AI feature catalog
Every AI feature with its permission, tool contexts, template variables and built-in agent — generated from the server.
- Source
- Generated from packages/server/src/services/ai (feature contracts and seeds), so it always matches the code.
Every AI feature in CHouse UI, where it appears, what it needs, the template variables it hands its agent, and the agent it runs on after a fresh install. Rebind a feature or edit its agent in AI Governance › Assistant — see AI agents.
Needs is the permission a user must hold to use the feature; the route checks it before any agent runs. Tools may use is the run context the feature gives its agent's tools — an agent bound to a feature can only use tools whose context the feature provides:
| Context | What the tools can do |
|---|---|
| ClickHouse session | Runs on the signed-in user's ClickHouse connection, with their data access rules. |
| Fleet nodes | Read-only system.* queries on the nodes the feature resolved. |
| Your CHouse access | Calls CHouse's own API as the chatting user — they see only what their permissions allow. |
Features marked Evidence only gather their evidence in code and hand it over as ctx.evidence; their agents work from that and call no tools.
All features
Chat features
Chat
ID chat · needs ai:chat · free-form chat answer
The chat bubble. The bound agent answers when a thread has no agent picked; users can pick any top-level chat agent they may use.
Tools may use: ClickHouse session, Your CHouse access. Built-in agent: CHouse Assistant.
No template variables — chat agents render without any.
Suggest memories
ID suggest-memories · needs ai:chat · structured answer (JSON contract)
Chobi › chat: after a conversation, suggests up to three notes worth keeping for the person or the team; a person chooses what is saved.
Tools may use: Evidence only. Built-in agent: Memory Suggester.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The conversation, what memory already holds, and the rules (JSON). |
SQL editor features
Optimize query
ID optimize-query · needs ai:optimize · structured answer (JSON contract)
SQL editor › Optimize: rewrites a SELECT for speed and memory, proven with a before→after EXPLAIN estimate.
Tools may use: ClickHouse session. Built-in agent: SQL Optimizer.
| Variable | Type | Value |
|---|---|---|
ctx.query | string | The SELECT to optimize (trimmed). |
ctx.additionalPrompt | string | Extra instructions from the user (trimmed; empty when none). |
Debug query
ID debug-query · needs ai:optimize · structured answer (JSON contract)
SQL editor › Debug: explains why a query failed and returns a validated fix.
Tools may use: ClickHouse session. Built-in agent: SQL Debugger.
| Variable | Type | Value |
|---|---|---|
ctx.query | string | The failed query (trimmed). |
ctx.error | string | The ClickHouse error message (trimmed). |
ctx.additionalPrompt | string | Extra instructions from the user (trimmed; empty when none). |
Optimization pre-screen
ID check-optimize · needs ai:optimize · structured answer (JSON contract)
SQL editor: silently decides whether a query is worth optimizing before offering Optimize.
Tools may use: ClickHouse session. Built-in agent: Query Evaluator.
| Variable | Type | Value |
|---|---|---|
ctx.query | string | The query to evaluate (trimmed). |
Doctor features
Fleet Doctor scan
ID fleet-scan · needs doctor:run · structured answer (JSON contract) · also runs in the background
Doctor › Scan (manual, scheduled or alert-triggered): reviews every node and deep-dives heavy queries into a health report.
Tools may use: Fleet nodes. Built-in agent: Fleet Doctor.
| Variable | Type | Value |
|---|---|---|
ctx.hours | number | Investigation window in hours. |
ctx.nodeCount | number | Number of nodes scanned. |
ctx.overview | json | Per-node overview (pretty-printed JSON). |
ctx.needsPlaybook | boolean | True when the scan found a heavy or top-memory query worth optimizing. |
Diagnostics features
Optimize a heavy query
ID optimize-log · needs ai:optimize · structured answer (JSON contract)
Query Logs › Optimize: rewrites one heavy query from the log, proven with a before→after EXPLAIN estimate.
