Explore by theme

Follow an idea
across the collection.

Topics connect individual product updates to the broader questions behind them: how agents coordinate, how context shapes outcomes, and where structure makes AI work more reliable.

42 studies

Agents & workflows

View every study

3 min read

Earn Autonomy Through Visible Evidence

Increase delegation workflow by workflow, using visible evidence, repeated performance, and clear approval boundaries rather than a general feeling of trust.

Read analysis3 min read

Parallel Tool Calls Need a Dependency Map

Group calls only when their real inputs are already known, wait at join points, and keep dependent lookups and state changes in sequence.

Read analysis3 min read

Advice or Action? Define the Finish Line

Choose an advisory or execution mode, define the observable end state, and state the boundaries before Claude uses tools.

Read analysis

49 studies

Prompting & context

View every study

3 min read

Earn Autonomy Through Visible Evidence

Increase delegation workflow by workflow, using visible evidence, repeated performance, and clear approval boundaries rather than a general feeling of trust.

Read analysis3 min read

Parallel Tool Calls Need a Dependency Map

Group calls only when their real inputs are already known, wait at join points, and keep dependent lookups and state changes in sequence.

Read analysis3 min read

Remove Prompt Rituals Before Adding More

Maintain prompts like software: retain current requirements, remove obsolete patches, and compare quality, cost, and latency on representative tasks.

Read analysis

35 studies

Trust & governance

View every study

3 min read

Earn Autonomy Through Visible Evidence

Increase delegation workflow by workflow, using visible evidence, repeated performance, and clear approval boundaries rather than a general feeling of trust.

Read analysis3 min read