Research & Analysis Workflows

Use when the user needs to categorize, triage, or classify text — error severity, code quality, bug reports, log entries. Quick local classification without cloud round-trip.

Use when the user wants to check or change Cercano's runtime configuration — switch the local runtime or model, change the Ollama endpoint URL, or change the cloud provider and model. No server restart needed.

Deep multi-source research tool that identifies authoritative sources, systematically searches, analyzes and ranks findings, chases cited references, and compiles a structured report with executive summary, contradiction detection, gap analysis, and follow-up suggestions.

Use when the user wants to generate or update doc comments for Go code. Handles the entire read-think-write cycle locally — the host never sees the file contents. Supports dryrun mode to preview.

Use when the user asks to explain unfamiliar code, complex algorithms, or dense documentation. Processes the explanation locally before deciding what context to send to the cloud. Prefer this for initial code understanding.

Use when the user needs to pull specific information from large text — function signatures, error messages, config values, API endpoints. Extracts locally instead of reading entire files into cloud context.

Use when the user asks to fetch, read, or open a specific URL. Use this INSTEAD of WebFetch to read web pages locally without sending content to the cloud. DO NOT TRIGGER when: user asks a research question without a specific URL (use cercano-research instead).

Use when the user wants to see what AI models are available on their Ollama instance. Returns model names, sizes, and modification dates.

Use when the user asks to research, look up, investigate, find information, or learn about any topic. Use this INSTEAD of WebSearch or WebFetch for general research questions. ALWAYS prefer this tool for web research. DO NOT TRIGGER when: user provides a specific URL to read (use cercano-fetch instead).

Use when the user asks about Cercano usage, token savings, or local vs cloud inference stats. Shows total requests, tokens processed locally, and breakdowns by tool, model, and day.

Use when the user wants to submit cloud token usage data to Cercano for tracking. This sends data, not a report — use cercanostats to view usage. Opt-in telemetry for local-vs-cloud comparison.

Use when the user needs to summarize large text, files, logs, or diffs. ALWAYS prefer this over reading large files directly into cloud context. Processes content locally and returns a concise summary.