Tools may use: Fleet nodes. Built-in agent: Heavy Query Optimizer.
| Variable | Type | Value |
|---|---|---|
ctx.node.id | string | Connection id of the node the query ran on. |
ctx.node.name | string | Connection name of that node. |
ctx.peakMemory | string | Observed peak memory, or "unknown". |
ctx.query | string | The cleaned query text (first 8000 characters). |
Diagnose a server error
ID diagnose-error · needs ai:optimize · structured answer (JSON contract)
Errors › Diagnose: explains one server error from system.errors and gives a concrete fix.
Tools may use: Fleet nodes. Built-in agent: Error Diagnostician.
| Variable | Type | Value |
|---|---|---|
ctx.node.id | string | Connection id of the node under investigation. |
ctx.node.name | string | Connection name of that node. |
ctx.error.code | string | Error code, or "?". |
ctx.error.name | string | Error name, e.g. TOO_MANY_PARTS. |
ctx.error.message | string | Last error message, or "(none)". |
Diagnose part health
ID diagnose-parts · needs ai:optimize · structured answer (JSON contract)
Parts › Diagnose: explains part and partition health of one MergeTree table.
Tools may use: Fleet nodes. Built-in agent: Parts Diagnostician.
| Variable | Type | Value |
|---|---|---|
ctx.node.id | string | Connection id of the node under investigation. |
ctx.node.name | string | Connection name of that node. |
ctx.database | string | Database of the table. |
ctx.table | string | Table name. |
Diagnose a schema finding
ID diagnose-schema · needs ai:optimize · structured answer (JSON contract)
Schema Advisor › Diagnose: turns one column-level finding into a concrete ALTER TABLE fix.
Tools may use: Fleet nodes. Built-in agent: Schema Diagnostician.
| Variable | Type | Value |
|---|---|---|
ctx.node.id | string | Connection id of the node under investigation. |
ctx.node.name | string | Connection name of that node. |
ctx.database | string | Database of the table. |
ctx.table | string | Table name. |
ctx.column | string | Column name. |
ctx.columnType | string | Current column type. |
ctx.category | string | Finding category: nullable, oversized or compression. |
ctx.sizeLine | string | One line with rows / on-disk / uncompressed bytes, or empty. |
DataOps features
Draft a scheduled query
ID draft-scheduled-query · needs ai:optimize · structured answer (JSON contract)
Scheduled Queries › New with AI: turns intent into an editable draft.
Tools may use: ClickHouse session. Built-in agent: Scheduled Query Drafter.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Scheduled query preflight
ID assess-scheduled-query · needs ai:optimize · structured answer (JSON contract)
Scheduled Queries › Editor › AI preflight: risks and improvements before saving.
Tools may use: ClickHouse session. Built-in agent: Scheduled Query Reviewer.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Scheduled query brief
ID summarize-scheduled-query · needs ai:optimize · structured answer (JSON contract)
Scheduled Queries › AI brief: purpose, health, meaningful change and whether action is needed.
Tools may use: Evidence only. Built-in agent: Scheduled Query Briefer.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Diagnose a scheduled run
ID diagnose-scheduled-run · needs ai:optimize · structured answer (JSON contract)
Scheduled Queries › Run › Diagnose: ranks causes of one failed or slow run.
Tools may use: Evidence only. Built-in agent: Scheduled Run Investigator.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Assess a recovery plan
ID plan-scheduled-recovery · needs ai:optimize · structured answer (JSON contract)
Scheduled Queries › Recover: assesses a bounded backfill before it runs.
Tools may use: Evidence only. Built-in agent: Recovery Planner.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Recommend health checks
ID recommend-health-promise · needs ai:optimize · structured answer (JSON contract)
Data Health › New with AI: recommends checks for one table from bounded aggregates.
Tools may use: ClickHouse session. Built-in agent: Health Promise Advisor.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Data health brief
ID summarize-data-health · needs ai:optimize · structured answer (JSON contract)
Data Health › AI brief for one protected dataset.
Tools may use: Evidence only. Built-in agent: Data Health Briefer.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Diagnose a data health incident
ID diagnose-health-incident · needs ai:optimize · structured answer (JSON contract)
Data Health › Incident › Diagnose: monitor failure or bad data, likely impact, safe next actions.
Tools may use: Evidence only. Built-in agent: Health Incident Investigator.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Tune health checks
ID tune-health-promise · needs ai:optimize · structured answer (JSON contract)
Data Health › Tune: recommends threshold and cadence changes from history.
