Skip to main content
Tools and skills turn AI Workforce agents from chat interfaces into AI automation tools that can do real work. They let agents retrieve trusted information, act in connected apps, follow optimized task playbooks, generate artifacts, and complete longer internal work. Brand Agents use a leaner, customer-facing tool surface. For public agents, see Brand Agent Connectors and Lead Capture. AI Workforce connector browser with app choices

​
AI Workforce Tool Types

AI Workforce agents can use: Use the section links above to jump to the tool type you are configuring.

​
Knowledge Bases

Knowledge Bases let agents retrieve trusted source material from websites, uploaded files, pasted text, and Q&A pairs. In Agent Build, the File Search tool connects one or more approved Knowledge Bases to the agent that needs them. The agent can then retrieve relevant passages during a run instead of relying only on its model knowledge. Use Knowledge Bases when the agent needs approved company, product, policy, support, sales, or website context. For AI Workforce, this usually means internal reference data the run should cite or use while preparing an artifact. For Brand Agents, Knowledge Bases power customer-facing answers from approved website and brand content. Knowledge Bases are retrieval tools, not broad app connectors. If the agent needs to take action in another system, pair the Knowledge Base with a connector, API Request, or custom MCP tool.

​
SketricGen Connectors

SketricGen connectors give AI Workforce agents access to 2,000+ applications. They are useful for internal workflows that need to read or update CRMs, calendars, email, documents, spreadsheets, support systems, project management tools, databases, commerce tools, marketing platforms, and team communication apps. When you add a connector, choose the app first, connect the account, then select only the actions this agent should be able to call. For example, a meeting-prep agent might receive calendar actions to list events and retrieve event details, while a sales operations agent might receive CRM actions to update a record or add a note. Connector action picker showing selected and available actions inside a connected app Action selection is the permission boundary that matters day to day. Review the selected action names, descriptions, configurable properties, and connected account before running sensitive workflows. For practical workflows, combine connectors with skills. A meeting-prep agent can use a calendar connector to fetch meeting details, a research skill to structure investigation, a document skill to produce the brief, and the run workspace to save the artifact. See Runs, Schedules, Files, and Artifacts for how outputs are stored.

​
Custom MCP Tools

Custom MCP tools let you connect a hosted MCP server directly to an AI Workforce agent. Use this when a service, vendor, or internal platform already exposes an MCP endpoint and you want to make selected MCP tools available to an agent through Agent Build. This is different from a single API Request. A hosted MCP can expose a group of tools, and SketricGen lets you discover those tools, choose the ones the agent can use, and attach the allowlisted set to the right agent. The example below uses a public weather MCP endpoint, fetches the available tools, and allowlists only the weather lookup tool for the agent. Custom MCP setup with hosted MCP URL, connection type, headers, and tool discovery To configure a Custom MCP tool:
  1. Add a Custom MCP tool node.
  2. Enter the hosted MCP server URL.
  3. Choose the connection type, usually Streamable HTTP unless the hosted MCP requires SSE over HTTP.
  4. Add headers for authentication, such as an authorization token or API key header.
  5. Click Filter Tools to fetch the tools exposed by that MCP server.
  6. Select only the tools this agent should be allowed to call.
  7. Save the tool and connect it to the main agent or the specialist sub agent that needs it.
The allowlist matters. If the hosted MCP exposes ten tools but this workflow only needs two, select those two. That keeps the agent easier to control, reduces accidental tool calls, and makes traces easier to review. Use Custom MCP when you have a reusable hosted tool surface, an internal service that already speaks MCP, or a third-party product that publishes an MCP endpoint. Use API Request when you only need to wrap one REST endpoint. For delegation and routing patterns, see Multi-Agent Orchestration and Handoffs.

