Skip to content
Evergrowth Documentation

Review agent outputs and re-run a single agent

The Research tab on any account or contact shows what each agent found, when it found it, the sources it used, and the reasoning behind the answer. Use it after running agents to read the results, judge their quality, give feedback, and re-run a single research agent without re-running everything else. For background on what these agents do, see Agents.

Steps

Section titled “Steps”

  1. Open an account or contact, then select the Research tab.

  2. On an account, the tab holds three sections: Qualification agents (whether the account fits your criteria), Research agents (the facts and signals that were gathered), and Business model. On a contact, the agent results sit in the Agent research section, followed by the LinkedIn insights, DISC profile, and persona card.

    Inside Research agents on an account, the results are split into two labelled groups, each with a count of how many results it holds:

    • Signals - “Time-sensitive triggers. Positive answers feed the signal score and can fire play generation.” These are the reasons to act now. See Account signals.
    • Data points - “Standing account facts. Stored on the record and synced back to your CRM.” These are the durable attributes you report and segment on. See CRM enrichment.

    Which group a result lands in follows how the agent was set up in the Agent Training Center, not anything about the answer itself. The split is worth reading deliberately: a rep scanning for an opening line wants the Signals group, and a group with a count of zero says that side of your research setup has nothing on this account yet rather than that the account is quiet. Each group carries its own message when it is empty, so “no signal results yet for this account” and “no data point results yet for this account” are separate statements. A search that matches nothing in one group still shows results in the other.

  3. To move between sections, use the row of links at the top of the tab; it stays pinned as you scroll. To find one result, type in the Search for agents value… box on the same row. It filters by the agent’s name or by the text of its answer, and the cards below filter to match. If nothing matches, the page tells you no agents were found for your search term.

  4. Read a result card. Each card shows:

    • The agent’s name and its answer, rendered with formatting. An empty answer shows a dash.
    • A timestamp chip showing when the result was last updated.
    • A Source and reasoning chip. Hover it to see the Source links the agent used and the Reasoning it gave for its answer. This chip only appears when the agent recorded sources or reasoning.
    • Two small meter icons showing the agent’s Effort and Speed setting. Hover each for the exact value.

  5. To give feedback on a result, use the two buttons on the right of the card. The thumbs-up button records that the answer was helpful and sends right away. The thumbs-down button opens a Share feedback box with the prompt Please tell us why this response wasn’t helpful to you. - type your note and select Submit. Either action shows a confirmation that your feedback was sent.

  6. To re-run a single research agent with its current settings, select the restart button at the far right of that card. The tooltip reads Research again. This re-runs only that one agent for this record - no other agents and no other records. The button shows a confirmation that research was triggered.

The restart button appears only on Research agents cards. Qualification answers are produced by running qualification, not by re-running one agent at a time. To refresh a qualification result, re-run qualification - see Run a Qualification agent.

Reading an out-of-date result

Section titled “Reading an out-of-date result”

If an agent’s settings were changed after this record was processed, its timestamp chip turns orange. Hover it for the exact date the agent was updated, with a note to re-run the agent if you want results based on the latest version. For research agents, the restart button on the same card does exactly that.

On an account, if new Qualification agents were added after the account was last qualified, the Qualification agents section ends with a Missing qualification agents panel listing them. Re-run qualification to fill those in.

If a result card shows a small orange warning icon instead of the meter icons, the underlying agent could not be found. This usually means the agent was renamed or removed in the Agent Training Center after this result was saved.

What happens next

Section titled “What happens next”

Selecting Research again starts a research job for that one agent and record. You can watch it under Agent tasks on the record’s Activity tab. When the job finishes, return to the Research tab - the agent’s answer, sources, reasoning, and timestamp update in place, and the orange “out of date” chip clears. Re-running uses credits, the same as running the agent the first time; see Credits.

Feedback you submit is recorded against that specific result and does not change the answer.

Section titled “Related”