Tools may use: Evidence only. Built-in agent: Health Promise Tuner.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Correlate incidents
ID correlate-health-incidents · needs ai:optimize · structured answer (JSON contract)
Data Health › Correlate: groups incidents that share a credible cause.
Tools may use: Evidence only. Built-in agent: Incident Correlator.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Observability features
Explain an incident
ID explain-incident · needs ai:optimize · structured answer (JSON contract)
Observe › Incident › Explain: narrates the stored root-cause chain and drafts catalog fixes.
Tools may use: Evidence only. Built-in agent: Incident Explainer.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Compile a watcher
ID compile-watcher · needs ai:optimize · structured answer (JSON contract)
Observe › Watch with AI: compiles a sentence into one Data Health check.
Tools may use: Evidence only. Built-in agent: Watcher Compiler.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Draft table context
ID draft-table-context · needs ai:optimize · structured answer (JSON contract)
Context › Draft with AI: drafts a table's curated context from metadata and an aggregate-only profile.
Tools may use: Evidence only. Built-in agent: Table Context Drafter.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Auto-triage
ID triage-incident · needs ai_agents:manage · structured answer (JSON contract) · also runs in the background
AI Governance › Auto-triage: investigates new incidents, alerts, failed scheduled runs and Doctor findings on its own, and proposes actions for approval.
Tools may use: Fleet nodes. Built-in agent: Incident Triager.
| Variable | Type | Value |
|---|---|---|
ctx.trigger | string | What happened, e.g. "Failed scheduled run". |
ctx.title | string | The subject's title. |
ctx.evidence | json | What CHouse knows about the subject (pretty-printed JSON). |
ctx.nodes | json | Connections the agent may query with query_node (id and name). |
Read upgrade release notes
ID match-upgrade-notes · needs ai:optimize · structured answer (JSON contract)
Monitoring › Upgrades › Check: reads the breaking-change notes between two versions against the names the workload uses.
Tools may use: Evidence only. Built-in agent: Upgrade Notes Reader.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The evidence object the feature assembled (JSON). |
Dashboards features
Draft a dashboard
ID draft-dashboard · needs ai:optimize · structured answer (JSON contract)
Dashboards › Ask AI: drafts a dashboard, or panels to add to one, from a goal; every panel is checked and dry-run before review.
Tools may use: ClickHouse session. Built-in agent: Dashboard Drafter.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The goal, the dashboard being added to, and the panel rules (JSON). |
Explain this spike
ID explain-spike · needs ai:optimize · structured answer (JSON contract)
Dashboards › Explain this spike: reads a panel's selected range, the changes around it, slow queries, mutations and merges, and explains the likely cause.
Tools may use: ClickHouse session. Built-in agent: Spike Explainer.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The panel, the selected range and the evidence gathered around it (JSON). |
AI Governance features
Draft a skill
ID draft-ai-skill · needs ai:optimize · structured answer (JSON contract)
AI Governance › Assistant › Skills › Draft with AI: drafts or refines a custom skill (SKILL.md and reference files) for review.
Tools may use: Evidence only. Built-in agent: Skill Author.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The request and the live registry facts the draft may use (JSON). |
Draft an agent
ID draft-ai-agent · needs ai:optimize · structured answer (JSON contract)
AI Governance › Assistant › Agents › Draft with AI: drafts or refines a custom agent — prompt, tools, skills, subagents and settings — for review.
Tools may use: Evidence only. Built-in agent: Agent Author.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The request and the live registry facts the draft may use (JSON). |
Draft a harness
ID draft-ai-harness · needs ai:optimize · structured answer (JSON contract)
AI Governance › Assistant › Harnesses › Draft with AI: drafts or refines a custom harness — a decision for every built-in tool — for review.
Tools may use: Evidence only. Built-in agent: Harness Author.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The request and the live registry facts the draft may use (JSON). |
Draft a guardrail
ID draft-guardrail · needs ai:optimize · structured answer (JSON contract)
AI Governance › Guardrails › Draft with AI: turns a goal into a guardrail draft (kind, settings, stages, action) for review.
