The Field Guide

How WorldbyFlow works.

The front page tells you what this is. This page shows you how it thinks — the method, the framework, the catalog, and what your research becomes once you have it.

The MethodThe FLOW FrameworkThe CatalogFormatsQuestions
Chapter I · The Method

Ask. Ground. Structure.

Every scan — ninety-plus of them, across twelve domains — runs the same three-step research discipline. The steps are why the output is trustworthy.

01

Ask

Bring whatever you have — a headline, an entity, a scenario, a pasted URL, or a plain question. Each scan applies a specific analytical method to it, rather than whatever a chat model felt like producing that day. Not sure which scan? The Router reads your question and picks one; the Planner designs a linked sequence toward a goal.

02

Ground

The scan runs against live search and domain-specific data — SEC EDGAR for finance, FRED for economics, GDELT for defense, NOAA for climate, OFAC for sanctions screening, and more. The grounding constrains what the research can claim: quantitative statements are anchored in time, names and titles are checked, and what can’t be verified is flagged rather than smoothed over.

03

Structure

What comes back is not a wall of text. It’s finished research with named fields — what happened, what it means, who’s exposed, what to watch — sized by the FLOW framework and ending in the sources it consulted, each one a click from the claim it supports. Structured output can be handed to a board, a class, or a teammate without translation.

Chapter II · The FLOW Framework

Every situation gets sized.

Two axes decide everything: SCALE — the organizational weight of a situation (dollars, authority, stakeholders) — and COMPLEXITY — how hard the right call is to see and to execute. Where a situation lands tells you what to do with it: delegate, resource, analyze, or mobilize.

One scale, three voices. The same letter answers a different question depending on the scan. On an Event or Entity scan it sizes a connection you’re interpreting; on a Risk Scan, Action Plan, or Options it sizes an action you’d be executing; everywhere, it sizes how much of your attention the thing deserves.

Routine & ContainedLow scale · low complexity
Delegate it.
Sizing itSmall stakes, easy to understand. Straightforward, with limited wider impact.
Reading a connectionA limited, straightforward connection — no hidden layers or surprising implications.
Executing an actionSimple to execute. Hand it to a line owner and move on — no executive attention required.
Significant but ClearModerate scale · low complexity
Escalate and resource it.
Sizing itMeaningful stakes, but the situation is well understood. The implications are evident.
Reading a connectionReal weight — resources, decisions, stakeholders — but what it means and where it leads is clear.
Executing an actionNeeds real resourcing and a clear owner, but the organization knows how to do this kind of thing.
Strategically ComplexSmaller scale · high complexity
Understand before acting.
Sizing itMeaningful stakes with real uncertainty — the situation could unfold in multiple directions.
Reading a connectionAmbiguity, competing interpretations, interconnected consequences. The key question tells you where to start.
Executing an actionThe right approach isn’t obvious — get aligned on what success looks like before mobilizing.
Large Scale & SignificantLarge scale · any complexity
Senior attention, now.
Sizing itVery high stakes. The scale alone makes this one of the most important items in the scan.
Reading a connectionWhatever the mechanics, the sheer magnitude at stake makes this one of the most consequential connections.
Executing an actionExecutive authority, cross-functional coordination, major resources — however simple it looks.
ExtraordinaryNo precedent · both axes
Rare by design.
Sizing itUnprecedented — this changes the rules, not just the situation. At most one or two per scan.
Reading a connectionOutside familiar patterns. Historical comparisons are limited; standard frameworks may not fully apply.
Executing an actionNormal playbooks don’t apply — a purpose-built approach with direct principal ownership.
Sizing it — every scanReading a connection — Event & Entity scansExecuting an action — Risk · Action Plan · Options
The Three Rules
1.

A FLOW C cannot exist at large scale. High complexity at large scale is a D — the scale decides.

2.

At large scale, scale alone drives the classification. You don’t debate the difficulty of a billion-dollar problem before escalating it.

3.

A and B differ only in scale. Both are low complexity — the question is just how much weight rides on the routine call.

One vocabulary across every domain — a FLOW D in finance reads the same as a FLOW D in policy. That’s the point: the classification travels, so your judgment does too.

Chapter III · The Catalog

Grouped by what you’re trying to do.

Six ways in, then the rest of the catalog organised by the move you’re making — establish the background, map the argument, work the record, analyse the connections, decide what to do. This is the Home domain in full; every other domain carries its own set, renamed in its own language.

