App inspirations

The four-quadrant method
3matching examples of 65
Research workflows

Chat over documents

Paste the brief into OpenCode, ask three questions whose answers you know, and check each citation opens the right passage.

Explore this idea →

Know what you want

What do you want to achieve — and what will a useful result look like?

Paste the brief into OpenCode, ask three questions whose answers you know, and check each citation opens the right passage.

  1. Structure it
    lab-library/↳ documents/*.pdf · *.md↳ index/↳ app/↳ README.md
  2. Understand itTrace a question end to end: retrieve passages → draft an answer that only uses those passages → show each passage next to its sentence.
    Input: a question + the curated library
    Process: retrieve top passages, draft an answer constrained to them, attach a citation to every sentence
    Output: answer with [n] chips, each opening the highlighted passage
  3. Choose toolsChoose an embedding model, an LLM for drafting, and a viewer that highlights passages; pick local or hosted models deliberately.
    Embedding model — turns chunks into vectors (local: nomic-embed / bge; hosted: any)LLM — drafts the answer under a 'cite or delete' rulePassage viewer — highlights the cited span in the source document
  4. Build itPaste the brief into OpenCode, ask three questions whose answers you know, and check each citation opens the right passage.
    OpenCode · development brief
Chat over documents
Source & credit

Chat over documents: Trace a question end to end: retrieve passages → draft an answer that only uses those passages → show each passage next to its sentence.

Every answer, traceable. Owner-supplied illustrative interface; source figures credited below.

AnythingLLM (MIT) — open-source reference implementation (https://github.com/Mintplex-Labs/anything-llm) Open WebUI — reference UI (Open WebUI License, keep branding) (https://github.com/open-webui/open-webui) Owner-supplied illustrative interface; source figures credited below.

Original source ↗

Chat over documents

Press Escape to close.

Cell biology & imaging

QuPath

Paste the brief into OpenCode, open the Ki67 region, and check the class colours match the QuPath convention (red positive, blue negative).

Explore this idea →

Know what you want

What do you want to achieve — and what will a useful result look like?

Paste the brief into OpenCode, open the Ki67 region, and check the class colours match the QuPath convention (red positive, blue negative).

  1. Structure it
    slide-review/↳ data/region.ome.tiff↳ data/annotations.geojson↳ data/detections.csv↳ LICENSE-images.md↳ README.md
  2. Understand itTrace the chain slide → region → detections → summary and decide which of those the app shows (all four, linked).
    Input: slide tile + region polygon + classified detections (QuPath output)
    Process: overlay detections on the tile, filter by class, summarise per region
    Output: region view with counts and the percentage shown next to its denominator
  3. Choose toolsUse QuPath for detection and classification, a tiled image viewer for display, and a table tool for the summary.
    QuPath — annotation, cell detection and classification (the science)OpenSeadragon or a canvas tile viewer — displays the regionData tool — recomputes the summary from detections.csv to cross-check QuPath's numbers
  4. Build itPaste the brief into OpenCode, open the Ki67 region, and check the class colours match the QuPath convention (red positive, blue negative).
    OpenCode · development brief
QuPath
Source & credit

QuPath: Trace the chain slide → region → detections → summary and decide which of those the app shows (all four, linked).

Slide → annotation → measured cells. Owner-supplied illustrative interface; source figures credited below.

QuPath documentation — Ki67 positive-cell detection screenshot, CC BY 4.0 (https://qupath.readthedocs.io/en/stable/_images/ki67_detecting_final_markup.jpg) Bankhead et al. 2017, Sci Rep 7:16878, Fig. 1 — CC BY 4.0 (https://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs41598-017-17204-5/MediaObjects/41598_2017_17204_Fig1_HTML.jpg) Owner-supplied illustrative interface; source figures credited below.

Original source ↗

QuPath

Press Escape to close.

Plant biology

Compare plant traits across ploidy groups

Paste the brief into OpenCode and confirm unknown ploidy stays separate.

Explore this idea →

Know what you want

What do you want to achieve — and what will a useful result look like?

Paste the brief into OpenCode and confirm unknown ploidy stays separate.

  1. Structure it
    ploidy-traits/↳ data/accessions.csv↳ data/ploidy.csv↳ data/traits.csv↳ index.html
  2. Understand itTrace one trait: select comparable units → group by documented ploidy → inspect variation.
    Input: three tables
    Process: group, keep unknown separate
    Output: matrix + source rows
  3. Choose toolsPython for grouping, HTML/SVG for the matrix.
    Python csvHTML + SVGNo LLM
  4. Build itPaste the brief into OpenCode and confirm unknown ploidy stays separate.
    OpenCode · development brief
Compare plant traits across ploidy groups
Source & credit

Compare plant traits across ploidy groups: Trace one trait: select comparable units → group by documented ploidy → inspect variation.

Unknown ploidy is its own group. Owner-supplied illustrative interface; source figures credited below.

Thomas Kraehahn, Wikimedia Commons — CC BY 4.0 (https://commons.wikimedia.org/wiki/File:Sand-Schaumkresse_im_NSG_Erpetal.jpg) Owner-supplied illustrative interface; source figures credited below.

Original source ↗

Compare plant traits across ploidy groups

Press Escape to close.