Tools may use: Evidence only. Built-in agent: Guardrail Drafter.
| Variable | Type | Value |
|---|---|---|
ctx.evidence | json | The goal, the guardrail kinds with their settings, and the drafting rules (JSON). |
Built-in agents
The 35 agents CHouse installs. Steps are the agent's step budget; its recursion limit defaults to four times that, and at least 24. Without a timeout of its own, a run stops after 4 minutes for a feature and 2 minutes in the chat. See Editing agents.
SQL Optimizer
Rewrites a SELECT for speed and memory from its DDL and EXPLAIN plan (SQL editor › Optimize).
| Setting | Value |
|---|---|
| Slug | sql-optimizer |
| Kind | Feature agent |
| Used by | Optimize query |
| Harness | Focused |
| Tuning | 10 steps |
| Tools | list_databases, list_tables, get_table_schema, get_table_ddl, get_table_size, get_table_sample, run_select_query, explain_query, get_database_info, get_running_queries, get_server_info, search_columns, analyze_query, validate_sql, export_query_result, get_slow_queries |
| Skills | all built-in skills on demand |
SQL Debugger
Explains why a query failed and returns a validated fix (SQL editor › Debug).
| Setting | Value |
|---|---|
| Slug | sql-debugger |
| Kind | Feature agent |
| Used by | Debug query |
| Harness | Focused |
| Tuning | 10 steps |
| Tools | list_databases, list_tables, get_table_schema, get_table_ddl, get_table_size, get_table_sample, run_select_query, explain_query, get_database_info, get_running_queries, get_server_info, search_columns, analyze_query, validate_sql, export_query_result, get_slow_queries |
| Skills | all built-in skills on demand |
Query Evaluator
Quick, silent pre-screen: is this query worth optimizing? (SQL editor).
| Setting | Value |
|---|---|
| Slug | query-evaluator |
| Kind | Feature agent |
| Used by | Optimization pre-screen |
| Harness | Focused |
| Tuning | 4 steps |
| Tools | analyze_query, get_table_ddl, get_table_schema |
| Skills | all built-in skills on demand |
Heavy Query Optimizer
Optimizes one heavy query picked from the Query Logs, proven with a before→after EXPLAIN estimate.
| Setting | Value |
|---|---|
| Slug | log-query-optimizer |
| Kind | Feature agent |
| Used by | Optimize a heavy query |
| Harness | Focused |
| Tuning | 8 steps · 16,000 output tokens |
| Tools | query_node |
| Skills | all built-in skills on demand; pinned clickhouse-playbook (reference.md) |
Error Diagnostician
Explains one server error from system.errors and gives a concrete fix.
| Setting | Value |
|---|---|
| Slug | error-diagnostician |
| Kind | Feature agent |
| Used by | Diagnose a server error |
| Harness | Focused |
| Tuning | 8 steps · 8,000 output tokens |
| Tools | query_node |
| Skills | all built-in skills on demand; pinned clickhouse-playbook (reference.md) |
Parts Diagnostician
Diagnoses part and partition health of one MergeTree table.
| Setting | Value |
|---|---|
| Slug | parts-diagnostician |
| Kind | Feature agent |
| Used by | Diagnose part health |
| Harness | Focused |
| Tuning | 8 steps · 8,000 output tokens |
| Tools | query_node |
| Skills | all built-in skills on demand; pinned clickhouse-playbook (reference.md) |
Schema Diagnostician
Turns one Schema Advisor finding into a concrete ALTER TABLE fix.
| Setting | Value |
|---|---|
| Slug | schema-diagnostician |
| Kind | Feature agent |
| Used by | Diagnose a schema finding |
| Harness | Focused |
| Tuning | 8 steps · 8,000 output tokens |
| Tools | query_node |
| Skills | all built-in skills on demand; pinned clickhouse-playbook (reference.md) |
Fleet Doctor
Reviews every node's health, deep-dives heavy queries and writes the Doctor report.
| Setting | Value |
|---|---|
| Slug | fleet-doctor |
| Kind | Feature agent |
| Used by | Fleet Doctor scan |
| Harness | Focused |
| Tuning | 12 steps · 16,000 output tokens |
| Tools | query_node |
| Skills | all built-in skills on demand |
Incident Triager
Investigates new incidents, fleet alerts, failed scheduled runs and Doctor findings on its own, and proposes actions for approval.
