Documentation Index
Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt
Use this file to discover all available pages before exploring further.
Available tools
WednesdayAI agents can use tools to take actions on your behalf — searching the web, running code, reading and writing files, and more. Tools run automatically when the agent decides they are needed; you don’t have to ask explicitly.Which tools are available depends on how your administrator has configured the gateway. Some tools (like shell execution and browser control) require explicit opt-in.
Common tools
Web search
The agent can search the web for current information. Just ask naturally:“What is the current price of NVDA stock?” “Find the latest Node.js release notes.”Search tools: Brave Search, Perplexity, and others depending on your deployment.
Code execution
The agent can write and run code, showing you the output:“Write a Python script to parse this CSV and find the top 10 values.” “Run this shell command and tell me what the output means.”Code execution may require administrator approval depending on your security policy.
File access
On channels where file tools are enabled, the agent can read and write files on the gateway host:
“Read my notes.txt file and summarise it.”
“Create a new Markdown file with the outline we just discussed.”
Browser
When browser tools are enabled, the agent can navigate websites, fill forms, take screenshots, and extract information:“Go to example.com and extract the pricing table.” “Take a screenshot of my dashboard.”
Memory
The agent maintains session memory — it remembers what you said earlier in a conversation. For long-running context across sessions, ask the agent to remember something:“Remember that my preferred language is TypeScript.” “What did I tell you about my project last week?”
Cron / scheduling
Schedule tasks to run at a later time:“Remind me in 2 hours to follow up on the Jenkins build.” “Run this command every day at 9am.”
How tools work
Tools run automatically — the agent decides when to use them based on your request. If a tool requires your approval (for example, shell execution withask=on), the agent will pause and ask before running.
To see what tools are active:
Tool output
By default, the agent summarises tool results in its reply. To see the full output:Requesting specific tools
You can ask the agent to use a specific tool or approach:“Search the web for this, don’t use your training data.” “Use the browser to check that URL for me.”The agent will use the tool if it is available and you have permission.