Quick Agent¶

The Quick Agent is the default entry point — ask a question, get an answer in one shot. No multi-step reasoning, no subagents. Perfect for 80% of daily network queries.

Feature Claims

ID	Claim	Status
C-NE-15	`olav "R1 BGP neighbors?"` returns query results from snapshot data	🔶 Env-Blocked
C-NE-16	Blacklisted commands are rejected by `execute_cli`	🔶 Env-Blocked
C-NE-17	`/learn_cmd "show version" --device R1` executes and generates a TextFSM template	🔶 Env-Blocked
C-NE-18	`take_snapshot` triggers incremental collection with a new snapshot_id	🔶 Env-Blocked
C-NE-19	Quick Agent suggests upgrading to Ops Agent for complex multi-step analysis	⬜ Pending

When to Use Quick Agent¶

Task	Quick Agent	Ops Agent
"How many BGP peers are down?"	Yes	Overkill
"Show R2 interfaces"	Yes	Overkill
"What changed since yesterday?"	Possible	Better (use Diff)
"Simulate link failure impact"	No	Yes (Analysis)
"Deploy a test lab"	No	Yes (Lab)

Quick Agent handles simple queries by generating SQL against the snapshot database or executing a single CLI command. For anything requiring iteration, comparison, or simulation, it will suggest using the Ops Agent.

Query Examples¶

Natural Language to SQL¶

olav "Are all BGP neighbors established on R1?"

OLAV translates this to:

SELECT neighbor_ip, neighbor_as, state
FROM v_bgp_neighbors_auto
WHERE device_name = 'R1' AND state != 'Established'

Direct SQL¶

olav "execute_sql: SELECT device_name, count(*) as cmd_count FROM netops.parsed_outputs GROUP BY 1"

CLI Execution¶

olav "Run 'show ip route' on R2"

The agent looks up the command in the whitelist, connects via SSH, and returns the output. Blacklisted commands are rejected before any connection is made.

Snapshot Collection¶

Trigger an on-demand snapshot from Quick Agent:

olav "Take a snapshot of R1 and R2"

This runs the collection pipeline for the specified devices, producing a new snapshot_id. The data is immediately queryable.

Learning New Commands¶

When a show command has no TextFSM template, use /learn_cmd to teach OLAV:

olav --agent ops "/learn_cmd 'show ip bgp community' --device R1"

This will:

Execute the command on the device via SSH
Analyze the output structure
Generate a TextFSM template
Save it to workspace/ops/config/templates/custom/

The template is available for all future collections without restart (hot-reload).

Tools Available¶

Quick Agent has access to these tools (all symlinked from ops/tools/):

Tool	Purpose
`execute_cli`	Run a single CLI command on a device
`search_commands`	Find available commands by platform and keyword
`diff_configs`	Compare device configs between two snapshots
`take_snapshot`	Trigger on-demand collection

Plus all core platform tools (execute_sql, format_and_export, recall_memory, etc.) inherited automatically.

Escalation¶

When Quick Agent determines a question requires multi-step analysis, it tells you:

"This question requires comparing multiple data sources across time. I recommend using the Ops Agent: olav --agent ops 'your question'"

This happens for questions involving simulation, drift detection, or multi-device correlation.