A workspace for community research

TrendSights

Advanced community-level insights.
In less time.

Answer local questions with public data and AI-assisted research. Create maps, notebooks and publishable briefs with sources and methods attached.

Explore the researchRequest beta access

For researchers, planners and community teams.

A real study · King County, Washington

Where did severe crashes increase?

Severe City Street crashes in Seattle, Bellevue and Tukwila, aggregated into one-kilometer cells for 2021–2023. Darker cells contain more reported crashes.

One finding · Seattle

Severe City Street crashes

179

2021

259

2023

+80 reported crashes

A reason to investigate roads, workplaces and local conditions.

WSDOT records · 2021–2023 · Three-city study in King County. Counts are not adjusted for travel exposure.

Inspect the map and sources

Ask a local question

Where did severe crashes rise in King County’s three-city study?

Connect the evidence

Inspect crash records alongside Census resident and workplace context.

Share a reviewable answer

Follow the same question through maps, a notebook and a published brief.

One question, connected outputs

Follow the question. Inspect the work.

Where did severe crashes increase? Explore the King County study through maps, an executable notebook and publications with sources attached.

Published research · Seattle, Bellevue and Tukwila

See crashes in their community context.

The crash counts raise a question. Compare where residents live and people work across Seattle, Bellevue and Tukwila, with source definitions beside the maps.

Explore the map study

Maps with their source context

Published maps comparing resident density and workplace primary job density in Seattle, Bellevue and Tukwila.
Actual study artifact · ACS resident context and LODES workplace jobs

Published King County artifacts and a reproducibility notebook built from the study tables. Available outputs depend on the workflow.

The research protocol

CRISP-DM, made practical.

Follow the King County crash study from a three-city question to published evidence. Six connected stages, with human review along the way.

01 · Business Understanding

Define what you need to know.

Investigate severe city-street crashes in Seattle, Bellevue and Tukwila, with a 2021–2023 focus.

What you carry forward
One question, three cities and a defined study period.
Published King County study map locating Seattle, Bellevue and Tukwila and the severe City Street crashes included in the research scope.
King County study · Three-city scope, 2021–2023View full size

Revisit earlier stages as evidence changes. These published King County artifacts illustrate the CRISP-DM process; a researcher reviews findings before use.

Research perspective · 4 min read

How CRISP-DM Could Help Community Researchers Manage Insight Fatigue

Agentic research can generate findings faster than people can review them. CRISP-DM could help community researchers keep the question, evidence and next action connected.

Read the article

For Codex users · Private plugin beta

Research can start in Codex.

Use TrendSights Research skills in Codex to scope a community question, plan sources and choose a research protocol.

Continue in the TrendSights workspace to explore results, inspect notebooks and share reviewed artifacts.

  1. 01Scope the question in Codex.
  2. 02Follow a TrendSights research protocol.
  3. 03Review and share the resulting work.
Request plugin beta access

Ask about plugin access and the workflows available for your setup.

TrendSights Research · Plugin configuration preview

TrendSights Research plugin configuration header showing the plugin identity and private, unpublished status.

King County research notebook

Python · Executed example

Question

Where did severe crashes increase?

Seattle, Bellevue and Tukwila · City Street · 2021–2023

In [2] · Python excerpt

summary = [
    {"city": city, "start": annual[city, 2021], "end": annual[city, 2023],
     "change": annual[city, 2023] - annual[city, 2021], "total": totals[city]}
    for city in cities
]

Executed output · Severe crash counts

City20212023Change
Seattle179259+80
Bellevue2021+1
Tukwila1214+2

Reconciles all 751 mapped events. Counts describe reported crashes, not travel-adjusted risk.

Reproducibility example from published study tables. Download notebook (.ipynb)
Actual private plugin configuration in OpenAI Platform. Notebook: a reproducible King County example from published study tables.

CLOUDRAVEN CASE STUDY · KING COUNTY, WASHINGTON

What do roads, residents and workplaces add to a crash study?

We started with a rise in severe crashes on city streets. Comparing Seattle, Bellevue and Tukwila brought new questions into view: where people work, which roads carry the traffic, and when crashes happen.

Explore the published study, real maps and Census context. Change the city, road category and time detail to inspect the evidence yourself.

Explore the case studyRead the two-page brief

Crashes: 2020–2024 · Increase focus: 2021–2023
ACS: 2020–2024 · Primary jobs: 2023 · Updated October 20, 2026

King County locator and a map of Seattle, Bellevue and Tukwila with severe City Street crash counts aggregated into one-kilometer cells, 2021–2023.
The research begins with a question and a place. The case study connects federal, state and local records through a documented research workflow.

Your next research question

What would clearer evidence help you do?

Bring a community question to the beta. Explore the available workflows and decide what the evidence needs to help you understand.

Request beta accessBrowse research workflows