Docs
Docs /Prism AI /Features
Prism AITools and context

Features

Prism AI answers from what you give it and what it looks up itself. You attach tabs, results, and tables with @, the agent calls tools to browse the schema, dry-run SQL, and run queries, and it renders results, charts, and follow-ups back into the panel so you can act on them without leaving the chat.

right panel
Prism×
Which makes fail their MOT most often? Use @fact_mot_test

search_schema · columns fact_mot_test
validate_sql · valid, 1.2 GB, $0.006
execute_query · 20 rows, 1.2 GB
Ford leads by count, but by rate it’s Vauxhall at 31% failed. The query groups on make and divides failed by total tests — I added a filter on completed_date so it only scans this year’s partitions.

Chart failure rate by makeBreak down by defect category

Plan, @ for context, / for commands Approveauto
Tool calls show as one-line entries above the answer; click one to expand the result.

Context with @

Type @ in the input (or click the @ button) and pick from open tabs, results, and the schema tree. Up to ten matches show as you type.

@ suggestions
MentionAttached
TabThe SQL and the last job’s bytes, cost, duration
ResultsSchema and row count; rows only under the share setting
TableColumns, types, descriptions, partition and cluster keys
Dataset, projectIts tables, so the agent can pick
Property graphLabels, properties, node and edge tables — needed before writing GQL

Attached items appear as pills above the input; the cross removes one. You can also attach files with the paperclip (.sql, .bqsql, .csv, .tsv, .txt, .md, .json, .jsonl, .yaml, .yml, 32 KB in total); their text is inlined into the message.

Commands with /

CommandEffect
/clearStart over: clears the conversation
/compactReplaces the history with a summary so a long conversation keeps fitting; add a note after it to say what to keep

Tools

The agent decides which tools to call; you see each call as a line in the reply. Reading tools never ask; the two that scan data or change a tab follow the mode.

Reading

ToolWhat it does
search_schemaBrowses projects, datasets, tables, columns, and property graphs. Supports * wildcards and multi-word matches
get_tab, list_tabsReads a tab’s SQL and job stats; lists every open tab
validate_sqlPrism diagnostics plus a BigQuery dry run: validity, cost, referenced tables. Accepts pipe syntax and GQL
sample_tablePer-column profiles and diverse sample rows through tabledata.list, which is free. Tables only, not views
get_optimization_tipsStructural cost findings: missing partition filters, SELECT *, join order, clustering
get_bq_docsSearches and loads BigQuery’s SQL reference so it doesn’t guess function signatures
get_skillLoads a longer playbook (optimize_query, error_resolution, notebooks) before a complex task
search_saved_queries, get_saved_queryFinds and reads your saved queries

Changing things

ToolWhat it does
execute_queryRuns a SELECT, up to 1000 rows. Anything else is rejected
edit_sql, revert_editReplaces or patches the SQL in the attached tab or a notebook cell; one level of undo
create_tab, rename_tabNew query or notebook tab; descriptive names after a run
create_notebook_cell, execute_notebook_cell, list_notebook_cells, get_notebook_cell, get_notebook_cell_schemaMulti-cell pipelines in notebooks

Showing you things

ToolRenders as
update_todoA progress list at the top of the reply for multi-step work
create_chartA chart from result rows, with a Download chart as PNG button
suggest_follow_upsOne to three chips under the reply; click one to send it

In the reply

  • Query results appear as a grid in the chat with Open in Results Panel and Open in Tab. What the model saw is separate from what you see; the privacy note under the result says which.
  • With models that expose it, a collapsed Reasoning block precedes the answer.
  • Thumbs up or down on any reply gives feedback; the down-vote asks what went wrong.
  • After 25 tool calls in one request the agent pauses and offers Continue, which counts as one more request.

Turning it off or tuning it

The master switch, AI ghost completions, auto-renaming of tabs, the results-sharing policy, and the provider list live in Settings → AI Features → Prism AI; see Settings.