Skip to main content
Agents are AI-powered assistants that use tools to solve open-ended tasks. An agent decides which tools to use and when, adapting its approach to the task in front of it.

​
What agents do

You give an agent a goal and a set of tools, and it figures out how to get there: which tools to call, in what order, and when to ask you for input.
  • Adaptive: takes different approaches for different situations
  • Tool-driven: uses your apps and data as needed
  • Conversational: works through a task in a back-and-forth conversation
  • Context-aware: considers your instructions, skills, and past tasks
One piece of work you hand to an agent is a task. Each task is its own conversation with its own history, files, and credit cost. When you give it a task, the agent analyzes the request, decides which tools to use and in what order, runs them, adapts based on the results, and asks for confirmation when your instructions call for it.

​
Configure an agent in three moves

You do not need to write a long system prompt up front. The fastest way to a useful agent is to let it do real work, then have it write its own instructions.
1

Connect your apps

Open the Connectors section and add the integrations the agent needs (Gmail, Salesforce, Slack, and so on). The connectors you add define what the agent can see and do, so start with the two or three it actually needs.
2

Give it a real task

Start a task and run something end to end. Watch where it guesses, asks the wrong thing, or misses a step.
3

Ask it to write its own instructions and skills

Once it completes a task the way you want, tell it: “Update your instructions so you always do it this way” or “Turn this into a skill.” The agent writes its own instructions and skills, getting you 90% of the way without hand-authoring anything.
This loop is the whole point: correct the agent once, have it capture the correction in its instructions or a skill, and it stops making that mistake. Every task makes the agent better.

​
Getting around an agent

Open an agent and the left sidebar has everything about it:
Agent sidebar with New Task, Artifacts, Performance, Channels, and a Recents list
When the agent is waiting on you to approve a tool call, a pending action request appears above Recents.

​
The agent builder

Everything you configure lives in four tabs at the top of the builder. Only Owners see them; what a User sees depends on the agent’s User Permissions. Sections open in place. Click a section header (for example Connectors) and it expands into a full view with an Agent > Connectors breadcrumb, so you can drill into a connector’s tools and come back without losing your place. Nothing saves until you press Save (Ctrl/Cmd + S); the arrow next to it undoes unsaved changes.
Agent tab showing Model, instructions, Edit Own Instructions, Connectors, Skills, Knowledge Sources, Subagents, Secrets, and Abilities
The model picker and the instructions box sit at the top, with Edit Own Instructions (self-improving instructions) right under them. Below that, one section per building block — each shows how many items it has, and + Add to add one.

​
Guided setup

A brand-new agent asks what it should take care of and sets itself up from your answer, instead of dropping you into the full builder. If you would rather start in the builder every time, turn on Skip guided agent setup in your profile preferences. The rest of this page covers each part, starting with the ones you will reach for most.

​
Connectors

Connectors are the integrations your agent connects to, such as Gmail, Salesforce, Slack, Notion, and 150+ more. The connectors you add determine what the agent can access, so this is the most important part of configuration.
Connectors section showing connected connector icons, an Add Connector row, and the AI Discovery toggle set to ON
Click + Connector to open the picker. The All tab lists every available connector (Gumloop-managed and your own), and the Custom tab filters to custom MCP servers you have added. Pick the few your agent actually needs rather than connecting everything.
Add a connector modal with a search box, All and Custom tabs, a Connected list with checkmarks, and an All connectors list
The AI Discovery toggle on the Connectors header is the same setting as Tool Discovery in Abilities. It lets the agent load tool schemas on demand instead of all at once, which keeps context lean when you connect many connectors.

​
Account selection

Click any connected app to open its detail view. The Account selector controls which login the agent uses to call that app’s tools.
Google Docs app detail view showing Activity, Tools Enabled, and Rules tiles, with an Account selector offering Use Personal Default and Use Specific Account
  • Use Personal Default: each person who runs the agent uses their own default account. This is the default.
  • Use Specific Account: pin one account for the agent, useful when you have multiple accounts for the same service.
  • Use Team Default (team agents only): everyone on the team uses the same shared account.

Credentials

How agents authenticate, personal vs. team credentials, and the account selection flow.

​
Tool Management and approvals

The same detail view has a Tool Management panel that controls which of an app’s tools the agent can call, and which ones need your approval first. Tools are grouped into Read-only tools and Write/delete tools.
Tool Management panel with an approval preset dropdown, read-only and write/delete tool groups, and per-tool allow, ask, and deny controls
Set a preset for the whole app, or control each tool individually: When a tool needs approval, the agent pauses mid-task and shows you an approval card. This is the human-in-the-loop guardrail for sensitive actions.