​
API Request

API Request turns a cURL-style REST endpoint into an API automation tool the agent can call. Use it when you have one endpoint, webhook, lookup, or action that should become available to the agent without building a full connector or MCP server. The configuration defines the request the agent is allowed to make: HTTP method, URL, headers, query parameters, request body fields, and tool instructions. Those fields become the tool schema the agent follows when it calls the endpoint. The example below wraps a public weather forecast endpoint as a GET tool, then prompts the builder to test the endpoint before saving. API Request setup with Import through AI, HTTP method, URL, headers, and query parameter controls You can configure API Request in two ways:
  • Manual setup: choose the method, paste the endpoint URL, add headers, define query parameters or body fields, then test the API before saving.
  • Import through AI: paste an API documentation URL, OpenAPI spec, or similar reference and describe the endpoint you want. SketricGen maps the endpoint, headers, parameters, and body fields into a usable tool configuration.
In the import flow, paste the API documentation or OpenAPI spec and describe the specific tool you want SketricGen to generate. Import API Configuration dialog for generating an API Request tool from documentation Use the description field to tell the agent when to call the API and what a successful response means. For example, a lead enrichment endpoint should only be called after the agent has a valid email or domain; a support ticket endpoint should only be called after the user confirms the issue should be escalated. API Request works best for controlled endpoints such as webhooks, internal APIs, simple read-only lookups, enrichment calls, REST API automation, or one-off write actions. If the agent needs many actions from the same service, use a connector or Custom MCP instead.

​
Structured Output

Structured Output lets an agent emit schema-validated JSON when a workflow or application needs predictable data. Add a title, explain exactly when the agent should call it, and define the fields the receiving application expects. Application UI events are one use of the same Structured Output tool, not a separate tool type. For example, a custom frontend can watch for a Structured Output call and use its validated fields to render recommendation cards, open a form, update typed project state, or navigate to the next application step. You can also use Structured Output for classifications, extraction results, connector-ready payloads, and any downstream process that needs predictable fields. The call appears in the run stream so your application can read the arguments and validated result. Structured Output does not automatically pause the run or end the agent’s turn. If the application needs the event to be the final action for that turn, state that explicitly in the agent and tool instructions. Use Human Input instead when the agent must pause and wait for a person’s answer before continuing. For the workflow JSON contract and stream-handling example, see Structured Output for Developers. Web Search lets an agent look up current public information when a Knowledge Base is not enough. Use Web Search for market research, recent news, public company information, competitive checks, and time-sensitive facts. For workflows that require approved internal facts, pair Web Search with a Knowledge Base and tell the agent which source should win when sources conflict. Web Search tool configuration

​
Code Interpreter

Code Interpreter gives AI Workforce agents a sandboxed Python environment for calculations, data analysis, file transformation, and artifact generation. Use it when the agent needs to inspect structured data, perform repeatable computation, or create a file rather than only explain an answer in chat. Treat generated files and calculations as run outputs that still require review. Give the agent clear input files, expected output format, and validation criteria, then inspect the resulting artifact and trace before using it downstream.

​
Image and Video Generation

Two built-in tools let AI Workforce agents produce visual media. They run on SketricGen’s own image and video models, so there is no account to connect. Each output is billed in credits.
  • Image Generation & Editing creates new images from a prompt and edits existing ones: a file the user uploaded to the conversation, or an image the agent generated earlier. Use it for requests like “make a banner for our sale”, “put our logo on this mug”, or “swap the background”.
  • Video Generation & Editing creates short clips from a prompt, and can animate an image you pass as the start frame. Clips can include sound when the user asks for it; sound costs more. It also edits existing clips: a video the user uploaded to the conversation, or one the agent generated earlier. Use it for requests like “turn this clip into a watercolor” or “put this jacket on the presenter”. An edit keeps the clip’s motion and changes what the prompt asks for. Reference images can guide the new look.
To add one, open the agent in Agent Build, add a tool, and choose the tool type. Then tick the models the agent may use and, for each model, the qualities it may use. The builder shows the credit price of every option, including the separate price for edits. When several models are ticked, the agent picks the one that fits each request. A new tool starts with the cheapest option your plan includes. For images, that is the cheapest model that can both create and edit. For video, it is the cheapest model that creates clips plus the cheapest model that edits them. Some models only create and others only edit. For edits, the agent uses the ticked models that can edit, or the cheapest editing model your plan includes if none of them can. Video edits also accept only certain clips, which the builder lists under the model: Kling O3 Pro edits MP4 and MOV clips of 3–15 seconds at 720p or higher, and keeps the clip’s original sound unless the user asks to drop it.

