Skip to main content

Episode 2 — Chat, in depth

The daily surface, used well — the same question asked ungrounded and grounded, model choice with evidence in Arena Mode, big deliverables in the canvas, and where deep research lives.

2 min read

Episode 1 toured the workspace; this episode moves into the room your team will actually live in. Its core beat is a controlled experiment: the same onboarding question asked twice — once with no context, once with the Q2 support review attached — so you can watch a fluent answer and a grounded answer stop being the same thing.

Episode 2 — Chat, in depth (3:08, captions available)

What the episode shows

AtScene
0:13The composer: agent, model, and context are three separate choices
0:28Asking without context — fluent, confident, generic
0:45The same topic grounded: the Q2 review attached, sources named
1:02The one habit that matters: fluent is not evidence, sources are
1:22The model picker and what Auto decides for you
1:41Arena Mode: one prompt, two models, a recorded verdict
2:05The canvas: a brief lands as a file, not a wall of chat text
2:24Deep research: the Researcher agent and where it lives

Where to go next

Chat basics covers the composer in reference depth; attachments explains what riding along as context really means. For the model side, read models and Arena Mode; for the workbench, the canvas pane; and for research with cited sources, deep research.

© 2026 Tale by Ruler GmbH — ISO 27001 & SOC 2 certified.

Tale is MIT licensed — free to use, modify, and distribute.