---
title: "Runs and proposals"
section: "Autonomous Agents"
description: "Run a SmartestQA agent with Run now, read the run detail (status, report, steps, cost), download the PDF, and apply or dismiss each proposal the agent recorded."
url: https://docs.smartestqa.ai/en/ai-agents-runs.html
audience: [customer, admin]
updated: 2026-11-08
keywords: "run now runs tab run detail status queued running succeeded failed stopped at limit budget blocked steps model tool proposal apply dismiss apply all download pdf outcome report json"
---
# Autonomous Agents: Runs and proposals

A run is one execution of an agent. Its detail shows what the agent did step by step, what it found, what it cost and which changes it proposes. You decide which proposals are applied.

## In short

**On this page you can**

- Start any active agent at once with Run now .
- Follow a run live and see each model decision and tool call.
- Read the report as a formatted page, as JSON or as a PDF.
- Apply or dismiss each proposed change, or use Apply all .
- Find all runs of the project, newest first, on the Runs tab.

**How to use it**

1. Switch the agent on and click Run now on its card.
2. Click a bar in Last runs , the summary line, or a row on Runs .
3. Read Summary and Outcome , then the Steps list.
4. For each PROPOSAL step, open it, read Input , then click Apply or Dismiss .
5. Click Download PDF to keep or share the report.

## Start a run

1. **Make sure the agent is on**

   The switch on the card must be on. **Run now** is greyed out while the agent is paused or a run of it is still going (the button then says **Running now**).
2. **Click Run now**

   You see “Run started.” The run is queued, then starts on the SmartestQA server with the [project’s AI connection](https://docs.smartestqa.ai/en/project-settings-ai.html#ai-account), also for agents set to [Claude Desktop](https://docs.smartestqa.ai/en/ai-agents-settings.html#runs-on).
3. **Watch it**

   The newest bar of **Last runs** pulses while the run is going. The page refreshes every 5 seconds; an open run detail every 3 seconds.

   The bar fills in its result colour and the card shows the summary under the bars.

If the agent has already spent its [daily budget](https://docs.smartestqa.ai/en/ai-agents-settings.html#limits), the run is saved as **Budget blocked** straight away and you see a warning with the amount spent and the limit.

## Read an agent’s card

- **Kind**: [**Autonomous agent**](https://docs.smartestqa.ai/en/ai-agents-catalog.html#which-agent) or [**Custom agent**](https://docs.smartestqa.ai/en/ai-agents-catalog.html#custom), then the name.
- **Trigger line**: [when it runs](https://docs.smartestqa.ai/en/ai-agents-settings.html#trigger), plus “Next” with the date for a schedule; “Paused: triggers are off” when off.
- **[Runs on](https://docs.smartestqa.ai/en/ai-agents-settings.html#runs-on)**: “User's LLM client (Claude Desktop)” appears when it runs there.
- **Last runs**: up to 14 bars, oldest on the left. Colour shows the result, height shows the cost. Failed and limited runs are hollow bars. Click a bar to open that run.
- **Today**: spent today against the daily budget, with a meter. [How it is drawn](https://docs.smartestqa.ai/en/ai-agents-numbers.html#budget-meter).
- **Chips**: number of [tools](https://docs.smartestqa.ai/en/ai-agents-settings.html#tools), [**Can apply changes**](https://docs.smartestqa.ai/en/ai-agents-settings.html#autonomy) or [**Suggests only**](https://docs.smartestqa.ai/en/ai-agents-settings.html#autonomy), and the [version](https://docs.smartestqa.ai/en/ai-agents-settings.html#versions).

## The Runs tab

The latest 100 runs of the project, newest first. Click a row (or focus it and press `Enter`) to open the run.

| Column | Shows |
| --- | --- |
| # | Run number |
| Agent | The agent’s name |
| Status | See [Run statuses](https://docs.smartestqa.ai/en/ai-agents-runs.html#statuses) |
| Trigger | **Manual** or **Schedule**. A run started by the [After each deploy](https://docs.smartestqa.ai/en/ai-agents-settings.html#trigger) trigger shows **Schedule**, because that trigger is an hourly check. **On test failure** appears only on older agents that still have that trigger. |
| Started · Duration | Start time; [duration](https://docs.smartestqa.ai/en/ai-agents-numbers.html#duration) as seconds or minutes and seconds |
| Steps | Steps recorded |
| Proposals | Proposals recorded (empty when none) |
| Cost (USD) | [Model cost of the run](https://docs.smartestqa.ai/en/ai-agents-numbers.html#run-cost), four decimals |
| Summary | The agent’s summary, or the error |

## Run statuses

| Status | Meaning |
| --- | --- |
| Queued | Created, waiting to start. |
| Running | The agent is working. A run in Claude Desktop stays Running until Claude reports the result. |
| Succeeded | The agent finished and wrote its summary. |
| Stopped at limit | It reached **[Max steps per run](https://docs.smartestqa.ai/en/ai-agents-settings.html#limits)** or **Max cost per run** before finishing. |
| Budget blocked | The agent’s daily budget was full, at the start or during the run. |
| Failed | An error stopped it, or the run made no progress for too long and was closed. [Why](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-run-failed). |