Human in the Loop

How approvals work, what the agent shows you, and how to tune when it pauses.

​
Skills

Skills teach your agent how to do specific work your way: multi-step processes, templates, and domain knowledge that load only when relevant. You rarely write one by hand. The easiest path is to prompt the agent in a task: get it to do the work well, then say “turn this into a skill.” When it gets something wrong later, give it feedback and it updates the skill. The AI Skill Editing toggle is what lets it create and edit skills on its own.
Skills section with AI Skill Editing toggle and the Skill menu showing Create With AI, Upload Files, Write Skill Instructions, and Add Existing Skill
You can also add a skill yourself with + Skill:
  • Create With AI: describe the skill and the agent generates it.
  • Upload Files: turn a document or .zip into a skill.
  • Write Skill Instructions: enter a name and description yourself.
  • Add Existing Skill: attach a skill you already created.

Agent Skills Guide

Create skills, attach them to agents, and build a library that improves over time.

​
Knowledge Sources

Give your agent a searchable memory of what your company knows. In the Knowledge Sources section, attach Brain sources (Google Drive, Notion, Slack, GitHub, Confluence, or uploaded files) so the agent answers from your real documents and messages, with citations, instead of guessing.
Knowledge Sources section in agent configuration with the prompt Give your agent knowledge: Attach Company Brain sources so this agent can search them, down to the exact files or folders within
Click + Source to attach whole sources, or drill into the exact files and folders that matter. When you ask about internal knowledge, the agent searches automatically (shown as Searching Company Brain) and can open a full document for more context.

Brain Guide

Connect knowledge sources, keep them synced, and give your agents company knowledge to search.

​
Triggers

Agents can run on their own, without anyone starting a task. The Triggers tab lists the triggers on the agent, and AI Managed in its header lets the agent create, edit, and manage its own triggers during a task.
Triggers tab showing AI Managed, a Mine filter, and the five ways to add a trigger
There are five ways to add one: Owners manage every trigger on the agent. Users can create and edit their own triggers while Create triggers is allowed in User Permissions. The Mine / Team filter switches between the two views.

Agent Triggers Guide

Set up app and scheduled triggers, write prompt templates, and manage active triggers.

​
Subagents

Subagents let your agent delegate to other agents. Instead of doing everything in one task, it can spin up focused helpers that work in parallel, then collect the results and continue.
There are two ways an agent delegates, both through the invoke_agent tool:
The agent clones itself, keeping the same tools and instructions. Useful for parallel work: spawn several clones, each handling a different subtask. The clone shows up as “(Me)” in the list and is enabled by default. Clones cannot clone themselves again (depth limit of 1), and you can scope a clone to a subset of apps.
Each subagent runs as its own task with its own context and computer, visible in your task history. A task can have at most 10 concurrent subagents, including subagents started by other subagents. Subagents also count toward your account’s concurrent-agent limit, so available capacity may be lower. If the agent reaches the subagent limit, it receives “Subagent limit reached.” Wait for running subagents to finish, or ask the agent to split the work into fewer batches before starting more. Behind the scenes, subagents run as queued background tasks with their own time budget (about half the parent’s). For batch invocations a shared progress board tracks each one, and the parent can hand specific files to a subagent before it starts. The parent reads each subagent’s results when it finishes.

​
Abilities

Abilities are the agent’s built-in capabilities. Most are on by default, and each can be toggled from the Abilities section.
Abilities section listing Web Search, Web Fetch, Image Generation, Search Past Conversations, Ask Question, Tool Discovery, and App Rules Creation

​
Image Generation

The Image Generation ability creates images from text prompts. New agents have it on by default and use GPT-Image 2.5 Flare as the default image model. On an agent, you choose the image model. The agent chooses the size, quality, background, format, aspect ratio, and resolution for each request based on the prompt. It is instructed to use the smallest option that satisfies the request.

​
Image models

The Recommended image preset tries these models in order: GPT-Image 2.5 Flare, GPT-Image 2.5 Sunburst, Gemini 3.1 Flash, Gemini 3 Pro, GPT-Image 2, and Gemini 2.5 Flash Image. It skips any model your organization restricts.