Start here

The six ways in
Event Scan — maps who an event actually affects — not just who’s in the headline
Ask — a direct, grounded answer to a bounded question
News Search — pull any thread, any time
Water Cooler — what practitioners and observers are actually saying
Market Research — the full read of a market — every sizing claim graded with its issuer named, and where value is moving
Inquiry — open-ended research where every material claim is adversarially re-checked before it’s allowed to stand

Explore

What could happen, and what else is out there
Scenario — the full space of what could unfold, with probabilities
Uncertainty Map — what is genuinely unknown — every material uncertainty graded by whether and how it can actually be reduced
Options — your actual choices, with tradeoffs, timelines, and risks
Compare — two things side by side, on the dimensions that decide it
Landscape — the whole competitive field, not just the headline player
Precedents — the historical analogues, and how closely they actually fit
Innovate — grounded solution ideas for a problem, each anchored to a real precedent and tagged by how proven it is

Background

The raw material, worked over
Chronology — how the situation developed, dated and sourced
Follow the Money — who pays, who profits, through which channels
Funding Map — who actually funds a field — documented programs and awards, amounts as disclosed
Case File — the documented legal record — proceedings by posture, what a court decided kept apart from what is only alleged
Budget Anatomy — a budget taken apart line by line — authorization never confused with appropriation
Key Players — the actors who matter, and what leverage each one holds
Who's On It — who has actually committed what to a live situation — a pledge is never counted as a presence
How It Works — the mechanism — inputs, stages, failure modes
Trend Trajectory — where a named trend actually sits on its arc, and what the evidence says comes next
Early Signals — the pre-mainstream observables at the edge of a space, each with a falsifier
Innovation Check — what has actually been demonstrated, graded against what is being claimed
Research Pulse — what the research layer has produced lately — and the reception it genuinely earned
By the Numbers — the key figures, each one sourced and dated
Why It Changed — why a published number actually moved — starting with whether the counting changed rather than the world

Debate

Where the disagreement actually is
Positions — who supports or opposes it, and the stated reason each gives
The Arguments — the case for and against, both steelmanned
Myths & Misconceptions — what people keep repeating, corrected against the record
Consensus Check — what the named forecasters expect — reported as a spread, never averaged
Poll Check — what the public actually thinks — every figure with its pollster named, the spread never averaged

Cases

The record itself
Scene — one pivotal moment reconstructed, strictly from what’s documented
Voices — real quotations, verbatim and exactly sourced — or omitted
Primary Documents — the operative record — filings, rulings, contracts, quoted with pinpoint citations
Case Study — one real instance worked end to end, with the lessons it carries
Playbook — the actionable steps the research implies, with the pitfalls
Decision Review — was the call right on what was knowable at the time — graded separately from how it turned out

Analyze

Connections, entities, and your own thinking
Entity — every intersection mapped — who they touch, how, and what to watch
Person — an individual profiled to the bottom
Profile — one entity through a chosen lens — strengths, pros and cons, or roads and barriers
Relations — how the entities around an event connect to each other
Relationship — the tie between two specific parties, in both directions
Idea Stress-Test — your own idea against the record — every load-bearing assumption graded, with the cheapest test that would settle it
Convergence — where two forces actually meet, anchored on things already happening
Track Record — past claims and forecasts against what actually happened
Why They Did It — what a move was actually for — checked first against whether they even had a choice, then their own stated reason, then the objectives the record supports
Method Study — how a named method actually works in practice — what it really is, every claim graded by the evidence behind it, the real step-by-step spine, and who uses or abandoned it
Options Appraisal — your own shortlist of 2–8 alternatives scored on your own criteria — the set closed before any option is examined, every cell earned from a named record, and the close names what would flip the ranking
Fact Grid — your own subjects across your own fields, every cell a graded fact with its source and date or an honest not-found — conflicts carried with both values, and the whole grid exports straight to CSV
Read Grid — your own subjects across your own questions — strategy, weaknesses, who they are really for — every cell a reading anchored in named observable behaviour, with what each subject says about itself kept separate from what the record shows, so you can see where the two come apart
Document Breakdown — bring a document you have — a report, memo, contract, whitepaper, pitch — and get the full decode: what it presents itself as, every material claim checked against the live record, its figures verified, its assumptions surfaced, and the research it opens
Synthesis — reasons across your prior scans and names the tensions between them

Markets

A market, read whole
Buyer Research — who actually buys, from documented behavior — never an invented persona
Supply Chain — what feeds it, mapped stage by stage, each one tagged documented, representative, or opaque
Logistics Read — how it actually moves — legs, nodes, constraints and costs, every figure tied to the record it came from
Operator Dossier — the organization that operates it, and what it ACTUALLY controls versus what merely carries its name
Regulatory Map — every rule that governs it, each with its real instrument and honest status
Deal Flow — who is buying whom — terms as disclosed, rumors labeled as rumors
Pricing Read — what things actually cost — every price verbatim from a named source, dated and scoped
Partnership Map — who is aligned with whom — documented partnerships only, an MOU never dressed as a JV

Act

What to do about it
Risk — where things break — before they break
Plan — phased steps, owners, timing, decision gates
Opportunity Brief — one solicitation, documented — requirements verbatim, honest stage, incumbency from the record
Sentinel — the specific early-warning signals worth watching
Catalyst Calendar — the dated events ahead that could move this, each with its basis
Briefing — the executive summary, written for someone who has to decide
What You Need — the tools, data, capabilities, and funding an objective needs — each tied to a real solution
Vulnerability Assessment — a competitor's exploitable weaknesses from public info — ranked by how pressable each is, with the angle it opens

Tools

Frameworks, on demand
Thinking — 25 structured frameworks — SWOT, pre-mortem, scenario matrix, ACH, Wardley mapping, and the rest — run against your subject

Don’t know which one you need? The Router reads a plain question and picks one; the Planner takes a goal and designs a linked sequence. Every completed scan also opens onto its own follow-ups — ask it a question, re-check what has changed since, red-team its judgments, or push a signal onto your watchboard.