## Read a run

![Run detail.](https://docs.smartestqa.ai/media/shots/AGT-SHOT-06.png)

1. **The top row**

   Status, **Trigger**, **Started**, **Duration**, **Steps**, **Tokens** (input plus output), **[Cost (USD)](https://docs.smartestqa.ai/en/ai-agents-numbers.html#spend)**, **Proposals**, **Model** and the agent **Version** that ran.
2. **Summary and Outcome**

   **Summary** is the agent’s own words. **Outcome** is its result: **Report** shows it as a formatted page (findings as cards, status and risk as badges), **JSON** shows the raw data. Your choice is remembered in this browser.
3. **What started it**

   **User request** shows a request given for this run only. **Trigger details** shows the scheduled time, or the [deploy events](https://docs.smartestqa.ai/en/deployments-overview.html#history) and [failed runs](https://docs.smartestqa.ai/en/report-list.html) the agent was given.
4. **The steps**

   One row per step, numbered. Click the arrow to open **Reasoning**, **Input** and **Output**. Each row also shows its cost and duration.
5. **The settings it used**

   **Settings used in this run** shows the agent’s settings at that moment, so a later change does not hide why a run behaved as it did.

| Step kind | Meaning |
| --- | --- |
| **MODEL** | One model decision: what to do next and why. Each one counts as a step against **Max steps per run**. |
| **TOOL** | A tool call and its result. **DENIED** means the tool is not allowed for this agent, or the user it runs as lacks the [permission](https://docs.smartestqa.ai/en/company-settings-roles.html#matrix). **ERROR** means the call failed. |
| **PROPOSAL** | A change the agent wants. Not carried out until a person applies it. |
| **FINAL** | The agent’s closing summary. |
| **ERROR** | The run hit an error. |

**Download PDF** (at the bottom left, available once the run has ended) opens the report in a new tab, ready to print or save as PDF. [E-mail targets](https://docs.smartestqa.ai/en/ai-agents-settings.html#reports) receive the same report as an attachment.

## Apply or dismiss proposals

When a run would change something (a [locator](https://docs.smartestqa.ai/en/discover-actions.html), a [defect](https://docs.smartestqa.ai/en/tasks.html), a tag, a [test case](https://docs.smartestqa.ai/en/automate-test-cases.html)), the server records the exact call as a **PROPOSAL** step instead of making it. While proposals wait, the run shows “*n* proposals are waiting. An applied proposal runs as you, with the same arguments.”

1. **Open the proposal**

   Proposal rows open by default. Read **Reasoning** (why) and **Input** (exactly what will be sent).
2. **Apply or dismiss**

   **Apply** runs the recorded call now, as you, with your [permissions](https://docs.smartestqa.ai/en/company-settings-roles.html#matrix). **Dismiss** drops it.
3. **Or apply all**

   **Apply all** applies the waiting proposals one after the other, in order, because later ones may build on earlier ones.

   The row shows **APPLIED** and its output starts with the result of the call.

| Proposal status | Meaning | You can |
| --- | --- | --- |
| (none) | Waiting for a decision | Apply, Dismiss |
| **APPLIED** | Done, by the user shown in the output | Nothing more |
| **DISMISSED** | Dropped | Nothing more |
| **APPLY_FAILED** | The call failed: “The proposal could not be applied; see the step output for details.” | Fix the cause and Apply again |
| **APPROVED** | A proposal from a [Claude Desktop run](https://docs.smartestqa.ai/en/ai-agents-settings.html#runs-on) that SmartestQA could not apply on its own; the agent’s next run in Claude Desktop applies it | Wait for the next run |

> **Tip: Why proposals, not changes**
>
> Nobody watches a scheduled run. A proposal keeps a person between the agent’s judgement and your test library. Because the proposal runs as you, it can do only what you are allowed to do in that project.

Video: [Review a run and apply proposals](https://docs.smartestqa.ai/media/videos/AGT-03.mp4) (2:30)

Open a run, read Outcome and Steps, apply one proposal and dismiss another.

Video transcript: Autonomous Agents starts with four numbers: active agents, runs today, proposals to review and spend. The Runs tab lists every run with its agent, status, trigger, duration, steps and cost. Click a run to open its detail. The top row shows trigger, start, duration, steps, tokens, cost and the model that ran. Summary is the agent's conclusion in plain words. Outcome holds the full result, as a report or as JSON. Steps lists what the agent did, call by call. Proposed changes would wait here for you to apply or dismiss.

## If something goes wrong

- [Run now is greyed out](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-run-now-disabled)
- [Budget blocked](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-budget-blocked) · [Stopped at limit](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-stopped-limit)
- [A step says DENIED](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-denied)
- [“The proposal could not be applied”](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-apply-failed)
- [A run failed or hangs](https://docs.smartestqa.ai/en/ai-agents-troubleshooting.html#fix-run-failed)