​
Models by plan

Each plan includes everything in the plans above it. Options above your plan appear locked in the builder, and a workflow that selects them cannot be saved. If a teamspace moves to a lower plan, its agents switch to the cheapest option the new plan includes. When the new plan has no option for a tool, such as video on Free or Explorer, the tool stops working and the agent tells users the plan needs an upgrade.

​
Credits and limits

  • You are charged only for outputs the agent delivers. Nothing is charged for an output the safety filter blocks, or for a failed or cancelled generation.
  • Video edits are billed per second of the edited clip. Before it starts, the agent sets aside credits for the full length of the clip, or for the model’s longest clip when the length can’t be read. You are then charged for the length it delivers.
  • One message can create or edit up to 10 images and 2 videos (4 images on Free). Send a new message to make more.
  • The agent checks your balance before it starts a generation. If the balance is too low, it tells the user instead of starting.
  • The credits each run used appear in its trace, on Image generation & editing and Video generation & editing rows.

​
Where outputs go

Generated images and videos show in the chat and are saved to the conversation’s files, so a later step can reuse them: edit an image, animate it, edit a clip, analyze it with Code Interpreter, or post it through a connector. Videos and video edits can take a few minutes to render. The chat shows progress while a clip renders. If a render outlasts the wait, the agent tells you it is still rendering. Ask about it later in the same conversation and the agent fetches the finished clip.

​
Watching videos

AI Workforce agents on a model that accepts video can watch videos; there is no tool to add. These models show a Video badge in the model picker, next to Multimodal. When a user uploads a video, or the agent generates or edits one, the agent loads it and sees and hears it directly, the way it sees an image. It can then say what happens, who or what appears, what is said, and any on-screen text. The model sees the video for that step only. The video isn’t added to the chat history the model reads and isn’t sent again, so the agent loads it again when it needs another look. The file itself stays in the conversation’s files. Other models, including GPT, Claude, and DeepSeek, can’t watch videos. The agent asks the user to select a model that supports video, the same way text-only models handle images. It can still share the video, and Video Generation & Editing can still edit MP4 or MOV clips of 3–15 seconds. Watching is billed like the agent’s own model usage, by the length of video watched. Large files are compressed automatically before watching, and only the first 10 minutes of a longer video are watched. Brand Agents do not include these tools.

​
Skills Marketplace

AI Workforce skill marketplace with search, verified skills, install counts, sources, categories, and install buttons Marketplace skills are reusable task packages you can install onto an agent. They make the skills marketplace a practical AI tools marketplace for proven processes such as PDF work, financial analysis, dashboard creation, product requirements, design review, research, writing, or planning. Use skills when you want more than raw app access. A connector lets an agent act in an app. A skill gives the agent a curated way to perform a task well. When browsing skills, review:
  • The skill name and description.
  • The source or namespace.
  • Verification and reputation signals such as installs.
  • Category tags that match the work you want the agent to do.
  • Whether the skill should be installed on the main agent or a specialist sub agent.
Click Install to attach the skill to the selected agent. After installation, the agent can use that skill during runs alongside its instructions, model, files, tools, and connected apps. Installed AI Workforce skills with workflow, version, status, edit, and uninstall controls Installed skills can be reviewed from the Skills page. This helps teams see which workflows use which skills, check status, edit skill files when needed, and remove skills that should no longer be available.

​
Tool Assignment

Attach tools only where they are needed. The main agent should have the tools required to plan and coordinate the run. Sub agents should receive the smaller tool set required for their specialist task. For example, a research sub-agent may need Web Search and a Knowledge Base, while a reporting sub-agent may need only run files and the dedicated Structured Output tool. For debugging tool calls, action errors, latency, and credit usage, see Traces and Optimization.