​
Per-request options

The agent selects these options for each image request: Agents can also pass reference images to edit them or keep a subject, product, or style consistent. OpenAI image models accept up to 16 reference images. Gemini 3.1 Flash and Gemini 3 Pro accept up to 14, and Gemini 2.5 Flash Image accepts up to 3. OpenAI accepts JPEG, PNG, and WebP; all Gemini image models also accept HEIC and HEIF. What it costs: Image generation is charged from the usage reported by the image model. Cost depends on the model and the options selected, so higher quality or resolution costs more credits. See Credits for how BYOK affects image generation. Older image model IDs are no longer in the picker. Requests that use a retired ID are remapped to a current model:

​
The agent’s computer

Every agent has a built-in computer for running Python and shell commands in a secure, isolated environment. It is always on, so the agent can analyze data, generate files, and run scripts automatically. You do not need to configure anything. It keeps installed packages and workspace files across tasks and ships with 80+ Python packages preinstalled.

Computer & Secrets

What the agent’s computer can do, persistence, execution limits, preinstalled packages, and Agent Secrets.

​
Measuring and improving an agent

Performance in the agent sidebar is where you see how the agent is doing and turn on the two features that improve it: Evaluations grade completed tasks against your criteria, and Reflections have the agent review past tasks and suggest improvements you can accept or dismiss.

Agent Performance

Insights, Evaluations, and Tasks for a single agent.

Evaluations

Define criteria and grade the agent’s answers so you catch regressions early.

Reflections

Let the agent review its own recent tasks and propose improvements.
Agents can also produce rich outputs such as documents, spreadsheets, and interactive charts. See Agent Artifacts for how those are generated, shared, and versioned.

​
Working in a task

​
Message input menu

The + menu in the message bar gives you quick actions while you work:
Chat input plus menu showing Add photos and files, Use skill, Mention integration, Mention secret, and an Incognito toggle
  • Add photos & files: attach files and images to your message.
  • Use skill: manually point the agent at a specific skill.
  • Mention integration: reference a connected app directly in your message.
  • Mention secret: reference a stored secret so the agent can use it without you pasting the value.
  • Incognito: toggle a private task (covered below).

​
Voice input

You can send audio instead of typing. Gumloop transcribes it on the server and sends the text to the agent, so the task flows the same whether you type or talk.
Agent chat input showing the microphone button for voice input
Supported formats include mp3, mp4, m4a, wav, and webm, up to 25 MB. Transcription runs on Gumloop’s servers using OpenAI transcription models (Whisper and GPT-4o Transcribe), so your agent only ever receives the text transcript, never the raw audio.

​
Message queue and steering

You do not have to wait for the agent to finish before sending your next message. While the agent is working, press Enter to add a follow-up to the message queue without interrupting its current step. You can edit, reorder, or remove a queued message before it is delivered.
Message queue showing multiple queued messages in different states
To redirect the current run immediately, click Send Now on a queued message, or press ⌘ Enter on Mac / Ctrl Enter on Windows or Linux. The agent interrupts its current step and continues with your new input instead of ending the task. Steering does not undo actions that have already completed, and it does not bypass a pending approval. Use the stop control when you want to end the run rather than redirect it.

​
Context usage meter

The circular meter in the bottom-right of the message input shows how much of the agent’s usable context window is in use — for models where you picked a short context window, that smaller window is the denominator. Hover it for a breakdown across System, AI Instructions, Abilities, Tools, Skills, Subagents, and Conversation.
Context Usage Meter showing a token breakdown by category
If context fills up, reduce the tools or skills attached, switch to a model with a larger context window, or rely on auto summarization to compress older messages.

​
Incognito mode

Incognito tasks are not saved to the database. They are held in temporary memory and auto-deleted after 24 hours. Toggle Incognito from the message input menu before sending.
Incognito applies to the whole task, including any subagents it spawns. Once it expires, messages and files are permanently gone.

​
Understanding credit costs

Agents consume credits for AI model usage, tool calls, the compute time they spend working, and an orchestration fee on top of those. Cost depends on the model, message length, task history, and the number of tools available. The task’s running credit total sits next to its name in the header. Select it to open the task’s details drawer, which shows the source, creation time, model, and participants, plus a row for each credit type the task was actually charged for: Chat & Reasoning, Tool Calls, Compute, Orchestration Fee, and Evaluation & Self-Improvement.
Chat details drawer opened from the credit count in the chat header, showing source, created time, model, participants, and a credit breakdown by type

Credits

Full model pricing, integration costs, and how to track usage.

​
Settings

The Settings tab covers how the agent presents itself and how the model behaves.
Settings tab showing Identity, Suggested Prompts, Advanced AI, Chat Summarization, Model Fallback, and Destructive
Two things that used to live here have moved: file sharing for generated files is now File Sharing on the Access tab, and Slack behavior is now under Channels → Slack. Secrets is a section on the Agent tab.

​
Channels

An agent is not limited to Gumloop. Channels in the agent sidebar is the single place you make it reachable somewhere else — every surface is set up from there, one per item in the list.
Channels page with Email Inbox, Slack, Microsoft Teams, Hosted Page, Developer, and MCP in a sidebar

Slack

Deploy agents to Slack channels for team-wide access.

