SUN · 9:02 PM
SUN · 9:02 PM

It’s 9 PM. The literature review is due Monday.

Alex has forty tabs, a chat that stopped making sense at message thirty, and six hours of battery. The one answer that mattered is buried four tangents deep.

green space + mental health, moderating factors?
Socioeconomic status significantly moderates…
wait, what about measurement methods?
Good question — most studies use self-report…
going back to the moderators thing —
⋯ 30 messages later, still scrolling

She closes the tab. Starts over — differently.

9:14 PM

One question, asked differently.

9:31 PM

The fork

Section two holds the claim her whole argument leans on. Do what Alex did — select the sentence.

Studies frequently show that individuals with greater proximity to or more frequent use of green areas report lower rates of depressive symptoms and higher levels of self-reported happiness.

ASK AI · ON THE HIGHLIGHTED SENTENCE

The strongest citation is White, Alcock, Wheeler & Depledge (2013, Psychological Science) — a fixed-effects analysis of the British Household Panel Survey, tracking ~10,000 households over time. Because it follows the same people as they move to greener or less-green neighborhoods, its panel design controls for the obvious confounder — that happier people simply choose greener neighborhoods — far better than a cross-sectional study could.

GO DEEPER · MODERATING FACTORS

A landmark 2019 meta-analysis of 1.2 million participants found that living within 300 meters of green space cut depression incidence by 12–16%, an effect that held even after controlling for income, physical health, and baseline mental health status. Green environments reduce cortisol and raise BDNF, promoting the hippocampal neuroplasticity that’s consistently reduced in clinical depression. But the benefit is not evenly distributed: lower-income and minority communities face a "green gap" — fewer parks, lower-quality vegetation, less perceived safety — so the antidepressant potential of green space is often least accessible to the populations at highest depression risk. Urban planners increasingly treat green infrastructure as a public health intervention, not just an aesthetic one.

Every tangent becomes its own node. Nothing buries anything.
10:05 PM

The right brain for the branch

×1
GO DEEPER · MODERATING FACTORS · CLAUDE HAIKU

A landmark 2019 meta-analysis of 1.2 million participants found that living within 300 meters of green space cut depression incidence by 12–16%, an effect that held even after controlling for income, physical health, and baseline mental health status. Green environments reduce cortisol and raise BDNF, promoting the hippocampal neuroplasticity that’s consistently reduced in clinical depression. But the benefit is not evenly distributed: lower-income and minority communities face a "green gap" — fewer parks, lower-quality vegetation, less perceived safety — so the antidepressant potential of green space is often least accessible to the populations at highest depression risk. Urban planners increasingly treat green infrastructure as a public health intervention, not just an aesthetic one.

The branch that matters gets the sharper mind. She’s paying per thought, not per month.

10:40 PM

Receipts

A January 2025 meta-analysis of 78 studies found nature exposure cut salivary cortisol by 21%, with the largest effect at 20–30 minutes of exposure. Heart-rate and autonomic findings are even more consistent — pooled RCT evidence shows an effect size of −0. 60 on heart rate, and a 2025 review of children and youth reinforces the same shift toward parasympathetic dominance. But a July 2024 evidence-grading overview found no pooled association with cortisol specifically — a reminder that "confirmed" findings can still be contested at the effect-size level, even as mood and heart-rate effects hold up.

11:47 PM

Two hours. Not a transcript — a map.

🌳
ROOT
Urban Green Space & Mental Health
drag to pan
MON · 12:56 AM

The mix

She stops branching and starts combining. Five branches, one question:

Select 2–6 nodes — including the ones you made.
🌳
ROOT
Urban Green Space & Mental Health
drag to pan
0 / 6 SELECTED
MON · 8:15 AM

It survives the night

Access to urban green space is consistently associated with reduced stress, improved mood, and lower depression risk across dozens of observational studies.

https://forkai.in/?sk=GfOPbyzL_s7Gr9sVqfUIYLOnno-gf4gzArRaFUIJGZg

If they sign up later, their branches follow them.

№4 — It ends as notes in Notion, not a transcript you’ll never reopen.

MON · 8:15 AM

The bill

FORK AI — SESSION RECEIPT
SUN 9:14 PM – 11:47 PM
1× root question$0.02
2× branches (Sonnet)$0.14
1× branch + web search$0.07
1× advisor branch (guest)$0.02
1× synthesis (Mixer)$0.03

TOTAL$0.34

“No subscription was harmed.”

Illustrative estimate — actual cost varies with models and question complexity.

Price your own nights

Typical model tier
Claude Haiku tier — Gemini, DeepSeek, and GLM are typically cheaper still.
$/month
$20 is just a common flat-fee reference point for illustration — edit it to match whatever you’re comparing against.
About $0.93/month with fork ai’s pay-as-you-go credit, at 40 questions/month on the fast tier.
That’s about $19.07 less than a flat $20.00/month plan.
Your free $5.00 signup credit covers about 215 questions at this tier before you’d need to add credit.

Estimate based on a typical multi-section answer (~1,500 input / ~2,800 output tokens) — your mileage will vary with question complexity and model choice. Not a guarantee.

11:59 PM — problem set due, three branches, $0.06
A Tuesday — literature review, forty branches across a week, $1.80
Always — research that lands in Notion, not in a transcript you’ll never reopen.
Fine print

No — your first session is free, up to 5 nodes, no account needed. Sign up later and any guest branches you made are automatically yours.

WHAT THE NIGHT PROVED
№1 — A research flow you can’t get lost in. Sections, not scroll.
№2 — Each branch carries only its own thread. Cleaner context in, sharper answers out.
№3 — The structure is the interaction: highlight → branch → node.
№4 — It ends as notes in Notion, not a transcript you’ll never reopen.
№5 — The Mixer: combine ideas → arrive at the answer.
It’s 9 PM somewhere.
Try fork ai free
Ask once. Branch forever.
No signup needed for a first session