SG.

HOW IT WORKS / VERSION 1.0

Give AI a process.
Keep the evidence.

The AI Workflow Method turns an objective into stages, checks and a record you can pick up again. The result comes with a way to understand how it was reached.

Drawn from the Research Engine. Portable beyond research.

01 / THE PROCESS

One objective.
A traceable way forward.

  1. 01

    Define

    Objective, inputs, constraints and what success means.

  2. 02

    Plan

    Stages, deliverables and the decisions a person must approve.

  3. 03

    Execute

    Do the authorized work. Save sources and real outputs.

  4. 04

    Verify

    Check against criteria. Record defects and correct them.

  5. 05

    Deliver

    Share the result, evidence, limits and next action.

A failed check sends work back for correction.
A checkpoint preserves the record; resuming starts by checking it.

02 / WHY A METHOD

More than
the next answer.

A normal chat can use these practices too. The method makes them explicit, repeatable and easy to carry between projects.

01

Criteria before conclusions

Define what will count as success before accepting an output.

02

Evidence attached to progress

“Complete” needs a real artifact and a check. Instructions alone do not complete work.

03

A record that survives the chat

Keep versions, sources, decisions, corrections and a clear place to resume.

04

Human decisions stay visible

Independent review and approval to publish remain distinct from an AI check.

03 / WHAT EXISTS TODAY

Clear about the machinery.

EXISTING RESEARCH ENGINE

The website prepares a handoff.

It generates research instructions and a downloadable project checkpoint in your browser. You give those to an execution agent. The website itself does not conduct research or run a background job.

NEW IN METHOD v1.0

A portable guide and local helper.

Schemas, a master template, domain playbooks and an optional local helper record ordered gates, artifact hashes, retries and resumable state. The helper is separately operated; it is not connected to the website.

Review records rely on an honest operator; the helper does not authenticate people or establish scientific correctness. Autonomous execution, live domain integrations and remote synchronization are not included.

04 / A WORKED EXAMPLE

Small scope.
Honest status.

A source-reporting audit checks a few claims in the accessible abstract of Attention Is All You Need. The note records the source version, exact locator and what was checked.

Read the example and limitations

EXAMPLE CHECKPOINT

Design
Bounded reporting audit
Evidence
Versioned source + hashed report
Status
Verification pending
Human approval
Not recorded
Next action
Review the exact report

Source claims were transcribed and checked. Experiments were not reproduced; no completed literature review is claimed.

05 / MAKE IT YOURS

Same process.
Different playbook.

The controller tracks the work. A domain adapter defines the tasks, evidence and human decisions. These adapters are templates, not live service integrations.

Research

Question → evidence → defensible draft. Keep source-linked extraction and independent review.

Career

Approved facts → job fit → application draft. Approve each submission.

Engineering

Design basis → calculations → checks. Keep units, assumptions and qualified review.

Website

Baseline → focused change → verified preview. Preserve behavior and a rollback path.

Business development

Public sources → fit assessment → outreach draft. Review claims and approve sending.

Start with one bounded task.

  1. Download the guide, master template and example request.
  2. Choose an adapter. Set the inputs, criteria and approvals.
  3. Give the package to your agent; save evidence and checkpoints as it works.

Keep this method's state separate from the Research Engine's existing project JSON. They use different schemas.

VERSION HISTORY

v1.0.0

November 7, 2026. General method extracted from Research Engine v2.0, with schemas, a reusable template, domain adapters, an honest worked example and a tested optional local helper.

To share: link to this page and include the version. To record a demo: show the objective, handoff, evidence and checkpoint. Review the recording for private data before publishing.

Try the Research Engine