Using Forward AI

Opening Forward AI

Forward AI is the default landing page, so it opens after you sign in. You can also click Forward AI in the left navigation at any time. The page opens in the currently selected network and uses the latest processed snapshot.

Page layout

The Forward AI page is split into three areas:

Area	What it shows
Conversations panel (left)	Your past conversations on the current network, sorted most-recent first. Click a conversation to reopen it; open its ⋯ menu to rename or delete it.
Transcript (center)	The current conversation: your prompts, the agent's replies, and the prompt input at the bottom.
Plan & tools panel (right)	The agent's plan for the active prompt and the tool calls it executed, with their results.

NQE results and other multi-row tool outputs render as sortable tables in the Plan & Tools panel so you can page through them without leaving the conversation.

Starting a conversation

A new conversation displays Get started with these prompts, with example prompts grouped under:

• Troubleshooting: path tracing, reachability checks, blocked-traffic diagnosis.
• Vulnerabilities: CVE exposure, vulnerable paths, prioritization.
• Compliance / Audit: config consistency, unused rules, direct internet exposure.
• Inventory: EOL devices, BGP session audits, host discovery.

Click an example to drop it into the prompt input; replace the <placeholder> values with real ones from your network, then press Send. To skip the suggestions, type your own prompt and press Send.

What happens after you send a prompt

1. The conversation status changes to Processing.
2. The agent classifies the prompt. If it's out of scope, the conversation ends with an explanation. See Limits and scope.
3. For complex prompts that need three or more distinct actions, the agent emits a plan in the right-hand panel: a short list of broad steps. Simpler prompts skip planning.
4. The agent runs one tool at a time. Each call appears in the panel as the agent decides to run it, with its inputs, status, and result.
5. The agent posts the final answer in the transcript: a summary and key insights.
6. The conversation status changes to Done.

You cannot send another message in the same conversation while it's still Processing, and you can only have one Processing conversation across all your chats. Wait for the current one to finish, or switch to a different conversation.

Inspecting evidence

Every tool the agent runs appears in the Plan & Tools panel, where you can open its inputs, status, and result. Select a tool to see the evidence behind an answer:

• Path search: the reply summarizes the path in the transcript; the Tracing path tool carries an Open in Search page link that opens the native Search application with the source, destination, protocol, and ports pre-filled. Use it to drill into the path or change parameters.

• NQE results render as a sortable table. The NQE tool fetches at most 100 rows per query; if your question requires more, ask the agent to refine it or open the underlying query in NQE.

• Device, interface, VLAN, VRF, host, and cloud-object lookups show structured fields, each with an Open in Search page link to the matching object.

• Generated NQE query: when you ask for a query you can run yourself, Forward AI opens the result in a query panel where you can run it against the snapshot, copy it into the Query Editor to edit, or save it to the NQE Library.

• Documentation: Forward AI answers NQE syntax and function questions in text. Each answer carries a Sources list linking to the documentation it drew on.

• CVE references in vulnerability replies are clickable and carry severity.

• Configuration history: while the agent works, the plan shows a Getting configuration history step. The reply includes a Configuration history table for the device, with one row per change. The Snapshot column shows the snapshot that collected the change, newest first. The Line changes column shows the lines added and removed, and is hidden when the history is too large to show in full. In that case, the table lists every collected change up to the conversation's snapshot, including older changes that the agent did not read. Each row has two actions:

  • See changes opens a Configuration history dialog with the diff against the previous collection.
  • Open in Diffs opens the device's configuration diff on the Diffs page in a new window. It is disabled on the device's first collection, which has no earlier version to compare.

  For a long history, the plan can also show Running command steps while the agent searches the history.

Vulnerability tables, successful NQE queries, and configuration history also render inline in the transcript, alongside the summary and key insights. Other tool results, including path search, stay in the Plan & Tools panel.

Following up

After a reply finishes, Forward AI may suggest a few follow-up prompts beneath the answer. Select one to send it as your next question, or type your own. The conversation keeps the full prior context, so you can reference earlier results ("for the device you mentioned in the last answer, list its interfaces") without restating them.

Renaming and deleting conversations

In the conversations panel, open a conversation's ⋯ menu for Rename and Delete:

• Rename sets a new title. Empty titles are rejected.
• Delete removes the conversation and all its messages. There is no undo.

You can only rename or delete conversations you own.

Sending feedback

Each assistant reply has thumbs-up and thumbs-down icons. Clicking either opens a dialog with up to 1000 characters of free-text comment.

Feedback is used by the Forward AI team to improve the agent. It is not visible to other users or to your org admin.

Where to go next

• Capabilities: the full set of question categories Forward AI can handle.
• Limits and scope: out-of-scope replies, per-message limits, and snapshot scoping.