What shipped

WTF-P is a public npm package and GitHub release, first published as v0.5.0. Its installer can place a common writing workflow into Claude Code, Gemini CLI, or OpenCode. The repository includes commands for project setup, planning, drafting, review, structure, and export; specialized agent roles; tests; a changelog; and a continuous-integration check at the released commit.

Installation, updates, diagnostics, runtime differences, and user-owned configuration all became product questions. Solving them changed the work from a clever instruction into a tool another researcher could try and remove.

My part, and why I built it

I created WTF-P from the writing and mentoring workflows around GRC and maintain its architecture, installer, commands, and release path. The deliberately blunt name comes from deadline energy, but the system underneath it is patient: decide what a section must accomplish, gather the evidence it may use, write inside that boundary, and review the result.

This is also entrepreneurial practice. I saw a repeated operational problem, formed an opinion about how it should work, packaged the opinion, and exposed it to public use. The aim is to make more of a team’s research judgment visible at the moment it is needed. The judgment stays with the team.

The boundary

WTF-P is pre-1.0 software. Its workflows do not verify that a scientific claim is true, make a weak source authoritative, or turn generated text into the author’s considered argument. Citation grounding and review steps can create better checkpoints; they cannot substitute for reading the sources or owning the final claim.

The released package also represents one opinionated workflow, not a universal model of scholarship. Disciplines, venues, teams, and individual writers organize evidence differently. The useful test is whether the structure helps a researcher see and improve the work, not whether every paper follows the same sequence.

What I am learning

  • Context quality depends more on explicit boundaries than on putting the entire project into one prompt.
  • Section isolation is useful only when the shared argument remains visible.
  • Installers and diagnostics are part of an intellectual tool because they determine who can actually try the idea.
  • The right role for an agent is often to maintain a demanding process, not to impersonate the author.

Code, releases, papers, and records

  1. code

    WTF-P repository

    The installer, writing workflows, agents, tests, and public development history.

  2. release

    WTF-P v0.8.1, November 8, 2026

    Makes the CLIO Coder desk the reference implementation of the author gates and record contract, and requalifies all seven host integrations on the packed release. v0.8.0 added that desk as its own extension, with planning records checked against their schemas and section word counts measured one way; v0.7.0 added an optional CiteNexus backend for citation lookup.

  3. package

    WTF-P on npm

    The versioned package that installs the workflow for supported coding assistants.

Related notes

  1. tutorial

    A closed loop for AI-assisted research writing

    Install CLIO Coder, WTF-P, and CiteNexus on Linux and run a first supervised writing session: the agent keeps the bookkeeping, every citation stays traceable to its source, and the author keeps the judgment.

    12 min
  2. essay

    Why your AI infrastructure is already obsolete

    Obsolete means built on assumptions that no longer hold. Seven such assumptions behind current AI infrastructure, and the dissertation problem hiding in each, from a doctoral seminar at Illinois Tech.

    8 min
  • 2023–present

    CLIO Coder

    A local-first coding agent with typed tools, bounded workers, and receipts.