Customising your agents in the AI Center
Choose the model each agent runs on, connect your own AI accounts, and give the agents your instructions, knowledge and skills.
Providers and models
The AI Center lists the AI providers and models available to Stratmill agents and shows which are available right now. The Research Lead, Strategy Developer, QA Agent, Strategy Analyst, Risk Officer and Portfolio Manager each run on the platform default unless you pick another model; a model that is unavailable falls back to the default automatically. The Ask AI assistant's model is chosen in its chat box. The platform's own prompts are never changed by your choices.
Your own keys and sign-in
You can connect your own AI provider account, either with an API key or by signing in with that provider's own sign-in flow. Keys are encrypted at rest and only a masked hint is shown after saving. When you have connected an account, calls for your workspace use your key first, then your signed-in account, then the platform's own access. If a provider cannot be used on the server, its card says so and calls fall back to another route.
Standing instructions
Customise an agent to add standing instructions, up to 2,000 characters: text added to that agent's prompt on every call in your workspace. Use it for preferences the agent should always respect, such as a venue, a timeframe, a leverage ceiling or a style of hypothesis.
Knowledge files
Upload reference files on the Knowledge tab: notes, research, playbooks, data sheets, in text, Markdown, CSV, JSON, PDF, Word, EPUB or HTML, up to 50 files. The text is extracted once and shown back to you, then attached to any agent with a switch. Attached files are inlined into the agent's prompt, within a size limit per file and per call.
Skills
A skill is a reusable procedure with a name, a one-line description of when it applies, and step-by-step instructions in Markdown. Write up to 50 skills on the Skills tab or import a Markdown file, then attach them to agents. The agent applies a skill when the task matches its description.
Where it applies
Instructions, knowledge and skills apply to every pipeline call for your runs and to the assistant's replies to you. They refine the platform rules and never lift a safety, fee, venue, risk or output-format rule.