Microsoft Teams

Deploy agents to Microsoft Teams channels.

Email

Give your agent an inbox it can read and reply from.

Hosted pages

Share a public or private hosted page for your agent.

​
Finding agents

The Agents page lists every agent you can access. Use the tabs to switch views:
Agents page showing the Shared with me tab with agent cards
Each card shows the agent name, connected apps, creator, and last activity. You can search by name and switch between grid and list views.

​
Usage stats

A line under the agent’s description summarises how it has been used over the last 31 days: how many tasks it worked on, and on a team agent, who used it most (Used by Ana, Ben and 4 others · 62 tasks in the last month, with avatars for the top users). A personal agent reads Worked on 62 tasks in the last month.
Stats respect Task Visibility. If you can only see your own tasks on an agent, the numbers cover just your usage and no users are named. Subagent runs are excluded, and incognito tasks never count.
For the full picture — credits over time, credits by model and member, connector and skill usage — open Performance in the agent sidebar. See Agent Performance. Organization-wide reporting lives in Insights.

​
Managing tasks

Every task appears under Recents in the sidebar. Right-click a task or open its three-dot menu to manage it.
Task context menu showing Share, Rename, and Delete options
Rename tasks to keep your sidebar organized. “Q2 Marketing Plan” is easier to find than an auto-generated title.

​
Guardrails

For agents that take real actions, layer on guardrails so they stay within bounds.

Human in the Loop

Make the agent pause for approval before write, delete, and other sensitive tool calls.

App Rules

Set conditions that block or flag specific tool calls at the agent or organization level.

​
Self-improving instructions

Your agent can update its own instructions while it works. Correct it once (“always check Salesforce first,” “keep emails under 100 words”) and it edits its instructions so the same mistake does not happen again. Changes take effect on the next step and persist across future tasks. The toggle sits below the system prompt editor and is on by default; there is no version history, so revert by editing the prompt manually.

​
AI advanced settings

Most agents never need this. Defaults are already set for a good balance of performance, cost, and reliability. Organization admins can set the defaults that new agents inherit. See Agent Default Settings. Open the Settings tab, then expand Advanced AI, Chat Summarization, or Model Fallback.
Settings tab with Advanced AI, Chat Summarization, and Model Fallback expandable sections
Per-provider model parameters. Switching models preserves your preferences for each provider.Reset Model Parameters to Defaults restores these values for the current provider.
Some models ship two context windows. When your agent is on one of those models, Context Window appears under Advanced AI.Every other model has a single window and never shows the setting. The choice is saved per provider. It is not sent to the model provider: it changes the context budget Gumloop enforces.GPT-5.6 and Grok 4.5/4.6 charge higher long-context rates once a request’s input tokens cross the short window, and the higher rates apply to the whole request. Claude’s 1M-token models bill at one flat rate.
When a task approaches the model’s context limit, older messages are compacted into a structured recap while recent messages are kept in full.Defaults: summarization starts at 80% of the context window, roughly the most recent 40,000 tokens are protected, and summaries are capped around 30,000 tokens.Turn on Override Auto Summarization to tune Summarization Trigger (%), Summary Model, Protected Context Tokens, and Max Summary Tokens. A lower trigger summarizes sooner and costs less per turn. A higher trigger keeps more raw history.
If the primary model is unavailable or unreachable, the agent retries and then switches to a fallback from a different provider. Enable Model Fallback is on by default. Turn on Override Auto Fallback to pick fallback models yourself.

AI Models

Browse the full model catalog by tier, vision models, and bring-your-own-key (BYOK).

​
Best practices and troubleshooting

Begin with two or three apps and short instructions. Test, watch how the agent behaves, then add tools and rules based on real usage. Avoid launching with 15 tools and a 2,000-word prompt.
When the agent makes a mistake, ask it: “What could I add to your instructions to prevent this?” Then have it update its own instructions or a skill. Review past tasks for patterns.
Be explicit about what the agent should never do without approval: delete records, send emails, make purchases, or modify production data. Back this up with Tool Management approvals.

​
Next steps

Agent Triggers

Run agents automatically on a schedule or in response to events.

Agent Skills

Build reusable knowledge packs that teach agents how to do specific work.

Brain

Give agents company knowledge to search from your connected sources.

Evaluations

Grade agent responses and catch regressions before they ship.

Reflections

Let agents review their own work and propose improvements.

Computer & Secrets

Run code securely and manage agent secrets.

Agent Access

Owners, Users, User Permissions, and Task Visibility.