| Setting | Value |
|---|---|
| Slug | incident-triager |
| Kind | Feature agent |
| Used by | Auto-triage |
| Harness | Focused |
| Tuning | 10 steps · 4,000 output tokens |
| Tools | query_node, kill_query, propose_remediation |
| Skills | all built-in skills on demand |
Dashboard Drafter
Turns a monitoring goal into a reviewed dashboard draft (Dashboards › Ask AI).
| Setting | Value |
|---|---|
| Slug | dashboard-drafter |
| Kind | Feature agent |
| Used by | Draft a dashboard |
| Harness | Focused |
| Tuning | 8 steps · 8,000 output tokens |
| Tools | list_databases, list_tables, get_table_schema, get_table_ddl, validate_sql |
| Skills | all built-in skills on demand |
Spike Explainer
Explains what most likely caused a spike on a dashboard panel, from evidence gathered as the viewer (Dashboards › Explain this spike).
| Setting | Value |
|---|---|
| Slug | spike-explainer |
| Kind | Feature agent |
| Used by | Explain this spike |
| Harness | Focused |
| Tuning | 3 steps · 3,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Guardrail Drafter
Turns a goal into a guardrail draft for review (AI Governance › Guardrails).
| Setting | Value |
|---|---|
| Slug | guardrail-drafter |
| Kind | Feature agent |
| Used by | Draft a guardrail |
| Harness | Focused |
| Tuning | 3 steps · 3,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Memory Suggester
Suggests notes worth keeping after a Chobi conversation, for the person to save or dismiss.
| Setting | Value |
|---|---|
| Slug | memory-suggester |
| Kind | Feature agent |
| Used by | Suggest memories |
| Harness | Focused |
| Tuning | 2 steps · 1,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Scheduled Query Drafter
Turns an operator's intent into an editable scheduled query draft.
| Setting | Value |
|---|---|
| Slug | scheduled-query-drafter |
| Kind | Feature agent |
| Used by | Draft a scheduled query |
| Harness | Focused |
| Tuning | 7 steps · 4,500 output tokens |
| Tools | list_databases, list_tables, get_table_schema, get_table_ddl, analyze_query |
| Skills | all built-in skills on demand |
Scheduled Query Reviewer
Preflight risk review of a scheduled query before it is saved.
| Setting | Value |
|---|---|
| Slug | scheduled-query-reviewer |
| Kind | Feature agent |
| Used by | Scheduled query preflight |
| Harness | Focused |
| Tuning | 6 steps · 3,000 output tokens |
| Tools | analyze_query, validate_sql, get_table_schema, get_table_ddl, explain_query |
| Skills | all built-in skills on demand |
Scheduled Query Briefer
Operational brief for one scheduled query.
| Setting | Value |
|---|---|
| Slug | scheduled-query-briefer |
| Kind | Feature agent |
| Used by | Scheduled query brief |
| Harness | Focused |
| Tuning | 3 steps · 2,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Scheduled Run Investigator
Ranks the likely causes of one failed or slow scheduled run.
| Setting | Value |
|---|---|
| Slug | scheduled-run-investigator |
| Kind | Feature agent |
| Used by | Diagnose a scheduled run |
| Harness | Focused |
| Tuning | 5 steps · 4,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Recovery Planner
Assesses a bounded backfill / recovery plan before it runs.
| Setting | Value |
|---|---|
| Slug | recovery-planner |
| Kind | Feature agent |
| Used by | Assess a recovery plan |
| Harness | Focused |
| Tuning | 3 steps · 2,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Health Promise Advisor
Recommends Data Health checks for one table from bounded aggregates.
| Setting | Value |
|---|---|
| Slug | health-promise-advisor |
| Kind | Feature agent |
| Used by | Recommend health checks |
| Harness | Focused |
| Tuning | 8 steps · 5,000 output tokens |
| Tools | get_table_schema, get_table_ddl, run_bounded_aggregate |
| Skills | all built-in skills on demand |
Data Health Briefer
Operational brief for one protected dataset.
