Usage Tips

Practical tips for getting the most out of your usage.

Working efficiently in Odeus means using your AI resources wisely. Whether you're chatting with models, building agents, running workflows, or integrating with your existing tools, a few simple habits help you get better results while staying within your usage allowance.

General best practices

Use lighter models for routine work and stronger models for complex analysis, planning, or creative work. See the Model Guide for full recommendations.

• Provide clear instructions, include relevant context, and specify the format you'd like. Be careful with large files: the bigger the document, the more of your usage each message consumes. When possible, reference specific sections rather than entire documents.
• Before starting a conversation, take a moment to think about what you actually need. Can you combine related questions into a single message? Which information does the model need to understand your request right away?
• Take a quick look at your message before hitting send. A few seconds of review can prevent unnecessary follow-up messages and wasted usage.

These best practices apply everywhere in Odeus. The sections below cover additional practices per feature.

Chat

Conversations accumulate cost as they grow. A few habits keep things efficient:

• Start a new conversation when you move to a new topic. The model processes the full history on every message, so long conversations get expensive fast.
• Not happy with a response or made a mistake? Edit your original prompt to refine it rather than writing a new message from scratch. This keeps your conversation concise.
• Save prompts that work well to your prompt library. Reusing a well-crafted prompt is almost always better than starting from scratch.
• Constrain the output length with a simple instruction such as "Max 5 bullet points" or "Use at most 50 words". This forces the model to prioritize what matters most, saving tokens and usually producing a sharper answer.
• Pick the right model for the task before you start. Each conversation runs on one model, so choosing a lighter model for routine work keeps usage down.

Agents

A well-built agent saves your team from explaining the same context over and over. A few things that make a real difference:

• Create more specific agents. Configure clear system instructions, attach only the relevant knowledge, and define constraints to produce accurate results.
• If your most-used agents are running users into limits, consider pinning a more resource-efficient model and refining the prompt.
• If you're repeatedly setting up the same context in chat, that's a sign you should create a dedicated agent instead. Agents retain their configuration across conversations.
• When you build an agent that works well, share it with your workspace. This prevents multiple team members from each spending usage to set up equivalent configurations.

Deep Research

Deep Research can run multi-step research and cite its sources, which uses more resources than a normal chat message.

• Choose the depth that fits the task. Use Quick or Standard for focused questions and save Deep for genuinely broad research.
• You can choose the models Deep Research uses per run. Pick lighter models when the task does not need frontier reasoning.

Workflows

Every step in a workflow adds to the cost, so it pays to keep things simple:

• Design efficient workflows by minimizing unnecessary steps and combining operations instead of chaining many small ones.
• Add conditions early in your workflow to skip branches that don't apply, rather than processing everything and filtering at the end.
• Not every step needs a frontier model. Use more resource-efficient models for simple extraction or formatting steps.
• If your workflow is triggered by events (form submissions, schedules), make sure the trigger conditions are specific enough to avoid unnecessary runs.

Need more usage?

If you're regularly hitting limits, talk to your admin about upgrading your plan for higher included usage, or enabling Extra Usage so you can keep working with all models beyond your included allocation.