# Spend less on recurring work Source: https://www.hyperagent.com/docs/guides/save-on-recurring-work > For AI agents: the documentation index is at https://www.hyperagent.com/llms.txt and the complete documentation in one file at https://www.hyperagent.com/llms-full.txt. Any docs page is also served as Markdown by appending `.md` to its URL. Build a reliable workflow, save it in skills, and use a lower-cost model to run it again. A daily brief does not always need the same model as a difficult planning session. Use a powerful model to develop the process, save what works in skills, then test a lower-cost model for the work your agent repeats. Your agent's [model](https://www.hyperagent.com/docs/concepts/agents/models), [system prompt](https://www.hyperagent.com/docs/concepts/agents/configuration), [skill instructions, and scripts](https://www.hyperagent.com/docs/concepts/skills#anatomy-of-a-skill) each have a different role. You can keep a tested method and change the model that carries it out. Start with one familiar workflow so you can judge both the result and the savings. Save the method and script, then reuse them with a lower-cost model. Costs are illustrative, not measured results or a guarantee of equal quality. A finished Daily Brief appears with an illustrative cost of $0.74 per run. The reusable Daily Briefing skill and build\_report.py script appear next. The schedule’s model changes to Gemini 3.8 Flash. A week later, a new brief appears with an illustrative cost of $0.12. The two results sit side by side: First run and Saved method + script. ## Let Hyperagent choose the model for you [#let-hyperagent-choose-the-model-for-you] Open your agent's [**Model settings**](https://www.hyperagent.com/docs/concepts/agents/models#set-the-usual-model-change-it-when-needed) and choose **Auto** to let Hyperagent select a model for each message. You can ask for a quick summary, then work through a difficult decision without choosing a model before each request. This sets the agent's default for new work. Existing conversations keep their own model selection. Your Auto profile guides the choice: Prioritize lower-cost models for routine work with clear requirements. Match the model to everyday research, drafting, and tool use. Favor the most capable models, with higher cost as the tradeoff. Start with **Low cost** for routine work with clear requirements. Review the result and use a more capable option when the task needs it. See [Models and compute](https://www.hyperagent.com/docs/concepts/agents/models) for the controls. Choose **Auto → Low cost** to use your [free allowance](https://www.hyperagent.com/docs/billing/plans/free-plan) for included work. Selecting a specific model does not use that allowance. If you already pay for ChatGPT, you can also [connect ChatGPT](https://www.hyperagent.com/docs/billing/plans/connect-chatgpt-subscription) to cover supported GPT model usage when subscription sharing is available for your account. ## Give your agent a process it can repeat [#give-your-agent-a-process-it-can-repeat] Use a powerful model to work through a job until you have a result you trust. Then ask Hyperagent to save the method as a [skill](https://www.hyperagent.com/docs/concepts/skills) and [attach it to your agent](https://www.hyperagent.com/docs/concepts/skills#how-skills-enter-a-thread). The next run can follow that method instead of working out the process again. Keep the agent's ongoing responsibility and standards in its [system prompt](https://www.hyperagent.com/docs/concepts/agents/configuration). Use the skill's instructions for the specific job: where to get information, what steps to follow, and what a finished result should contain. This gives a lower-cost model a clearer path to a useful result. Make the method concrete Say when to use the skill and what inputs it needs. Name the sources, comparison period, and steps in order. Define the result: sections, format, source links, and checks. Explain what to do when data is missing or a check fails. Tell the agent which script to run, what to pass in, and how to check its result. Leave the process to guesswork Rely on vague requests such as “make a great report.” Copy the entire conversation into the instructions. Hard-code today's figures or a one-off date into a reusable method. Duplicate the agent's system prompt or add conflicting rules. Ask the model to rewrite code or HTML that a saved script can generate. Use the latest sales export and the previous day's export. Include revenue, order count, and the biggest changes, with links to the sources. Check for missing dates and duplicate order IDs before comparing results. If either export is missing, report the gap instead of estimating the figures. Deliver the brief as a webpage. Save the method and checks in the skill’s instructions. ## Let scripts do the computer work [#let-scripts-do-the-computer-work] Once the method works, look for parts the agent can execute as code. A skill can include [saved scripts alongside its instructions](https://www.hyperagent.com/docs/concepts/skills#anatomy-of-a-skill). Those scripts run in the [thread's sandboxed execution environment](https://www.hyperagent.com/docs/tools/data-and-code), giving the agent a computer where it can process files, calculate figures, and build the finished output. For the daily brief, save a script that validates the exports, calculates the totals, and generates the [HTML