Turn a promising Hermes setup into a workflow your team can use. Agree what it should do, connect the right context, and put the runtime, permissions, and support around it before expanding its role.
Installing the agent is the starting point. Make the delegated work, access, and responsibility clear so the system has a useful place in your operation.
It works when its creator is there. Nobody has agreed how the team will access it, what happens when it stops, or who maintains it.
The agent has tools, but your records, procedures, and approval rules are still outside its reach.
The task worked once. Skills, permissions, difficult cases, and changes still need a review process before the team can depend on it.
Choose a task that fits the framework and your operating requirements. These are illustrative starting points to assess before agreeing a build.
Someone repeatedly gathers context from agreed sources and writes a summary for another person to use.
Read approved sources, assemble a briefing with references, and send uncertain or conflicting details to the reviewer.
Preparation time, source accuracy, and corrections before the briefing is used.
The work follows a recognizable procedure, but each run requires context and tools from several places.
Apply a reviewed procedure to one request, use only the permitted tools, and return a result that its owner can inspect.
Completion quality, manual intervention, and consistent handling of exceptions.
Useful checks happen only when somebody remembers to run them and assemble the result.
Run an agreed check on a schedule, record the outcome, and route exceptions to a named person.
Missed checks, useful alerts, and the effort required to review each run.
We agree the deployment and responsibilities around the job. The framework provides capabilities; the implementation makes them fit your environment.
Choose one task, its owner, and what a useful result looks like. Check whether Hermes fits the job.
Set the hosting, permitted tools, data boundaries, and support responsibilities before connecting business records.
Configure the runtime and reviewed skills. Show working results to your team each week.
Try incomplete context, tool failures, unexpected requests, and the pause or recovery path.
Start with a defined user group and reviewed results. Make access, escalation, and ownership clear.
Track result quality, intervention, and running costs. Extend the job only after the first workflow earns its place.
A senior engineering team on a monthly basis, sized to how fast you want to move. Any tier can work through the same roadmap. A smaller team takes more months; a larger team moves more of it forward at once.
An agreed first release, then weekly progress
Work through the roadmap in priority order at a steady monthly budget.
An agreed first release, then weekly progress
Add capacity to move the build, integrations, and rollout forward together.
An agreed first release, then weekly progress
Bring more capacity to a tighter timeline or several connected workstreams.
Three-month minimum, thirty days' notice. You own the code from the first commit. Model usage and third-party tool fees are separate. We estimate these against the workflow and agree budgets before rollout.
You own the repository, prompts, and workflow-specific tests we build for you. We document how the system works so another team can maintain it.
Agree who owns each model, cloud, and integration account. Keep usage, credentials, and access responsibilities visible to your business.
Hosting, monitoring, backups, and security updates are included while we work together. Agree who reviews exceptions and how support continues after handover.
Define what the system can read and change, what it logs, and how long records are kept. Review provider terms and specialist requirements before using sensitive information.
Runs discovery and architecture on every project and writes code on all of them. Built Agency ERP, Arlo, and Ollie for our own operations first.
Owns the data model, migrations, and integrations. The person who makes QuickBooks, Stripe, and your spreadsheets agree with each other.
Builds the product surface: the screens your team uses every day, the permissions behind them, and the tests that keep them working.
Clear answers on timelines, pricing, ownership, and what shipping actually looks like with a senior engineering team.
Hermes Agent is an open-source agent project by Nous Research. Its documented capabilities include tools, skills, memory, messaging access, and scheduled tasks. We assess the current release against your workflow before recommending a deployment.
We provide independent implementation services. Hermes Agent is Nous Research’s project; our work is to assess, configure, integrate, and support a setup around your business requirements.
We start with the job, available context, and operating requirements. If a simpler automation or an existing tool meets the need, that may be a better choice. A framework is a means of delivering the workflow, not the reason to build it.
Not necessarily. Model calls and connected services may send data to external providers. We map those flows, review account and retention settings, and agree which records the workflow may use.
That is part of the operating plan. We agree who can change procedures and permissions, what needs approval, and which checks run before a change reaches daily use.
Engineering retainers start at $7k per month, with $13k and $18k+ options for more delivery capacity. The tier sets the pace through an agreed roadmap. There is a three-month minimum and thirty days’ notice. Model usage and third-party service fees are separate.
We target a useful first workflow in 3–4 weeks once scope, access, and data are ready. We review working software each week. The time to wider rollout depends on integrations, testing, and the people who will use it.
You own the custom code, prompts, and workflow-specific tests we create for you. Your accounts and access responsibilities are agreed up front. Third-party platforms and open-source frameworks retain their own licenses.
Tell us what you're building or fixing. We'll come prepared with questions, not a pitch, and you'll leave the call with a straight answer on fit, which tier, and how soon you'd have version one in your hands.
Or email hello@buildfutur.com