Chapter IV · Formats

One scan, many shapes.

A scan isn’t trapped on the screen you ran it on. Every completed scan converts to the shape the moment needs.

Readevery scan unfolds into a long-form prose narrative when you’d rather read an essay than a structured scan · free on paid tiers
Listena spoken analyst walkthrough, delivered to a personal podcast feed · 1 credit
Episodean 8–10 minute two-voice episode — host and analyst working through the scan — with a subtitled video for YouTube or LinkedIn · 5 credits
Summary Decka vertical carousel for TikTok, Reels, LinkedIn or X, written from the scan and rendered ready to post · 2 credits
Visual carda dashboard-style image built from the scan’s own structure, ready to share · free on paid tiers
PDF & Markdownprint-grade documents and portable Markdown for Slack, Notion, or email · free
Sharea public link anyone can read, or a private hand-off to another WorldbyFlow user with a thread attached · free
Books & reportsThe Studio turns an objective into a planned, researched, written and edited book — or a report, situation report, briefing book, or course · flat rate per build
Chapter V · Questions

The things people ask.

How is this different from a chat box?
A chat box gives you a paragraph you have to re-read to decode, and it forgets the conversation. WorldbyFlow gives you structured output — named fields, classified weight, listed options, specific watch signals — and it holds onto your work. Prior scans quietly inform new ones, so the second time you look at a topic the research is sharper than the first. And each scan applies a specific method (Event Scan, Scenario, Risk, Landscape) rather than whatever the model felt like producing that day.
Does this work if I’m not an analyst?
Yes — it’s built for anyone who has to make sense of a complex situation. Educators turn scans into lesson plans. Nonprofit leaders use them to brief boards. Public-sector workers frame policy memos. Founders read a market move. Students break down a topic for a paper. The tools produce structured output with plain-language labels you can hand to a board, a class, or a teammate without translation.
How is this different from a news aggregator or a research database?
Aggregators deliver content — articles, tickers, reports. WorldbyFlow delivers structure over content: events pre-classified by scale and complexity, broken into who’s affected and how, and connected to scenarios, risks, options, and decisions. An aggregator tells you what happened; a scan tells you who it affects, how much to weight it, what comes next, and what to do. And whatever you analyze stays on your workbench — you don’t lose the thread between sessions.
Where does the data come from?
Scans ground against live Brave Search (news + web + discussion threads) and domain-specific APIs — SEC EDGAR for finance, FRED for economics, GDELT for defense, NOAA for climate, FDA for health, OFAC for sanctions screening, and more. The grounding constrains what the model can claim, alongside prompt-level disciplines built into every analytical scan: temporal anchoring on quantitative claims, anti-hallucination rules on names and titles, and scholarly-source rules where applicable. Every analytical scan cites the web sources it consulted so you can verify the grounding yourself.
Can I export or share what I get?
Yes. Every scan exports as a print-grade PDF or portable Markdown, and can be shared via a public link or directly with another WorldbyFlow user, who can reply in a thread on it. Paid tiers also get prose narratives, audio walkthroughs on a personal podcast feed, two-voice episodes with a subtitled video, social carousels, and shareable visual cards. Approved books export to EPUB and KDP-ready PDF. A public link is unlisted by default; you decide per page whether search engines may index it.
What do credits cost in practice?
Four paid tiers, and every scan is unlocked on all of them — the difference is monthly credits and how many research projects you can keep open. Standard is $10/month for 20 credits and Premium $25/month for 60, which covers regular analytical work. Pro ($50 for 125) and Studio ($100 for 275) are for turning research into finished work: a full book or report runs on about a month of Pro, roughly two on Studio. Most scans cost 1–4 credits depending on depth — light scans are 1, core scans 2, the search-heavy building blocks and flagship reasoning (Scenario, Risk, Idea Stress-Test) 3, Plan and Synthesis 4, and multi-step entity work 5. Inquiry is the deliberate exception at 15: it plans its own research angles, runs each one separately, then tries to REFUTE every material claim before letting it stand, so one Inquiry is a dozen model calls and a verification pass rather than one. Unused subscription credits bank while you stay subscribed, and credit packs are available if you run out mid-month.

Enough reading. Go look.

The preview is the real product with real research — no account, no card. Pricing, when you want it, is one page over.

Enter the preview →See pricing