webpage](https://www.hyperagent.com/docs/tools/webpages-and-slides). The model supplies the analysis and recommendations; the script handles the data processing and layout. Each morning, the agent runs the saved code with fresh inputs instead of generating that code and HTML again. Keep reusable calculations and page-building code alongside the instructions. The skill instructions tell the agent when to run the script, which inputs to supply, and how to check the result. Have the script save the webpage as a file and return a short summary. The model still uses tokens to call the script and read its results, but it does not need the full HTML returned to its context. Review the proposed changes and test them with both complete and missing inputs. Once the skill produces a reliable result, try a lower-cost model for the recurring run. Keep a more capable model available for improving the process or handling difficult exceptions. ## Give scheduled work its own model [#give-scheduled-work-its-own-model] You can keep a powerful model for developing the workflow and use a cheaper model for its scheduled runs. A schedule's model choice does not change the agent's model everywhere. [Edit the schedule](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#create-and-configure-a-schedule) and review its model setting. Choose a lower-cost model to test, keeping the timing and instructions unchanged. Use the comparison below to check that it meets your requirements. See [Choose a model for scheduled runs](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#choose-a-model-for-scheduled-runs). Open the schedule's **advanced settings** and choose its **Model**. Keep the message, timing, and delivery destination the same while you compare models. Choose a model for this schedule under Advanced. Keep the message and timing consistent while comparing models. Use a powerful model to improve the briefing instructions and report-building script. Once the process works, use a lower-cost model for the morning schedule. The scheduled run follows the saved method, runs the scripts, and prepares the brief with fresh information. The [thread strategy](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#choose-a-thread-strategy) affects what happens afterward. When a schedule starts a new thread, that thread keeps the selected model. When it continues an existing thread, the schedule's model applies to that run; the thread keeps its own model for other work. Before testing, check the [delivery destination](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#deliver-results) and [actions the workflow can take](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#integration-writes-and-approvals). Use a draft destination if the normal run sends messages or updates connected data. ## Put it into practice [#put-it-into-practice] With the method saved, choose [**Manual**](https://www.hyperagent.com/docs/concepts/agents/models#choose-a-model-in-manual) in the model picker and try a lower-cost option from the [supported model catalog](https://www.hyperagent.com/docs/concepts/agents/models#supported-model-catalog). [Grok](https://www.hyperagent.com/docs/concepts/agents/models#grok), [Gemini Flash](https://www.hyperagent.com/docs/concepts/agents/models#gemini), and [Muse Spark](https://www.hyperagent.com/docs/concepts/agents/models#meta) are alternatives to consider when available on your plan. Compare the specific model's cost, rather than assuming every model in a family costs the same. ### Compare model token rates [#compare-model-token-rates] Intelligence source: Artificial Analysis comparisons for Opus and Grok and Gemini and Muse . ### Test the result [#test-the-result] Keep the inputs, instructions, skills, and output requirements the same during the comparison. ### Save a result you trust [#save-a-result-you-trust] Keep a good example and record [the completed run's usage](https://www.hyperagent.com/docs/billing/invoices#what-one-thread-cost). This gives you something concrete to compare against. ### Run the same task with the alternative [#run-the-same-task-with-the-alternative] Check facts, sources, calculations, required sections, and formatting. Include a case with missing information or an unusual result. ### Compare the work you can actually use [#compare-the-work-you-can-actually-use] Review several runs. Include corrections and retries when comparing cost. Keep the cheaper option if it consistently meets your requirements. Check [usage](https://www.hyperagent.com/docs/billing/invoices) rather than relying only on the model's token price. A cheaper model can cost more overall if it takes repeated attempts to finish the job. ## FAQs [#faqs] No. You can keep the same skills and instructions when comparing models. Check that the selected model supports the [tools your workflow needs](https://www.hyperagent.com/docs/tools), then test the result before relying on it. That depends on the workflow, model, amount of information, and retries. Compare several completed runs against the same requirements. Scripts can reduce repeated calculations and generated formatting, but the model still does work to read information, make decisions, and use tools. No. Auto chooses a model; it is not a spending limit. Use [Billing](https://hyperagent.com/settings/billing) to review your usage, credit, and auto-recharge settings. See [Control your costs](https://www.hyperagent.com/docs/billing/control-costs) for billing controls.