| Setting | Value |
|---|---|
| Slug | data-health-briefer |
| Kind | Feature agent |
| Used by | Data health brief |
| Harness | Focused |
| Tuning | 3 steps · 2,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Health Incident Investigator
Diagnoses a Data Health incident: monitor failure or bad data.
| Setting | Value |
|---|---|
| Slug | health-incident-investigator |
| Kind | Feature agent |
| Used by | Diagnose a data health incident |
| Harness | Focused |
| Tuning | 5 steps · 4,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Health Promise Tuner
Tunes noisy or insensitive Data Health checks from their history.
| Setting | Value |
|---|---|
| Slug | health-promise-tuner |
| Kind | Feature agent |
| Used by | Tune health checks |
| Harness | Focused |
| Tuning | 4 steps · 3,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Incident Correlator
Groups Data Health incidents that share a credible cause.
| Setting | Value |
|---|---|
| Slug | incident-correlator |
| Kind | Feature agent |
| Used by | Correlate incidents |
| Harness | Focused |
| Tuning | 4 steps · 3,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Incident Explainer
Narrates an incident's stored root-cause chain and drafts catalog fixes.
| Setting | Value |
|---|---|
| Slug | incident-explainer |
| Kind | Feature agent |
| Used by | Explain an incident |
| Harness | Focused |
| Tuning | 3 steps · 3,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Watcher Compiler
Compiles a sentence into one Data Health check.
| Setting | Value |
|---|---|
| Slug | watcher-compiler |
| Kind | Feature agent |
| Used by | Compile a watcher |
| Harness | Focused |
| Tuning | 3 steps · 2,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Table Context Drafter
Drafts a table's curated context from metadata and an aggregate-only profile.
| Setting | Value |
|---|---|
| Slug | table-context-drafter |
| Kind | Feature agent |
| Used by | Draft table context |
| Harness | Focused |
| Tuning | 3 steps · 2,500 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Upgrade Notes Reader
Reads ClickHouse's breaking-change notes for an upgrade against the names one workload uses (Monitoring › Upgrades).
| Setting | Value |
|---|---|
| Slug | upgrade-notes-reader |
| Kind | Feature agent |
| Used by | Read upgrade release notes |
| Harness | Focused |
| Tuning | 3 steps · 6,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Skill Author
Drafts and refines custom skills (SKILL.md and reference files) from a goal or pasted runbook.
| Setting | Value |
|---|---|
| Slug | skill-author |
| Kind | Feature agent |
| Used by | Draft a skill |
| Harness | Focused |
| Tuning | 3 steps · 12,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Agent Author
Drafts and refines custom agents — prompt, tools, skills, subagents, harness and tuning — from a goal.
| Setting | Value |
|---|---|
| Slug | agent-author |
| Kind | Feature agent |
| Used by | Draft an agent |
| Harness | Focused |
| Tuning | 3 steps · 12,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
Harness Author
Drafts and refines custom harnesses with a decision for every built-in tool.
| Setting | Value |
|---|---|
| Slug | harness-author |
| Kind | Feature agent |
| Used by | Draft a harness |
| Harness | Focused |
| Tuning | 3 steps · 6,000 output tokens |
| Tools | none |
| Skills | all built-in skills on demand |
ClickHouse Data
Read-only investigator for CHouse Assistant: databases, tables, columns, SQL, query performance, server state and charts.
| Setting | Value |
|---|---|
| Slug | clickhouse-data |
| Kind | Chat agent |
| Used by | subagent of CHouse Assistant |
| Harness | Focused |
| Tuning | 12 steps |
| Tools | list_databases, list_tables, get_table_schema, get_table_ddl, get_table_size, get_table_sample, run_select_query, explain_query, get_database_info, get_running_queries, get_server_info, search_columns, analyze_query, validate_sql, export_query_result, get_slow_queries, render_chart, generate_query, optimize_query |
| Skills | all built-in skills on demand |
Access Auditor
Users, roles, permissions, data access policies, personal access tokens, SSO, and ClickHouse users and roles.
| Setting | Value |
|---|---|
| Slug | access-auditor |
| Kind | Chat agent |
| Used by | subagent of CHouse Assistant |
| Harness | Focused |
| Tuning | 8 steps |
| Tools | whoami, list_users, get_user, list_roles, get_role, list_permissions, list_data_access_policies, list_my_access_tokens, list_clickhouse_users, list_clickhouse_roles, get_sso_settings |
| Skills | none |
Operations Analyst
Scheduled jobs and runs, Data Health promises and incidents, alerting, observability incidents, remediation actions and investigation notebooks, Doctor reports, fleet health, query regressions, capacity, upgrade readiness, the observability collectors and custom dashboards.
| Setting | Value |
|---|---|
| Slug | operations-analyst |
| Kind | Chat agent |
| Used by | subagent of CHouse Assistant |
| Harness | Focused |
| Tuning | 8 steps |
| Tools | list_scheduled_jobs, get_scheduled_job, list_scheduled_runs, list_health_checks, get_health_check, list_health_incidents, list_alerting, list_observe_incidents, list_remediation_actions, get_investigation_notebook, list_doctor_reports, fleet_snapshots, get_query_regressions, get_capacity, list_upgrade_assessments, get_upgrade_assessment, get_upgrade_status, get_collector_status, get_collector_schedule, list_dashboards, get_dashboard, get_dashboard_annotations |
| Skills | none |
Platform Auditor
Connections, AI models, CHouse's AI agents and their usage, cost, data sent to providers and guardrails, external agents and MCP settings, and the audit log.
| Setting | Value |
|---|---|
| Slug | platform-auditor |
| Kind | Chat agent |
| Used by | subagent of CHouse Assistant |
| Harness | Focused |
| Tuning | 8 steps |
| Tools | whoami, list_connections, list_ai_models, list_ai_agents, list_ai_guardrails, list_ai_guardrail_triggers, get_ai_usage, list_ai_requests, get_ai_request, list_agent_sessions, get_agent_governance, audit_log |
| Skills | none |
CHouse Assistant
Chobi's assistant: answers, investigates with read-only investigators, and makes changes in CHouse and ClickHouse — each checked by its tier.
| Setting | Value |
|---|---|
| Slug | chouse-assistant |
| Kind | Chat agent |
| Used by | Chat |
| Harness | Assistant |
| Tuning | 16 steps · 240 s timeout |
| Tools | list_databases, list_tables, get_table_schema, get_table_ddl, get_table_size, get_table_sample, run_select_query, explain_query, get_database_info, get_running_queries, get_server_info, search_columns, analyze_query, validate_sql, export_query_result, get_slow_queries, render_chart, generate_query, optimize_query, whoami, load_toolkit, navigate, open_entity, fill_form, kill_query, create_saved_query, update_saved_query, delete_saved_query, share_saved_query, create_database, create_table, drop_table, drop_database, run_sql_change, create_scheduled_query, update_scheduled_job, pause_scheduled_job, resume_scheduled_job, run_scheduled_job, delete_scheduled_job, create_health_promise, watch_table, update_health_promise, pause_health_promise, resume_health_promise, run_health_check, acknowledge_health_incident, snooze_health_incident, delete_health_promise, propose_remediation, create_alert_rule, update_alert_rule, mute_alert_rule, test_alert_channel, post_alert_message, clear_alert_events, acknowledge_observe_incident, dismiss_suggestion, pin_table_criticality, add_notebook_cell, update_cost_rates, update_collector_schedule, start_codec_trial, run_doctor_scan, update_doctor_schedule, update_fleet_alert_config, run_upgrade_assessment, create_dashboard, update_dashboard, add_panel, update_panel, remove_panel, restore_dashboard_version, delete_dashboard, add_dashboard_note, delete_dashboard_note, share_dashboard, update_table_context, upsert_metric, delete_metric, create_user, update_user, deactivate_user, assign_role, create_role, update_role, delete_role, create_data_access_policy, update_data_access_policy, delete_data_access_policy, set_role_policies, create_clickhouse_role, update_clickhouse_role, draft_ai_agent, run_ai_eval, publish_ai_agent, update_my_preferences |
| Skills | all built-in skills on demand |
| Subagents | ClickHouse Data, Operations Analyst, Access Auditor, Platform Auditor |